Convolutional Neural Network (CNN)-based accurate prediction typically
requires large-scale annotated training data. In Medical Imaging, however, both
obtaining medical data and annotating them by expert physicians are
challenging; to overcome this lack of data, Data Augmentation (DA) using
Generative Adversarial Networks (GANs) is essential, since they can synthesize
additional annotated training data to handle small and fragmented medical
images from various scanners--those generated images, realistic but completely
novel, can further fill the real image distribution uncovered by the original
dataset. As a tutorial, this paper introduces GAN-based Medical Image
Augmentation, along with tricks to boost classification/object
detection/segmentation performance using them, based on our experience and
related work. Moreover, we show our first GAN-based DA work using automatic
bounding box annotation, for robust CNN-based brain metastases detection on 256
x 256 MR images; GAN-based DA can boost 10% sensitivity in diagnosis with a
clinically acceptable number of additional False Positives, even with
highly-rough and inconsistent bounding boxes.
PURPOSE: The medical literature relevant to germline genetics is growing
exponentially. Clinicians need tools monitoring and prioritizing the literature
to understand the clinical implications of the pathogenic genetic variants. We
developed and evaluated two machine learning models to classify abstracts as
relevant to the penetrance (risk of cancer for germline mutation carriers) or
prevalence of germline genetic mutations. METHODS: We conducted literature
searches in PubMed and retrieved paper titles and abstracts to create an
annotated dataset for training and evaluating the two machine learning
classification models. Our first model is a support vector machine (SVM) which
learns a linear decision rule based on the bag-of-ngrams representation of each
title and abstract. Our second model is a convolutional neural network (CNN)
which learns a complex nonlinear decision rule based on the raw title and
abstract. We evaluated the performance of the two models on the classification
of papers as relevant to penetrance or prevalence. RESULTS: For penetrance
classification, we annotated 3740 paper titles and abstracts and used 60% for
training the model, 20% for tuning the model, and 20% for evaluating the model.
The SVM model achieves 89.53% accuracy (percentage of papers that were
correctly classified) while the CNN model achieves 88.95 % accuracy. For
prevalence classification, we annotated 3753 paper titles and abstracts. The
SVM model achieves 89.14% accuracy while the CNN model achieves 89.13 %
accuracy. CONCLUSION: Our models achieve high accuracy in classifying abstracts
as relevant to penetrance or prevalence. By facilitating literature review,
this tool could help clinicians and researchers keep abreast of the burgeoning
knowledge of gene-cancer associations and keep the knowledge bases for clinical
decision support tools up to date.
The Hausdorff Distance (HD) is widely used in evaluating medical image
segmentation methods. However, existing segmentation methods do not attempt to
reduce HD directly. In this paper, we present novel loss functions for training
convolutional neural network (CNN)-based segmentation methods with the goal of
reducing HD directly. We propose three methods to estimate HD from the
segmentation probability map produced by a CNN. One method makes use of the
distance transform of the segmentation boundary. Another method is based on
applying morphological erosion on the difference between the true and estimated
segmentation maps. The third method works by applying circular/spherical
convolution kernels of different radii on the segmentation probability maps.
Based on these three methods for estimating HD, we suggest three loss functions
that can be used for training to reduce HD. We use these loss functions to
train CNNs for segmentation of the prostate, liver, and pancreas in ultrasound,
magnetic resonance, and computed tomography images and compare the results with
commonly-used loss functions. Our results show that the proposed loss functions
can lead to approximately 18-45 % reduction in HD without degrading other
segmentation performance criteria such as the Dice similarity coefficient. The
proposed loss functions can be used for training medical image segmentation
methods in order to reduce the large segmentation errors.
Evaluating the clinical similarities between pairwise patients is a
fundamental problem in healthcare informatics. A proper patient similarity
measure enables various downstream applications, such as cohort study and
treatment comparative effectiveness research. One major carrier for conducting
patient similarity research is Electronic Health Records(EHRs), which are
usually heterogeneous, longitudinal, and sparse. Though existing studies on
learning patient similarity from EHRs have shown being useful in solving real
clinical problems, their applicability is limited due to the lack of medical
interpretations. Moreover, most previous methods assume a vector-based
representation for patients, which typically requires aggregation of medical
events over a certain time period. As a consequence, temporal information will
be lost. In this paper, we propose a patient similarity evaluation framework
based on the temporal matching of longitudinal patient EHRs. Two efficient
methods are presented, unsupervised and supervised, both of which preserve the
temporal properties in EHRs. The supervised scheme takes a convolutional neural
network architecture and learns an optimal representation of patient clinical
records with medical concept embedding. The empirical results on real-world
clinical data demonstrate substantial improvement over the baselines. We make
our code and sample data available for further study.
The discovery of adversarial examples has raised concerns about the practical
deployment of deep learning systems. In this paper, we demonstrate that
adversarial examples are capable of manipulating deep learning systems across
three clinical domains. For each of our representative medical deep learning
classifiers, both white and black box attacks were highly successful. Our
models are representative of the current state of the art in medical computer
vision and, in some cases, directly reflect architectures already seeing
deployment in real world clinical settings. In addition to the technical
contribution of our paper, we synthesize a large body of knowledge about the
healthcare system to argue that medicine may be uniquely susceptible to
adversarial attacks, both in terms of monetary incentives and technical
vulnerability. To this end, we outline the healthcare economy and the
incentives it creates for fraud and provide concrete examples of how and why
such attacks could be realistically carried out. We urge practitioners to be
aware of current vulnerabilities when deploying deep learning systems in
clinical settings, and encourage the machine learning community to further
investigate the domain-specific characteristics of medical learning systems.
The training of medical image analysis systems using machine learning
approaches follows a common script: collect and annotate a large dataset, train
the classifier on the training set, and test it on a hold-out test set. This
process bears no direct resemblance with radiologist training, which is based
on solving a series of tasks of increasing difficulty, where each task involves
the use of significantly smaller datasets than those used in machine learning.
In this paper, we propose a novel training approach inspired by how
radiologists are trained. In particular, we explore the use of meta-training
that models a classifier based on a series of tasks. Tasks are selected using
teacher-student curriculum learning, where each task consists of simple
classification problems containing small training sets. We hypothesize that our
proposed meta-training approach can be used to pre-train medical image analysis
models. This hypothesis is tested on the automatic breast screening
classification from DCE-MRI trained with weakly labeled datasets. The
classification performance achieved by our approach is shown to be the best in
the field for that application, compared to state of art baseline approaches:
DenseNet, multiple instance learning and multi-task learning.
Machine Learning is an important sub-field of the Artificial Intelligence and
it has been become a very critical task to train Machine Learning techniques
via effective method or techniques. Recently, researchers try to use
alternative techniques to improve ability of Machine Learning techniques.
Moving from the explanations, objective of this study is to introduce a novel
SVM-CoDOA (Cognitive Development Optimization Algorithm trained Support Vector
Machines) system for general medical diagnosis. In detail, the system consists
of a SVM, which is trained by CoDOA, a newly developed optimization algorithm.
As it is known, use of optimization algorithms is an essential task to train
and improve Machine Learning techniques. In this sense, the study has provided
a medical diagnosis oriented problem scope in order to show effectiveness of
the SVM-CoDOA hybrid formation.
Typical personal medical data contains sensitive information about
individuals. Storing or sharing the personal medical data is thus often risky.
For example, a short DNA sequence can provide information that can not only
identify an individual, but also his or her relatives. Nonetheless, most
countries and researchers agree on the necessity of collecting personal medical
data. This stems from the fact that medical data, including genomic data, are
an indispensable resource for further research and development regarding
disease prevention and treatment. To prevent personal medical data from being
misused, techniques to reliably preserve sensitive information should be
developed for real world application. In this paper, we propose a framework
called anonymized generative adversarial networks (AnomiGAN), to improve the
maintenance of privacy of personal medical data, while also maintaining high
prediction performance. We compared our method to state-of-the-art techniques
and observed that our method preserves the same level of privacy as
differential privacy (DP), but had better prediction results. We also observed
that there is a trade-off between privacy and performance results depending on
the degree of preservation of the original data. Here, we provide a
mathematical overview of our proposed model and demonstrate its validation
using UCI machine learning repository datasets in order to highlight its
utility in practice. Experimentally, our approach delivers a better performance
compared to that of the DP approach.
Sequential decision making for lifetime maximization is a critical problem in
many real-world applications, such as medical treatment and portfolio
selection. In these applications, a `reneging' phenomenon, where participants
may disengage from future interactions after observing an unsatisfiable
outcome, is rather prevalent. To address the above issue, this paper proposes a
model of heteroscedastic linear bandits with reneging, which allows each
participant to have a distinct `satisfaction level,' with any interaction
outcome falling short of that level resulting in that participant reneging.
Moreover, it allows the variance of the outcome to be context-dependent. Based
on this model, we develop a UCB-type policy, namely HR-UCB, and prove that it
achieves \pch{$\mathcal{O}\big(\sqrt{{T}(\log({T}))^{3}}\big)$} regret.
