15
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A deep-learning classifier identifies patients with clinical heart failure using whole-slide images of H&E tissue

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Over 26 million people worldwide suffer from heart failure annually. When the cause of heart failure cannot be identified, endomyocardial biopsy (EMB) represents the gold-standard for the evaluation of disease. However, manual EMB interpretation has high inter-rater variability. Deep convolutional neural networks (CNNs) have been successfully applied to detect cancer, diabetic retinopathy, and dermatologic lesions from images. In this study, we develop a CNN classifier to detect clinical heart failure from H&E stained whole-slide images from a total of 209 patients, 104 patients were used for training and the remaining 105 patients for independent testing. The CNN was able to identify patients with heart failure or severe pathology with a 99% sensitivity and 94% specificity on the test set, outperforming conventional feature-engineering approaches. Importantly, the CNN outperformed two expert pathologists by nearly 20%. Our results suggest that deep learning analytics of EMB can be used to predict cardiac outcome.

          Related collections

          Most cited references22

          • Record: found
          • Abstract: found
          • Article: not found

          The global health and economic burden of hospitalizations for heart failure: lessons learned from hospitalized heart failure registries.

          Heart failure is a global pandemic affecting an estimated 26 million people worldwide and resulting in more than 1 million hospitalizations annually in both the United States and Europe. Although the outcomes for ambulatory HF patients with a reduced ejection fraction (EF) have improved with the discovery of multiple evidence-based drug and device therapies, hospitalized heart failure (HHF) patients continue to experience unacceptably high post-discharge mortality and readmission rates that have not changed in the last 2 decades. In addition, the proportion of HHF patients classified as having a preserved EF continues to grow and may overtake HF with a reduced EF in the near future. However, the prognosis for HF with a preserved EF is similar and there are currently no available disease-modifying therapies. HHF registries have significantly improved our understanding of this clinical entity and remain an important source of data shaping both public policy and research efforts. The authors review global HHF registries to describe the patient characteristics, management, outcomes and their predictors, quality improvement initiatives, regional differences, and limitations of the available data. Moreover, based on the lessons learned, they also propose a roadmap for the design and conduct of future HHF registries. Copyright © 2014 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Deep Learning in Neural Networks: An Overview

            (2014)
            In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features

              Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients' prognoses. In this study, we obtain 2,186 haematoxylin and eosin stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), and 294 additional images from Stanford Tissue Microarray (TMA) Database. We extract 9,879 quantitative image features and use regularized machine-learning methods to select the top features and to distinguish shorter-term survivors from longer-term survivors with stage I adenocarcinoma (P<0.003) or squamous cell carcinoma (P=0.023) in the TCGA data set. We validate the survival prediction framework with the TMA cohort (P<0.036 for both tumour types). Our results suggest that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology. Our methods are extensible to histopathology images of other organs.
                Bookmark

                Author and article information

                Contributors
                Role: Data curationRole: Formal analysisRole: InvestigationRole: MethodologyRole: SoftwareRole: Writing – original draftRole: Writing – review & editing
                Role: Formal analysisRole: InvestigationRole: MethodologyRole: SoftwareRole: SupervisionRole: Writing – review & editing
                Role: Data curationRole: ResourcesRole: Writing – review & editing
                Role: Data curationRole: Resources
                Role: ConceptualizationRole: Data curationRole: ResourcesRole: SupervisionRole: Writing – review & editing
                Role: ConceptualizationRole: Data curationRole: ResourcesRole: SupervisionRole: Writing – review & editing
                Role: ConceptualizationRole: Funding acquisitionRole: MethodologyRole: Project administrationRole: SupervisionRole: Writing – review & editing
                Role: Editor
                Journal
                PLoS One
                PLoS ONE
                plos
                plosone
                PLoS ONE
                Public Library of Science (San Francisco, CA USA )
                1932-6203
                3 April 2018
                2018
                : 13
                : 4
                : e0192726
                Affiliations
                [1 ] Department of Physiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States of America
                [2 ] Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States of America
                [3 ] Cardiovascular Research Institute, University of Pennsylvania, Philadelphia, PA, United States of America
                [4 ] Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA, United States of America
                Stanford University, UNITED STATES
                Author notes

                Competing Interests: Dr. Madabhushi is the co-founder and stakeholder in Ibris Inc., a cancer diagnostics company. Drs. Madabhushi and Feldman are equity holders and have technology licensed to both Elucid Bioimaging and Inspirata Inc. Drs. Madabhushi and Feldman are scientific advisory consultants for Inspirata Inc. and sit on its scientific advisory board. Dr. Feldman is also a consultant for Phillips Healthcare, XFIN, and Virbio. Dr. Margulies hold research grants from Thoratec Corporation and Merck and serves as a scientific consultant/advisory board member for Janssen, Merck, Pfizer, Ridgetop Research and Glaxo-Smith-Kline. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

                Author information
                http://orcid.org/0000-0001-6857-341X
                http://orcid.org/0000-0002-5741-0399
                Article
                PONE-D-18-03044
                10.1371/journal.pone.0192726
                5882098
                29614076
                a22e524e-06fa-4b85-862c-f00b9fff3892
                © 2018 Nirschl et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 14 July 2017
                : 29 January 2018
                Page count
                Figures: 3, Tables: 4, Pages: 16
                Funding
                Funded by: National Institute of Neurological Disorders and Stroke (US)
                Award ID: F30NS092227
                Award Recipient :
                Funded by: National Cancer Institute (US)
                Award ID: U24CA199374-01
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/100000054, National Cancer Institute;
                Award ID: R21CA195152-01
                Award Recipient :
                