Finally, we validate the performance of HR-UCB via simulations.
The principle of equivariance to symmetry transformations enables a
theoretically grounded approach to neural network architecture design.
Equivariant networks have shown excellent performance and data efficiency on
vision and medical imaging problems that exhibit symmetries. Here we show how
this principle can be extended beyond global symmetries to local gauge
transformations. This enables the development of a very general class of
convolutional neural networks on manifolds that depend only on the intrinsic
geometry, and which includes many popular methods from equivariant and
geometric deep learning. We implement gauge equivariant CNNs for signals
defined on the surface of the icosahedron, which provides a reasonable
approximation of the sphere. By choosing to work with this very regular
manifold, we are able to implement the gauge equivariant convolution using a
single conv2d call, making it a highly scalable and practical alternative to
Spherical CNNs. Using this method, we demonstrate substantial improvements over
previous methods on the task of segmenting omnidirectional images and global
climate patterns.
Among all physiological signals, electrocardiogram (ECG) has seen some of the
largest expansion in both medical and recreational applications with the rise
of single-lead versions. These versions are embedded in medical devices and
wearable products such as the injectable Medtronic Linq monitor, the iRhythm
Ziopatch wearable monitor, and the Apple Watch Series 4. Recently, deep neural
networks have been used to classify ECGs, outperforming even physicians
specialized in cardiac electrophysiology. However, deep learning classifiers
have been shown to be brittle to adversarial examples, including in
medical-related tasks. Yet, traditional attack methods such as projected
gradient descent (PGD) create examples that introduce square wave artifacts
that are not physiological. Here, we develop a method to construct smoothed
adversarial examples. We chose to focus on models learned on the data from the
2017 PhysioNet/Computing-in-Cardiology Challenge for single lead ECG
classification. For this model, we utilized a new technique to generate
smoothed examples to produce signals that are 1) indistinguishable to
cardiologists from the original examples 2) incorrectly classified by the
neural network. Further, we show that adversarial examples are not rare. Deep
neural networks that have achieved state-of-the-art performance fail to
classify smoothed adversarial ECGs that look real to clinical experts.
The emergence of real-time auction in online advertising has drawn huge
attention of modeling the market competition, i.e., bid landscape forecasting.
The problem is formulated as to forecast the probability distribution of market
price for each ad auction. With the consideration of the censorship issue which
is caused by the second-price auction mechanism, many researchers have devoted
their efforts on bid landscape forecasting by incorporating survival analysis
from medical research field. However, most existing solutions mainly focus on
either counting-based statistics of the segmented sample clusters, or learning
a parameterized model based on some heuristic assumptions of distribution
forms. Moreover, they neither consider the sequential patterns of the feature
over the price space. In order to capture more sophisticated yet flexible
patterns at fine-grained level of the data, we propose a Deep Landscape
Forecasting (DLF) model which combines deep learning for probability
distribution forecasting and survival analysis for censorship handling.
Specifically, we utilize a recurrent neural network to flexibly model the
conditional winning probability w.r.t. each bid price. Then we conduct the bid
landscape forecasting through probability chain rule with strict mathematical
derivations. And, in an end-to-end manner, we optimize the model by minimizing
two negative likelihood losses with comprehensive motivations. Without any
specific assumption for the distribution form of bid landscape, our model shows
great advantages over previous works on fitting various sophisticated market
price distributions. In the experiments over two large-scale real-world
datasets, our model significantly outperforms the state-of-the-art solutions
under various metrics.
Tree-based machine learning models such as random forests, decision trees,
and gradient boosted trees are the most popular non-linear predictive models
used in practice today, yet comparatively little attention has been paid to
explaining their predictions. Here we significantly improve the
interpretability of tree-based models through three main contributions: 1) The
first polynomial time algorithm to compute optimal explanations based on game
theory. 2) A new type of explanation that directly measures local feature
interaction effects. 3) A new set of tools for understanding global model
structure based on combining many local explanations of each prediction. We
apply these tools to three medical machine learning problems and show how
combining many high-quality local explanations allows us to represent global
structure while retaining local faithfulness to the original model. These tools
enable us to i) identify high magnitude but low frequency non-linear mortality
risk factors in the general US population, ii) highlight distinct population
sub-groups with shared risk characteristics, iii) identify non-linear
interaction effects among risk factors for chronic kidney disease, and iv)
monitor a machine learning model deployed in a hospital by identifying which
features are degrading the model's performance over time. Given the popularity
of tree-based machine learning models, these improvements to their
interpretability have implications across a broad set of domains.
Histopathology slides are routinely marked by pathologists using permanent
ink markers that should not be removed as they form part of the medical record.
Often tumour regions are marked up for the purpose of highlighting features or
other downstream processing such an gene sequencing. Once digitised there is no
established method for removing this information from the whole slide images
limiting its usability in research and study. Removal of marker ink from these
high-resolution whole slide images is non-trivial and complex problem as they
contaminate different regions and in an inconsistent manner. We propose an
efficient pipeline using convolution neural networks that results in ink-free
images without compromising information and image resolution. Our pipeline
includes a sequential classical convolution neural network for accurate
classification of contaminated image tiles, a fast region detector and a domain
adaptive cycle consistent adversarial generative model for restoration of
foreground pixels. Both quantitative and qualitative results on four different
whole slide images show that our approach yields visually coherent ink-free
whole slide images.
The dearth of prescribing guidelines for physicians is one key driver of the
current opioid epidemic in the United States. In this work, we analyze medical
and pharmaceutical claims data to draw insights on characteristics of patients
who are more prone to adverse outcomes after an initial synthetic opioid
prescription. Toward this end, we propose a generative model that allows
discovery from observational data of subgroups that demonstrate an enhanced or
diminished causal effect due to treatment. Our approach models these
sub-populations as a mixture distribution, using sparsity to enhance
interpretability, while jointly learning nonlinear predictors of the potential
outcomes to better adjust for confounding. The approach leads to
human-interpretable insights on discovered subgroups, improving the practical
utility for decision support
Recently, Deep Neural Networks (DNNs) have been achieving impressive results
on wide range of tasks. However, they suffer from being well-calibrated. In
decision-making applications, such as autonomous driving or medical diagnosing,
the confidence of deep networks plays an important role to bring the trust and
reliability to the system. To calibrate the deep networks' confidence, many
probabilistic and measure-based approaches are proposed. Temperature Scaling
(TS) is a state-of-the-art among measure-based calibration methods which has
low time and memory complexity as well as effectiveness. In this paper, we
study TS and show it does not work properly when the validation set that TS
uses for calibration has small size or contains noisy-labeled samples. TS also
cannot calibrate highly accurate networks as well as non-highly accurate ones.
Accordingly, we propose Attended Temperature Scaling (ATS) which preserves the
advantages of TS while improves calibration in aforementioned challenging
situations. We provide theoretical justifications for ATS and assess its
effectiveness on wide range of deep models and datasets. We also compare the
calibration results of TS and ATS on skin lesion detection application as a
practical problem where well-calibrated system can play important role in
making a decision.
Clinical diagnostic decision making and population-based studies often rely
on multi-modal data which is noisy and incomplete. Recently, several works
proposed geometric deep learning approaches to solve disease classification, by
modeling patients as nodes in a graph, along with graph signal processing of
multi-modal features. Many of these approaches are limited by assuming
modality- and feature-completeness, and by transductive inference, which
requires re-training of the entire model for each new test sample. In this
work, we propose a novel inductive graph-based approach that can generalize to
out-of-sample patients, despite missing features from entire modalities per
patient. We propose multi-modal graph fusion which is trained end-to-end
towards node-level classification. We demonstrate the fundamental working
principle of this method on a simplified MNIST toy dataset. In experiments on
medical data, our method outperforms single static graph approach in
multi-modal disease classification.
Artificial intelligence (AI) researchers claim that they have made great
`achievements' in clinical realms. However, clinicians point out the so-called
`achievements' have no ability to implement into natural clinical settings. The
root cause for this huge gap is that many essential features of natural
clinical tasks are overlooked by AI system developers without medical
background. In this paper, we propose that the clinical benchmark suite is a
novel and promising direction to capture the essential features of the
real-world clinical tasks, hence qualifies itself for guiding the development
of AI systems, promoting the implementation of AI in real-world clinical
practice.
Great performances of deep learning are undeniable, with impressive results
on wide range of tasks. However, the output confidence of these models is
usually not well calibrated, which can be an issue for applications where
confidence on the decisions is central to bring trust and reliability (e.g.,
autonomous driving or medical diagnosis). For models using softmax at the last
layer, Temperature Scaling (TS) is a state-of-the-art calibration method, with
low time and memory complexity as well as demonstrated effectiveness.TS relies
on a T parameter to rescale and calibrate values of the softmax layer, using a
labelled dataset to determine the value of that parameter.We are proposing an
Unsupervised Temperature Scaling (UTS) approach, which does not dependent on
labelled samples to calibrate the model,allowing, for example, using a part of
test samples for calibrating the pre-trained model before going into inference
mode. We provide theoretical justifications for UTS and assess its
effectiveness on the wide range of deep models and datasets. We also
demonstrate calibration results of UTS on skin lesion detection, a problem
where a well-calibrated output can play an important role for accurate
decision-making.
Clinical decision making is challenging because of pathological complexity,
as well as large amounts of heterogeneous data generated as part of routine
clinical care. In recent years, machine learning tools have been developed to
aid this process. Intensive care unit (ICU) admissions represent the most data
dense and time-critical patient care episodes. In this context, prediction
models may help clinicians determine which patients are most at risk and
prioritize care. However, flexible tools such as artificial neural networks
(ANNs) suffer from a lack of interpretability limiting their acceptability to
clinicians. In this work, we propose a novel interpretable Bayesian neural
network architecture which offers both the flexibility of ANNs and
interpretability in terms of feature selection. In particular, we employ a
sparsity inducing prior distribution in a tied manner to learn which features
are important for outcome prediction. We evaluate our approach on the task of
mortality prediction using two real-world ICU cohorts. In collaboration with
clinicians we found that, in addition to the predicted outcome results, our
approach can provide novel insights into the importance of different clinical
measurements. This suggests that our model can support medical experts in their
decision making process.
With the arrival of the big data era, more and more data are becoming readily
available in various real-world applications and those data are usually highly
heterogeneous. Taking computational medicine as an example, we have both
Electronic Health Records (EHR) and medical images for each patient. For
complicated diseases such as Parkinson's and Alzheimer's, both EHR and
neuroimaging information are very important for disease understanding because
they contain complementary aspects of the disease. However, EHR and neuroimage
are completely different. So far the existing research has been mainly focusing
on one of them. In this paper, we proposed a framework, Memory-Based Graph
Convolution Network (MemGCN), to perform integrative analysis with such
multi-modal data. Specifically, GCN is used to extract useful information from
the patients' neuroimages. The information contained in the patient EHRs before
the acquisition of each brain image is captured by a memory network because of
its sequential nature. The information contained in each brain image is
combined with the information read out from the memory network to infer the
disease state at the image acquisition timestamp. To further enhance the
analytical power of MemGCN, we also designed a multi-hop strategy that allows
multiple reading and updating on the memory can be performed at each iteration.
We conduct experiments using the patient data from the Parkinson's Progression
Markers Initiative (PPMI) with the task of classification of Parkinson's
Disease (PD) cases versus controls. We demonstrate that superior classification
performance can be achieved with our proposed framework, comparing with
existing approaches involving a single type of data.
Clustering is an essential technique for discovering patterns in data. The
steady increase in amount and complexity of data over the years led to
improvements and development of new clustering algorithms. However, algorithms
that can cluster data with mixed variable types (continuous and categorical)
remain limited, despite the abundance of data with mixed types particularly in
the medical field. Among existing methods for mixed data, some posit
unverifiable distributional assumptions or that the contributions of different
variable types are not well balanced.
We propose a two-step hybrid density- and partition-based algorithm (HyDaP)
that can detect clusters after variables selection. The first step involves
both density-based and partition-based algorithms to identify the data
structure formed by continuous variables and recognize the important variables
for clustering; the second step involves partition-based algorithm together
with a novel dissimilarity measure we designed for mixed data to obtain
clustering results. Simulations across various scenarios and data structures
were conducted to examine the performance of the HyDaP algorithm compared to
commonly used methods. We also applied the HyDaP algorithm on electronic health
records to identify sepsis phenotypes.
The predictive performance of supervised learning algorithms depends on the
quality of labels. In a typical label collection process, multiple annotators
provide subjective noisy estimates of the "truth" under the influence of their
varying skill-levels and biases. Blindly treating these noisy labels as the
ground truth limits the accuracy of learning algorithms in the presence of
strong disagreement. This problem is critical for applications in domains such
as medical imaging where both the annotation cost and inter-observer
variability are high. In this work, we present a method for simultaneously
learning the individual annotator model and the underlying true label
distribution, using only noisy observations. Each annotator is modeled by a
confusion matrix that is jointly estimated along with the classifier
predictions. We propose to add a regularization term to the loss function that
encourages convergence to the true annotator confusion matrix. We provide a
theoretical argument as to how the regularization is essential to our approach
both for the case of single annotator and multiple annotators. Despite the
simplicity of the idea, experiments on image classification tasks with both
simulated and real labels show that our method either outperforms or performs
on par with the state-of-the-art methods and is capable of estimating the
skills of annotators even with a single label available per image.
Multiple Instance Learning (MIL) is a weak supervision learning paradigm that
allows modeling of machine learning problems in which labels are available only
for groups of examples called bags. A positive bag may contain one or more
positive examples but it is not known which examples in the bag are positive.
All examples in a negative bag belong to the negative class. Such problems
arise frequently in fields of computer vision, medical image processing and
bioinformatics. Many neural network based solutions have been proposed in the
literature for MIL, however, almost all of them rely on introducing specialized
blocks and connectivity in the architectures. In this paper, we present a novel
and effective approach to Multiple Instance Learning in neural networks.
Instead of making changes to the architectures, we propose a simple bag-level
ranking loss function that allows Multiple Instance Classification in any
neural architecture. We have demonstrated the effectiveness of our proposed
method for popular MIL benchmark datasets. In addition, we have tested the
performance of our method in convolutional neural networks used to model an MIL
problem derived from the well-known MNIST dataset. Results have shown that
despite being simpler, our proposed scheme is comparable or better than
existing methods in the literature in practical scenarios. Python code files
for all the experiments can be found at https://github.com/amina01/ESMIL.
The tongue image provides important physical information of humans. It is of
great importance for diagnoses and treatments in clinical medicine. Herbal
prescriptions are simple, noninvasive and have low side effects. Thus, they are
widely applied in China. Studies on the automatic construction technology of
herbal prescriptions based on tongue images have great significance for deep
learning to explore the relevance of tongue images for herbal prescriptions, it
can be applied to healthcare services in mobile medical systems. In order to
adapt to the tongue image in a variety of photographic environments and
construct herbal prescriptions, a neural network framework for prescription
construction is designed. It includes single/double convolution channels and
fully connected layers. Furthermore, it proposes the auxiliary therapy topic
loss mechanism to model the therapy of Chinese doctors and alleviate the
interference of sparse output labels on the diversity of results. The
experiment use the real world tongue images and the corresponding prescriptions
and the results can generate prescriptions that are close to the real samples,
which verifies the feasibility of the proposed method for the automatic
construction of herbal prescriptions from tongue images. Also, it provides a
reference for automatic herbal prescription construction from more physical
information.
The electrocardiogram (ECG) is a widely-used medical test, typically
consisting of 12 voltage versus time traces collected from surface recordings
over the heart. Here we hypothesize that a deep neural network can predict an
important future clinical event (one-year all-cause mortality) from ECG
voltage-time traces. We show good performance for predicting one-year mortality
with an average AUC of 0.85 from a model cross-validated on 1,775,926 12-lead
resting ECGs, that were collected over a 34-year period in a large regional
health system. Even within the large subset of ECGs interpreted as 'normal' by
a physician (n=297,548), the model performance to predict one-year mortality
remained high (AUC=0.84), and Cox Proportional Hazard model revealed a hazard
ratio of 6.6 (p<0.005) for the two predicted groups (dead vs alive one year
after ECG) over a 30-year follow-up period. A blinded survey of three
cardiologists suggested that the patterns captured by the model were generally
not visually apparent to cardiologists even after being shown 240 paired
examples of labeled true positives (dead) and true negatives (alive). In
summary, deep learning can add significant prognostic information to the
interpretation of 12-lead resting ECGs, even in cases that are interpreted as
'normal' by physicians.
The recent adoption of Electronic Health Records (EHRs) by health care
providers has introduced an important source of data that provides detailed and
highly specific insights into patient phenotypes over large cohorts. These
datasets, in combination with machine learning and statistical approaches,
generate new opportunities for research and clinical care. However, many
methods require the patient representations to be in structured formats, while
the information in the EHR is often locked in unstructured texts designed for
human readability. In this work, we develop the methodology to automatically
extract clinical features from clinical narratives from large EHR corpora
without the need for prior knowledge. We consider medical terms and sentences
appearing in clinical narratives as atomic information units. We propose an
efficient clustering strategy suitable for the analysis of large text corpora
and to utilize the clusters to represent information about the patient
compactly. To demonstrate the utility of our approach, we perform an
association study of clinical features with somatic mutation profiles from
4,007 cancer patients and their tumors. We apply the proposed algorithm to a
dataset consisting of about 65 thousand documents with a total of about 3.2
million sentences. We identify 341 significant statistical associations between
the presence of somatic mutations and clinical features. We annotated these
associations according to their novelty, and report several known associations.
We also propose 32 testable hypotheses where the underlying biological
mechanism does not appear to be known but plausible. These results illustrate
that the automated discovery of clinical features is possible and the joint
analysis of clinical and genetic datasets can generate appealing new
hypotheses.
Odor identification is an important area in a wide range of industries like
cosmetics, food, beverages and medical diagnosis among others. Odor detection
could be done through an array of gas sensors conformed as an electronic nose
where a data acquisition module converts sensor signals to a standard output to
be analyzed. To facilitate odors detection a system is required for the
identification. This paper presents the results of an automated odor
identification process implemented by a fuzzy system and an electronic nose.
First, an electronic nose prototype is manufactured to detect organic compounds
vapor using an array of five tin dioxide gas sensors, an arduino uno board is
used as a data acquisition section. Second, an intelligent module with a fuzzy
system is considered for the identification of the signals received by the
electronic nose. This solution proposes a system to identify odors by using a
personal computer. Results show an acceptable precision.
State-of-the-art named entity recognition (NER) systems have been improving
continuously using neural architectures over the past several years. However,
many tasks including NER require large sets of annotated data to achieve such
performance. In particular, we focus on NER from clinical notes, which is one
of the most fundamental and critical problems for medical text analysis. Our
work centers on effectively adapting these neural architectures towards
low-resource settings using parameter transfer methods. We complement a
standard hierarchical NER model with a general transfer learning framework
consisting of parameter sharing between the source and target tasks, and
showcase scores significantly above the baseline architecture. These sharing
schemes require an exponential search over tied parameter sets to generate an
optimal configuration. To mitigate the problem of exhaustively searching for
model optimization, we propose the Dynamic Transfer Networks (DTN), a gated
architecture which learns the appropriate parameter sharing scheme between
source and target datasets. DTN achieves the improvements of the optimized
transfer learning framework with just a single training setting, effectively
removing the need for exponential search.
The opioid epidemic in the United States claims over 40,000 lives per year,
and it is estimated that well over two million Americans have an opioid use
disorder. Over-prescription and misuse of prescription opioids play an
important role in the epidemic. Individuals who are prescribed opioids, and who
are diagnosed with opioid use disorder, have diverse underlying health states.
Policy interventions targeting prescription opioid use, opioid use disorder,
and overdose often fail to account for this variation. To identify latent
health states, or phenotypes, pertinent to opioid use and opioid use disorders,
we use probabilistic topic modeling with medical diagnosis histories from a
statewide population of individuals who were prescribed opioids. We demonstrate
that our learned phenotypes are predictive of future opioid use-related
outcomes. In addition, we show how the learned phenotypes can provide important
context for variability in opioid prescriptions. Understanding the
heterogeneity in individual health states and in prescription opioid use can
help identify policy interventions to address this public health crisis.
Generalized linear models (GLM) are link function based statistical models.
Many supervised learning algorithms are extensions of GLMs and have link
functions built into the algorithm to model different outcome distributions.
There are two major drawbacks when using this approach in applications using
real world datasets. One is that none of the link functions available in the
popular packages is a good fit for the data. Second, it is computationally
inefficient and impractical to test all the possible distributions to find the
optimum one. In addition, many GLMs and their machine learning extensions
struggle on problems of overdispersion in Tweedie distributions. In this paper
we propose a quantum extension to GLM that overcomes these drawbacks. A quantum
gate with non-Gaussian transformation can be used to continuously deform the
outcome distribution from known results. In doing so, we eliminate the need for
a link function. Further, by using an algorithm that superposes all possible
distributions to collapse to fit a dataset, we optimize the model in a
computationally efficient way. We provide an initial proof-of-concept by
testing this approach on both a simulation of overdispersed data and then on a
benchmark dataset, which is quite overdispersed, and achieved state of the art
results. This is a game changer in several applied fields, such as part failure
modeling, medical research, actuarial science, finance and many other fields
where Tweedie regression and overdispersion are ubiquitous.
Factor analysis or sometimes referred to as variable analysis has been
extensively used in classification problems for identifying specific factors
that are significant to particular classes. This type of analysis has been
widely used in application such as customer segmentation, medical research,
network traffic, image, and video classification. Today, factor analysis is
prominently being used in fault diagnosis of machines to identify the
significant factors and to study the root cause of a specific machine fault.
The advantage of performing factor analysis in machine maintenance is to
perform prescriptive analysis (helps answer what actions to take?) and
preemptive analysis (helps answer how to eliminate the failure mode?). In this
paper, a real case of an industrial rotating machine was considered where
vibration and ambient temperature data was collected for monitoring the health
of the machine. Gaussian mixture model-based clustering was used to cluster the
data into significant groups, and spectrum analysis was used to diagnose each
cluster to a specific state of the machine. The significant features that
attribute to a particular mode of the machine were identified by using the
random forest classification model. The significant features for specific modes
of the machine were used to conclude that the clusters generated are distinct
and have a unique set of significant features.
Archiving large sets of medical or cell images in digital libraries may
require ordering randomly scattered sets of image data according to specific
criteria, such as the spatial extent of a specific local color or contrast
content that reveals different meaningful states of a physiological structure,
tissue, or cell in a certain order, indicating progression or recession of a
pathology, or the progressive response of a cell structure to treatment. Here
we used a Self Organized Map (SOM)-based, fully automatic and unsupervised,
classification procedure described in our earlier work and applied it to sets
of minimally processed grayscale and/or color processed Scanning Electron
Microscopy (SEM) images of CD4+ T-lymphocytes (so-called helper cells) with
varying extent of HIV virion infection. It is shown that the quantization error
in the SOM output after training permits to scale the spatial magnitude and the
direction of change (+ or -) in local pixel contrast or color across images of
a series with a reliability that exceeds that of any human expert. The
procedure is easily implemented and fast, and represents a promising step
towards low-cost automatic digital image archiving with minimal intervention of
a human operator.
Clinical decision support systems (CDSS) will play an in-creasing role in
improving the quality of medical care for critically ill patients. However, due
to limitations in current informatics infrastructure, CDSS do not always have
com-plete information on state of supporting physiologic monitor-ing devices,
which can limit the input data available to CDSS. This is especially true in
the use case of mechanical ventilation (MV), where current CDSS have no
knowledge of critical ventilation settings, such as ventilation mode. To enable
MV CDSS to make accurate recommendations related to ventilator mode, we
developed a highly performant ma-chine learning model that is able to perform
per-breath clas-sification of 5 of the most widely used ventilation modes in
the USA with an average F1-score of 97.52%. We also show how our approach makes
methodologic improvements over previous work and that it is highly robust to
missing data caused by software/sensor error.
With the advent of the era of artificial intelligence (AI), deep neural
networks (DNNs) have shown huge superiority over human in image recognition,
speech processing, autonomous vehicles and medical diagnosis. However, recent
studies indicate that DNNs are vulnerable to adversarial examples (AEs) which
are designed by attackers to fool deep learning models. Different from real
examples, AEs can hardly be distinguished by human eyes, but mislead the model
to predict incorrect outputs and therefore threaten security critical
deep-learning applications. In recent years, the generation and defense of AEs
have become a research hotspot in the field of AI security. This article
reviews the latest research progress of AEs. First, we introduce the concept,
cause, characteristics and evaluation metrics of AEs, then give a survey on the
state-of-the-art AE generation methods with the discussion of advantages and
disadvantages. After that, we review the existing defenses and discuss their
limitations. Finally, the future research opportunities and challenges on AEs
are prospected.
Over the past one hundred years, the classic teaching methodology of "see
one, do one, teach one" has governed the surgical education systems worldwide.
With the advent of Operation Room 2.0, recording video, kinematic and many
other types of data during the surgery became an easy task, thus allowing
artificial intelligence systems to be deployed and used in surgical and medical
practice. Recently, surgical videos has been shown to provide a structure for
peer coaching enabling novice trainees to learn from experienced surgeons by
replaying those videos. However, the high inter-operator variability in
surgical gesture duration and execution renders learning from comparing novice
to expert surgical videos a very difficult task. In this paper, we propose a
novel technique to align multiple videos based on the alignment of their
corresponding kinematic multivariate time series data. By leveraging the
Dynamic Time Warping measure, our algorithm synchronizes a set of videos in
order to show the same gesture being performed at different speed. We believe
that the proposed approach is a valuable addition to the existing learning
tools for surgery.
Clinical researchers use disease progression modeling algorithms to predict
future patient status and characterize progression patterns. One approach for
disease progression modeling is to describe patient status using a small number
of states that represent distinctive distributions over a set of observed
measures. Hidden Markov models (HMMs) and its variants are a class of models
that both discover these states and make predictions concerning future states
for new patients. HMMs can be trained using longitudinal observations of
subjects from large-scale cohort studies, clinical trials, and electronic
health records. Despite the advantages of using the algorithms for discovering
interesting patterns, it still remains challenging for medical experts to
interpret model outputs, complex modeling parameters, and clinically make sense
of the patterns. To tackle this problem, we conducted a design study with
physician scientists, statisticians, and visualization experts, with the goal
to investigate disease progression pathways of certain chronic diseases, namely
type 1 diabetes (T1D), Huntington's disease, Parkinson's disease, and chronic
obstructive pulmonary disease (COPD). As a result, we introduce DPVis which
seamlessly integrates model parameters and outcomes of HMMs into interpretable,
and interactive visualizations. In this study, we demonstrate that DPVis is
successful in evaluating disease progression models, visually summarizing
disease states, interactively exploring disease progression patterns, and
designing and comparing clinically relevant subgroup cohorts by introducing a
case study on observation data from clinical studies of T1D.
Inspired by complexity and diversity of biological neurons, our group
proposed quadratic neurons by replacing the inner product in current artificial
neurons with a quadratic operation on input data, thereby enhancing the
capability of an individual neuron. Along this direction, we are motivated to
evaluate the power of quadratic neurons in popular network architectures,
simulating human-like learning in the form of quadratic-neuron-based deep
learning. Our prior theoretical studies have shown important merits of
quadratic neurons and networks in representation, efficiency, and
interpretability. In this paper, we use quadratic neurons to construct an
encoder-decoder structure, referred as the quadratic autoencoder, and apply it
to low-dose CT denoising. The experimental results on the Mayo low-dose CT
dataset demonstrate the utility of quadratic autoencoder in terms of image
denoising and model efficiency. To our best knowledge, this is the first time
that the deep learning approach is implemented with a new type of neurons and
demonstrates a significant potential in the medical imaging field.
In recent years, research unveiled more and more evidence for the so-called
Bayesian Brain Paradigm, i.e. the human brain is interpreted as a probabilistic
inference machine and Bayesian modelling approaches are hence used
successfully. One of the many theories is that of Probabilistic Population
Codes (PPC). Although this model has so far only been considered as meaningful
and useful for sensory perception as well as motor control, it has always been
suggested that this mechanism also underlies higher cognition and
decision-making. However, the adequacy of PPC for this regard cannot be
confirmed by means of neurological standard measurement procedures.
In this article we combine the parallel research branches of recommender
systems and predictive data mining with theoretical neuroscience. The nexus of
both fields is given by behavioural variability and resulting internal
distributions. We adopt latest experimental settings and measurement approaches
from predictive data mining to obtain these internal distributions, to inform
the theoretical PPC approach and to deduce medical correlates which can indeed
be measured in vivo. This is a strong hint for the applicability of the PPC
approach and the Bayesian Brain Paradigm for higher cognition and human
decision-making.
Different functional areas of the human brain play different roles in brain
activity, which has not been paid sufficient research attention in the
brain-computer interface (BCI) field. This paper presents a new approach for
electroencephalography (EEG) classification that applies attention-based
transfer learning. Our approach considers the importance of different brain
functional areas to improve the accuracy of EEG classification, and provides an
additional way to automatically identify brain functional areas associated with
new activities without the involvement of a medical professional. We
demonstrate empirically that our approach out-performs state-of-the-art
approaches in the task of EEG classification, and the results of visualization
indicate that our approach can detect brain functional areas related to a
certain task.
One major challenge in the medication of Parkinson's disease is that the
severity of the disease, reflected in the patients' motor state, cannot be
measured using accessible biomarkers. Therefore, we develop and examine a
variety of statistical models to detect the motor state of such patients based
on sensor data from a wearable device. We find that deep learning models
consistently outperform a classical machine learning model applied on
hand-crafted features in this time series classification task. Furthermore, our
results suggest that treating this problem as a regression instead of an
ordinal regression or a classification task is most appropriate. For consistent
model evaluation and training, we adopt the leave-one-subject-out validation
scheme to the training of deep learning models. We also employ a
class-weighting scheme to successfully mitigate the problem of high multi-class
imbalances in this domain. In addition, we propose a customized performance
measure that reflects the requirements of the involved medical staff on the
model. To solve the problem of limited availability of high quality training
data, we propose a transfer learning technique which helps to improve model
performance substantially. Our results suggest that deep learning techniques
offer a high potential to autonomously detect motor states of patients with
Parkinson's disease.
In many applications where collecting data is expensive, for example
neuroscience or medical imaging, the sample size is typically small compared to
the feature dimension. It is challenging in this setting to train expressive,
non-linear models without overfitting. These datasets call for intelligent
regularization that exploits known structure, such as correlations between the
features arising from the measurement device. However, existing structured
regularizers need specially crafted solvers, which are difficult to apply to
complex models. We propose a new regularizer specifically designed to leverage
structure in the data in a way that can be applied efficiently to complex
models. Our approach relies on feature grouping, using a fast clustering
algorithm inside a stochastic gradient descent loop: given a family of feature
groupings that capture feature covariations, we randomly select these groups at
each iteration. We show that this approach amounts to enforcing a denoising
regularizer on the solution. The method is easy to implement in many model
architectures, such as fully connected neural networks, and has a linear
computational cost. We apply this regularizer to a real-world fMRI dataset and
the Olivetti Faces datasets. Experiments on both datasets demonstrate that the
proposed approach produces models that generalize better than those trained
with conventional regularizers, and also improves convergence speed.
In this paper we present a Recurrent neural networks (RNN) based architecture
that achieves an AUCROC of 0.9147 for predicting the onset of Congestive Heart
Failure (CHF) 15 months in advance using a 12-month observation window on a
large cohort of 216,394 patients. We believe this to be the largest study in
CHF onset prediction with respect to the number of CHF case patients in the
cohort and the test set (3,332 CHF patients) on which the AUC metrics are
reported. We explore the extent to which LSTM (Long Short Term Memory) based
model, a variant of RNNs, can accurately predict the onset of CHF when compared
to known linear baselines like Logistic Regression, Random Forests and deep
learning based models such as Multi-Layer Perceptron and Convolutional Neural
Networks. We utilize demographics, medical diagnosis and procedure data from
21,405 CHF and 194,989 control patients to as our features. We describe our
feature embedding strategy for medical diagnosis codes that accommodates the
sparse, irregular, longitudinal, and high-dimensional characteristics of EHR
data. We empirically show that LSTMs can capture the longitudinal aspects of
EHR data better than the proposed baselines. As an attempt to interpret the
model, we present a temporal data analysis-based technique on false positives
to attribute feature importance. A model capable of predicting the onset of
congestive heart failure months in the future with this level of accuracy and
precision can support efforts of practitioners to implement risk factor
reduction strategies and researchers to begin to systematically evaluate
interventions to potentially delay or avert development of the disease with
high mortality, morbidity and significant costs.
Online detection of instantaneous changes in the generative process of a data
sequence generally focuses on retrospective inference of such change points
without considering their future occurrences. We extend the Bayesian Online
Change Point Detection algorithm to also infer the number of time steps until
the next change point (i.e., the residual time). This enables us to handle
observation models which depend on the total segment duration, which is useful
to model data sequences with temporal scaling. In addition, we extend the model
by removing the i.i.d. assumption on the observation model parameters. The
resulting inference algorithm for segment detection can be deployed in an
online fashion, and we illustrate applications to synthetic and to two medical
real-world data sets.
Over-parameterized deep neural networks have proven to be able to learn an
arbitrary dataset with 100$\%$ training accuracy. Because of a risk of
overfitting and computational cost issues, we cannot afford to increase the
number of network nodes if we want achieve better training results for medical
images. Previous deep learning research shows that the training ability of a
neural network improves dramatically (for the same epoch of training) when a
few nodes with supplementary information are added to the network. These few
informative nodes allow the network to learn features that are otherwise
difficult to learn by generating a disentangled data representation. This paper
analyzes how concatenation of additional information as supplementary axes
affects the training of the neural networks. This analysis was conducted for a
simple multilayer perceptron (MLP) classification model with a rectified linear
unit (ReLU) on two-dimensional training data. We compared the networks with and
without concatenation of supplementary information to support our analysis. The
model with concatenation showed more robust and accurate training results
compared to the model without concatenation. We also confirmed that our
findings are valid for deeper convolutional neural networks (CNN) using
ultrasound images and for a conditional generative adversarial network (cGAN)
using the MNIST data.
In recent years, besides the medical treatment methods in medical field,
Computer Aided Diagnosis (CAD) systems which can facilitate the decision making
phase of the physician and can detect the disease at an early stage have
started to be used frequently. The diagnosis of Idiopathic Pulmonary Fibrosis
(IPF) disease by using CAD systems is very important in that it can be followed
by doctors and radiologists. It has become possible to diagnose and follow up
the disease with the help of CAD systems by the development of high resolution
computed imaging scanners and increasing size of computation power. The purpose
of this project is to design a tool that will help specialists diagnose and
follow up the IPF disease by identifying areas of honeycombing and ground glass
patterns in High Resolution Computed Tomography (HRCT) lung images. Creating a
program module that segments the lung pair and creating a self-learner deep
learning model from given Computed Tomography (CT) images for the specific
diseased regions thanks to doctors are the main purposes of this work. Through
the created model, program module will be able to find special regions in given
new CT images. In this study, the performance of lung segmentation was tested
by the S{\o}rensen-Dice coefficient method and the mean performance was
measured as 90.7%, testing of the created model was performed with data not
used in the training stage of the CNN network, and the average performance was
measured as 87.8% for healthy regions, 73.3% for ground-glass areas and 69.1%
for honeycombing zones.
Diabetic eye disease is one of the fastest growing causes of preventable
blindness. With the advent of anti-VEGF (vascular endothelial growth factor)
therapies, it has become increasingly important to detect center-involved
diabetic macular edema (ci-DME). However, center-involved diabetic macular
edema is diagnosed using optical coherence tomography (OCT), which is not
generally available at screening sites because of cost and workflow
constraints. Instead, screening programs rely on the detection of hard exudates
in color fundus photographs as a proxy for DME, often resulting in high false
positive or false negative calls. To improve the accuracy of DME screening, we
trained a deep learning model to use color fundus photographs to predict
ci-DME. Our model had an ROC-AUC of 0.89 (95% CI: 0.87-0.91), which corresponds
to a sensitivity of 85% at a specificity of 80%. In comparison, three retinal
specialists had similar sensitivities (82-85%), but only half the specificity
(45-50%, p<0.001 for each comparison with model). The positive predictive value
(PPV) of the model was 61% (95% CI: 56-66%), approximately double the 36-38% by
the retinal specialists. In addition to predicting ci-DME, our model was able
to detect the presence of intraretinal fluid with an AUC of 0.81 (95% CI:
0.81-0.86) and subretinal fluid with an AUC of 0.88 (95% CI: 0.85-0.91). The
ability of deep learning algorithms to make clinically relevant predictions
that generally require sophisticated 3D-imaging equipment from simple 2D images
has broad relevance to many other applications in medical imaging.
Early hospital mortality prediction is critical as intensivists strive to
make efficient medical decisions about the severely ill patients staying in
intensive care units. As a result, various methods have been developed to
address this problem based on clinical records. However, some of the laboratory
test results are time-consuming and need to be processed. In this paper, we
propose a novel method to predict mortality using features extracted from the
heart signals of patients within the first hour of ICU admission. In order to
predict the risk, quantitative features have been computed based on the heart
rate signals of ICU patients. Each signal is described in terms of 12
statistical and signal-based features. The extracted features are fed into
eight classifiers: decision tree, linear discriminant, logistic regression,
support vector machine (SVM), random forest, boosted trees, Gaussian SVM, and
K-nearest neighborhood (K-NN). To derive insight into the performance of the
proposed method, several experiments have been conducted using the well-known
clinical dataset named Medical Information Mart for Intensive Care III
(MIMIC-III). The experimental results demonstrate the capability of the
proposed method in terms of precision, recall, F1-score, and area under the
receiver operating characteristic curve (AUC). The decision tree classifier
satisfies both accuracy and interpretability better than the other classifiers,
producing an F1-score and AUC equal to 0.91 and 0.93, respectively. It
indicates that heart rate signals can be used for predicting mortality in
patients in the ICU, achieving a comparable performance with existing
predictions that rely on high dimensional features from clinical records which
need to be processed and may contain missing information.
We propose a novel method for compressed sensing recovery using untrained
deep generative models. Our method is based on the recently proposed Deep Image
Prior (DIP), wherein the convolutional weights of the network are optimized to
match the observed measurements. We show that this approach can be applied to
solve any differentiable inverse problem. We also introduce a novel learned
regularization technique which incorporates a small amount of prior information
on the network weights. Compared to previous unlearned methods for compressed
sensing, our algorithm requires fewer measurements in most cases. Unlike
previous learned approaches based on generative models, our method does not
require pre-training over large datasets. As such, we can apply our method to
various medical imaging datasets for which data acquisition is expensive and
generative models are difficult to train.
In biomedical research many different types of patient data can be collected,
including various types of omics data and medical imaging modalities. Applying
multi-view learning to these different sources of information can increase the
accuracy of medical classification models compared with single-view procedures.
However, the collection of biomedical data can be expensive and taxing on
patients, so that superfluous data collection should be avoided. It is
therefore necessary to develop multi-view learning methods which can accurately
identify the views most important for prediction. In recent years, several
biomedical studies have used an approach known as multi-view stacking (MVS),
where a model is trained on each view separately and the resulting predictions
are combined through stacking. In these studies, MVS has been shown to increase
classification accuracy. However, the MVS framework can also be used for
selecting a subset of important views. To study the view selection potential of
MVS, we develop a special case called stacked penalized logistic regression
(StaPLR). Compared with existing view-selection methods, StaPLR can make use of
faster optimization algorithms and is easily parallelized. We show that
nonnegativity constraints on the parameters of the function which combines the
views are important for preventing unimportant views from entering the model.
We investigate the performance of StaPLR through simulations, and consider two
real data examples. We compare the performance of StaPLR with an existing view
selection method called the group lasso and observe that, in terms of view
selection, StaPLR has a consistently lower false positive rate.
Interpretability has become an important topic of research as more machine
learning (ML) models are deployed and widely used to make important decisions.
Due to it's complexity, i For high-stakes domains such as medical, providing
intuitive explanations that can be consumed by domain experts without ML
expertise becomes crucial. To this demand, concept-based methods (e.g., TCAV)
were introduced to provide explanations using user-chosen high-level concepts
rather than individual input features. While these methods successfully
leverage rich representations learned by the networks to reveal how
human-defined concepts are related to the prediction, they require users to
select concepts of their choice and collect labeled examples of those concepts.
In this work, we introduce DTCAV (Discovery TCAV) a global concept-based
interpretability method that can automatically discover concepts as image
segments, along with each concept's estimated importance for a deep neural
network's predictions. We validate that discovered concepts are as coherent to
humans as hand-labeled concepts. We also show that the discovered concepts
carry significant signal for prediction by analyzing a network's performance
with stitched/added/deleted concepts. DTCAV results revealed a number of
undesirable correlations (e.g., a basketball player's jersey was a more
important concept for predicting the basketball class than the ball itself) and
show the potential shallow reasoning of these networks.
Conventional optimization based methods have utilized forward models with
image priors to solve inverse problems in image processing. Recently, deep
neural networks (DNN) have been investigated to significantly improve the image
quality of the solution for inverse problems. Most DNN based inverse problems
have focused on using data-driven image priors with massive amount of data.
However, these methods often do not inherit nice properties of conventional
approaches using theoretically well-grounded optimization algorithms such as
monotone, global convergence. Here we investigate another possibility of using
DNN for inverse problems in image processing. We propose methods to use DNNs to
seamlessly speed up convergence rates of conventional optimization based
methods. Our DNN-incorporated scaled gradient projection methods, without
breaking theoretical properties, significantly improved convergence speed over
state-of-the-art conventional optimization methods such as ISTA or FISTA in
practice for inverse problems such as image inpainting, compressive image
recovery with partial Fourier samples, image deblurring, and medical image
reconstruction with sparse-view projections.
$\varepsilon$-differential privacy is a leading protection setting, focused
by design on individual privacy. Many applications, such as in the medical /
pharmaceutical domains, would rather posit privacy at a group level,
furthermore of unknown size, a setting in which classical budget scaling tricks
typically cannot guarantee non-trivial privacy levels. We call this privacy
setting integral privacy.
In this paper, we study a major problem of machine learning and statistics
with related applications in domains cited above that have recently met with
substantial press: sampling. Our formal contribution is twofolds: we provide a
general theory for sampling to be integrally private, and we show how to
achieve integral privacy with guarantees on the approximation of the true
(non-private) density. Our theory introduces $\varepsilon$-mollifiers, subsets
of densities whose sampling is guaranteed to be integrally private. Guaranteed
approximation bounds of the true density are obtained via the boosting theory
as it was originally formulated: we learn sufficient statistics in an
$\varepsilon$-mollifier of exponential families using classifiers, which brings
guaranteed approximation and convergence rates that degrade gracefully with the
privacy budget, under weak assumptions. Approximation guarantees cover the mode
capture problem. Experimental results against private kernel density estimation
and private GANs displays the quality of our results, in particular for high
privacy regimes.
Neural Networks (NN) have recently emerged as backbone of several sensitive
applications like automobile, medical image, security, etc. NNs inherently
offer Partial Fault Tolerance (PFT) in their architecture; however, the biased
PFT of NNs can lead to severe consequences in applications like cryptography
and security critical scenarios. In this paper, we propose a revised
implementation which enhances the PFT property of NN significantly with
detailed mathematical analysis. We evaluated the performance of revised NN
considering both software and FPGA implementation for a cryptographic primitive
like AES SBox. The results show that the PFT of NNs can be significantly
increased with the proposed methodology.
Utility functions or their equivalents (value functions, objective functions,
loss functions, reward functions, preference orderings) are a central tool in
most current machine learning systems. These mechanisms for defining goals and
guiding optimization run into practical and conceptual difficulty when there
are independent, multi-dimensional objectives that need to be pursued
simultaneously and cannot be reduced to each other. Ethicists have proved
several impossibility theorems that stem from this origin; those results appear
to show that there is no way of formally specifying what it means for an
outcome to be good for a population without violating strong human ethical
intuitions (in such cases, the objective function is a social welfare
function). We argue that this is a practical problem for any machine learning
system (such as medical decision support systems or autonomous weapons) or
rigidly rule-based bureaucracy that will make high stakes decisions about human
lives: such systems should not use objective functions in the strict
mathematical sense.
We explore the alternative of using uncertain objectives, represented for
instance as partially ordered preferences, or as probability distributions over
total orders. We show that previously known impossibility theorems can be
transformed into uncertainty theorems in both of those settings, and prove
lower bounds on how much uncertainty is implied by the impossibility results.
We close by proposing two conjectures about the relationship between
uncertainty in objectives and severe unintended consequences from AI systems.
Many reinforcement learning applications involve the use of data that is
sensitive, such as medical records of patients or financial information.
However, most current reinforcement learning methods can leak information
contained within the (possibly sensitive) data on which they are trained. To
address this problem, we present the first differentially private approach for
off-policy evaluation. We provide a theoretical analysis of the
privacy-preserving properties of our algorithm and analyze its utility (speed
of convergence). After describing some results of this theoretical analysis, we
show empirically that our method outperforms previous methods (which are
restricted to the on-policy setting).
Inverse problems arise in a number of domains such as medical imaging, remote
sensing, and many more, relying on the use of advanced signal and image
processing approaches -- such as sparsity-driven techniques -- to determine
their solution. This paper instead studies the use of deep learning approaches
to approximate the solution of inverse problems. In particular, the paper
provides a new generalization bound, depending on key quantity associated with
a deep neural network -- its Jacobian matrix -- that also leads to a number of
computationally efficient regularization strategies applicable to inverse
problems. The paper also tests the proposed regularization strategies in a
number of inverse problems including image super-resolution ones. Our numerical
results conducted on various datasets show that both fully connected and
convolutional neural networks regularized using the regularization or proxy
regularization strategies originating from our theory exhibit much better
performance than deep networks regularized with standard approaches such as
weight-decay.
Capturing the dynamical properties of time series concisely as interpretable
feature vectors can enable efficient clustering and classification for
time-series applications across science and industry. Selecting an appropriate
feature-based representation of time series for a given application can be
achieved through systematic comparison across a comprehensive time-series
feature library, such as those in the hctsa toolbox. However, this approach is
computationally expensive and involves evaluating many similar features,
limiting the widespread adoption of feature-based representations of time
series for real-world applications. In this work, we introduce a method to
infer small sets of time-series features that (i) exhibit strong classification
performance across a given collection of time-series problems, and (ii) are
minimally redundant. Applying our method to a set of 93 time-series
classification datasets (containing over 147000 time series) and using a
filtered version of the hctsa feature library (4791 features), we introduce a
generically useful set of 22 CAnonical Time-series CHaracteristics, catch22.
This dimensionality reduction, from 4791 to 22, is associated with an
approximately 1000-fold reduction in computation time and near linear scaling
with time-series length, despite an average reduction in classification
accuracy of just 7%. catch22 captures a diverse and interpretable signature of
time series in terms of their properties, including linear and non-linear
autocorrelation, successive differences, value distributions and outliers, and
fluctuation scaling properties. We provide an efficient implementation of
catch22, accessible from many programming environments, that facilitates
feature-based time-series analysis for scientific, industrial, financial and
medical applications using a common language of interpretable time-series
properties.
There is a need for automatic diagnosis of certain diseases from medical
images that could help medical practitioners for further assessment towards
treating the illness. Alzheimers disease is a good example of a disease that is
often misdiagnosed. Alzheimers disease (Hear after referred to as AD), is
caused by atrophy of certain brain regions and by brain cell death and is the
leading cause of dementia and memory loss [1]. MRI scans reveal this
information but atrophied regions are different for different individuals which
makes the diagnosis a bit more trickier and often gets misdiagnosed [1, 13]. We
believe that our approach to this particular problem would improve the
assessment quality by pre-flagging the images which are more likely to have AD.
We propose two solutions to this; one with transfer learning [9] and other by
BellCNN [14], a custom made Convolutional Neural Network (Hear after referred
to as CNN). Advantages and disadvantages of each approach will also be
discussed in their respective sections. The dataset used for this project is
provided by Open Access Series of Imaging Studies (Hear after referred to as
OASIS) [2, 3, 4], which contains over 400 subjects, 100 of whom have mild to
severe dementia. The dataset has labeled these subjects by two standards of
diagnosis; MiniMental State Examination (Hear after referred to as MMSE) and
Clinical Dementia Rating (Hear after referred to as CDR). These are some of the
general tools and concepts which are prerequisites to our solution; CNN [5, 6],
Neural Networks [10] (Hear after referred to as NN), Anaconda bundle for
python, Regression, Tensorflow [7]. Keywords: Alzheimers Disease, Convolutional
Neural Network, BellCNN, Image Recognition, Machine Learning, MRI, OASIS,
Tensorflow
Classification may not be reliable for several reasons: noise in the data,
insufficient input information, overlapping distributions and sharp definition
of classes. Faced with several possibilities neural network may in such cases
still be useful if instead of a classification elimination of improbable
classes is done. Eliminators may be constructed using classifiers assigning new
cases to a pool of several classes instead of just one winning class.
Elimination may be done with the help of several classifiers using modified
error functions. A real life medical application of neural network is presented
illustrating the usefulness of elimination.
We propose a novel automatic method for accurate segmentation of the prostate
in T2-weighted magnetic resonance imaging (MRI). Our method is based on
convolutional neural networks (CNNs). Because of the large variability in the
shape, size, and appearance of the prostate and the scarcity of annotated
training data, we suggest training two separate CNNs. A global CNN will
determine a prostate bounding box, which is then resampled and sent to a local
CNN for accurate delineation of the prostate boundary. This way, the local CNN
can effectively learn to segment the fine details that distinguish the prostate
from the surrounding tissue using the small amount of available training data.
To fully exploit the training data, we synthesize additional data by deforming
the training images and segmentations using a learned shape model. We apply the
proposed method on the PROMISE12 challenge dataset and achieve state of the art
results. Our proposed method generates accurate, smooth, and artifact-free
segmentations. On the test images, we achieve an average Dice score of 90.6
with a small standard deviation of 2.2, which is superior to all previous
methods. Our two-step segmentation approach and data augmentation strategy may
be highly effective in segmentation of other organs from small amounts of
annotated medical images.
Deep learning has been successfully applied to a variety of image
classification tasks. There has been keen interest to apply deep learning in
the medical domain, particularly specialties that heavily utilize imaging, such
as ophthalmology. One issue that may hinder application of deep learning to the
medical domain is the vast amount of data necessary to train deep neural
networks (DNNs). Because of regulatory and privacy issues associated with
medicine, and the generally proprietary nature of data in medical domains,
obtaining large datasets to train DNNs is a challenge, particularly in the
ophthalmology domain.
Transfer learning is a technique developed to address the issue of applying
DNNs for domains with limited data. Prior reports on transfer learning have
examined custom networks to fully train or used a particular DNN for transfer
learning. However, to the best of my knowledge, no work has systematically
examined a suite of DNNs for transfer learning for classification of diabetic
retinopathy, diabetic macular edema, and two key features of age-related
macular degeneration. This work attempts to investigate transfer learning for
classification of these ophthalmic conditions. Part I gives a condensed
overview of neural networks and the DNNs under evaluation. Part II gives the
reader the necessary background concerning diabetic retinopathy and prior work
on classification using retinal fundus photographs. The methodology and results
of transfer learning for diabetic retinopathy classification are presented,
showing that transfer learning towards this domain is feasible, with promising
accuracy. Part III gives an overview of diabetic macular edema, choroidal
neovascularization and drusen (features associated with age-related macular
degeneration), and presents results for transfer learning evaluation using
optical coherence tomography to classify these entities.
The classification of time series data is a well-studied problem with
numerous practical applications, such as medical diagnosis and speech
recognition. A popular and effective approach is to classify new time series in
the same way as their nearest neighbours, whereby proximity is defined using
Dynamic Time Warping (DTW) distance, a measure analogous to sequence alignment
in bioinformatics. However, practitioners are not only interested in accurate
classification, they are also interested in why a time series is classified a
certain way. To this end, we introduce here the problem of finding a minimum
length subsequence of a time series, the removal of which changes the outcome
of the classification under the nearest neighbour algorithm with DTW distance.
Informally, such a subsequence is expected to be relevant for the
classification and can be helpful for practitioners in interpreting the
outcome. We describe a simple but optimized implementation for detecting these
subsequences and define an accompanying measure to quantify the relevance of
every time point in the time series for the classification. In tests on
electrocardiogram data we show that the algorithm allows discovery of important
subsequences and can be helpful in detecting abnormalities in cardiac rhythms
distinguishing sick from healthy patients.
Statistical inference based on lossy or incomplete samples is of fundamental
importance in research areas such as signal/image processing, medical image
storage, remote sensing, signal transmission. In this paper, we propose a
nonparametric testing procedure based on quantized samples. In contrast to the
classic nonparametric approach, our method lives on a coarse grid of sample
information and are simple-to-use. Under mild technical conditions, we
establish the asymptotic properties of the proposed procedures including
asymptotic null distribution of the quantization test statistic as well as its
minimax power optimality. Concrete quantizers are constructed for achieving the
minimax optimality in practical use. Simulation results and a real data
analysis are provided to demonstrate the validity and effectiveness of the
proposed test. Our work bridges the classical nonparametric inference to modern
lossy data setting.
Machine learning has shown much promise in helping improve the quality of
medical, legal, and economic decision-making. In these applications, machine
learning models must satisfy two important criteria: (i) they must be causal,
since the goal is typically to predict individual treatment effects, and (ii)
they must be interpretable, so that human decision makers can validate and
trust the model predictions. There has recently been much progress along each
direction independently, yet the state-of-the-art approaches are fundamentally
incompatible. We propose a framework for learning causal interpretable
models---from observational data---that can be used to predict individual
treatment effects. Our framework can be used with any algorithm for learning
interpretable models. Furthermore, we prove an error bound on the treatment
effects predicted by our model. Finally, in an experiment on real-world data,
we show that the models trained using our framework significantly outperform a
number of baselines.
Sparsity and low-rank models have been popular for reconstructing images and
videos from limited or corrupted measurements. Dictionary or transform learning
methods are useful in applications such as denoising, inpainting, and medical
image reconstruction. This paper proposes a framework for online (or
time-sequential) adaptive reconstruction of dynamic image sequences from linear
(typically undersampled) measurements. We model the spatiotemporal patches of
the underlying dynamic image sequence as sparse in a dictionary, and we
simultaneously estimate the dictionary and the images sequentially from
streaming measurements. Multiple constraints on the adapted dictionary are also
considered such as a unitary matrix, or low-rank dictionary atoms that provide
additional efficiency or robustness. The proposed online algorithms are memory
efficient and involve simple updates of the dictionary atoms, sparse
coefficients, and images. Numerical experiments demonstrate the usefulness of
the proposed methods in inverse problems such as video reconstruction or
inpainting from noisy, subsampled pixels, and dynamic magnetic resonance image
reconstruction from very limited measurements.
To improve the performance of Intensive Care Units (ICUs), the field of
bio-statistics has developed scores which try to predict the likelihood of
negative outcomes. These help evaluate the effectiveness of treatments and
clinical practice, and also help to identify patients with unexpected outcomes.
However, they have been shown by several studies to offer sub-optimal
performance. Alternatively, Deep Learning offers state of the art capabilities
in certain prediction tasks and research suggests deep neural networks are able
to outperform traditional techniques. Nevertheless, a main impediment for the
adoption of Deep Learning in healthcare is its reduced interpretability, for in
this field it is crucial to gain insight on the why of predictions, to assure
that models are actually learning relevant features instead of spurious
correlations. To address this, we propose a deep multi-scale convolutional
architecture trained on the Medical Information Mart for Intensive Care III
(MIMIC-III) for mortality prediction, and the use of concepts from coalitional
game theory to construct visual explanations aimed to show how important these
inputs are deemed by the network. Our results show our model attains state of
the art performance while remaining interpretable. Supporting code can be found
at https://github.com/williamcaicedo/ISeeU.
One of the challenges in large-scale information retrieval (IR) is to develop
fine-grained and domain-specific methods to answer natural language questions.
Despite the availability of numerous sources and datasets for answer retrieval,
Question Answering (QA) remains a challenging problem due to the difficulty of
the question understanding and answer extraction tasks. One of the promising
tracks investigated in QA is to map new questions to formerly answered
questions that are `similar'. In this paper, we propose a novel QA approach
based on Recognizing Question Entailment (RQE) and we describe the QA system
and resources that we built and evaluated on real medical questions. First, we
compare machine learning and deep learning methods for RQE using different
kinds of datasets, including textual inference, question similarity and
entailment in both the open and clinical domains. Second, we combine IR models
with the best RQE method to select entailed questions and rank the retrieved
answers. To study the end-to-end QA approach, we built the MedQuAD collection
of 47,457 question-answer pairs from trusted medical sources, that we introduce
and share in the scope of this paper. Following the evaluation process used in
TREC 2017 LiveQA, we find that our approach exceeds the best results of the
medical task with a 29.8% increase over the best official score. The evaluation
results also support the relevance of question entailment for QA and highlight
the effectiveness of combining IR and RQE for future QA efforts. Our findings
also show that relying on a restricted set of reliable answer sources can bring
a substantial improvement in medical QA.
This paper presents a new method for medical diagnosis of neurodegenerative
diseases, such as Parkinson's, by extracting and using latent information from
trained Deep convolutional, or convolutional-recurrent Neural Networks (DNNs).
In particular, our approach adopts a combination of transfer learning, k-means
clustering and k-Nearest Neighbour classification of deep neural network
learned representations to provide enriched prediction of the disease based on
MRI and/or DaT Scan data. A new loss function is introduced and used in the
training of the DNNs, so as to perform adaptation of the generated learned
representations between data from different medical environments. Results are
presented using a recently published database of Parkinson's related
information, which was generated and evaluated in a hospital environment.
Chest radiography is an extremely powerful imaging modality, allowing for a
detailed inspection of a patient's thorax, but requiring specialized training
for proper interpretation. With the advent of high performance general purpose
computer vision algorithms, the accurate automated analysis of chest
radiographs is becoming increasingly of interest to researchers. However, a key
challenge in the development of these techniques is the lack of sufficient
data. Here we describe MIMIC-CXR, a large dataset of 371,920 chest x-rays
associated with 227,943 imaging studies sourced from the Beth Israel Deaconess
Medical Center between 2011 - 2016. Each imaging study can pertain to one or
more images, but most often are associated with two images: a frontal view and
a lateral view. Images are provided with 14 labels derived from a natural
language processing tool applied to the corresponding free-text radiology
reports. All images have been de-identified to protect patient privacy. The
dataset is made freely available to facilitate and encourage a wide range of
research in medical computer vision.
The classification of shapes is of great interest in diverse areas ranging
from medical imaging to computer vision and beyond. While many statistical
frameworks have been developed for the classification problem, most are
strongly tied to early formulations of the problem - with an object to be
classified described as a vector in a relatively low-dimensional Euclidean
space. Statistical shape data have two main properties that suggest a need for
a novel approach: (i) shapes are inherently infinite dimensional with strong
dependence among the positions of nearby points, and (ii) shape space is not
Euclidean, but is fundamentally curved. To accommodate these features of the
data, we work with the square-root velocity function of the curves to provide a
useful formal description of the shape, pass to tangent spaces of the manifold
of shapes at different projection points which effectively separate shapes for
pairwise classification in the training data, and use principal components
within these tangent spaces to reduce dimensionality. We illustrate the impact
of the projection point and choice of subspace on the misclassification rate
with a novel method of combining pairwise classifiers.
Large, labeled datasets have driven deep learning methods to achieve
expert-level performance on a variety of medical imaging tasks. We present
CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240
patients. We design a labeler to automatically detect the presence of 14
observations in radiology reports, capturing uncertainties inherent in
radiograph interpretation. We investigate different approaches to using the
uncertainty labels for training convolutional neural networks that output the
probability of these observations given the available frontal and lateral
radiographs. On a validation set of 200 chest radiographic studies which were
manually annotated by 3 board-certified radiologists, we find that different
uncertainty approaches are useful for different pathologies. We then evaluate
our best model on a test set composed of 500 chest radiographic studies
annotated by a consensus of 5 board-certified radiologists, and compare the
performance of our model to that of 3 additional radiologists in the detection
of 5 selected pathologies. On Cardiomegaly, Edema, and Pleural Effusion, the
model ROC and PR curves lie above all 3 radiologist operating points. We
release the dataset to the public as a standard benchmark to evaluate
performance of chest radiograph interpretation models.
The dataset is freely available at
https://stanfordmlgroup.github.io/competitions/chexpert .
Label shift refers to the phenomenon where the marginal probability p(y) of
observing a particular class changes between the training and test
distributions while the conditional probability p(x|y) stays fixed. This is
relevant in settings such as medical diagnosis, where a classifier trained to
predict disease based on observed symptoms may need to be adapted to a
different distribution where the baseline frequency of the disease is higher.
Given calibrated estimates of p(y|x), one can apply an EM algorithm to correct
for the shift in class imbalance between the training and test distributions
without ever needing to calculate p(x|y). Unfortunately, modern neural networks
typically fail to produce well-calibrated probabilities, compromising the
effectiveness of this approach. Although Temperature Scaling can greatly reduce
miscalibration in these networks, it can leave behind a systematic bias in the
probabilities that still poses a problem. To address this, we extend
Temperature Scaling with class-specific bias parameters, which largely
eliminates systematic bias in the calibrated probabilities and allows for
effective domain adaptation under label shift. We term our calibration approach
"Bias-Corrected Temperature Scaling". On experiments with CIFAR10, we find that
EM with Bias-Corrected Temperature Scaling significantly outperforms both EM
with Temperature Scaling and the recently-proposed Black-Box Shift Estimation.
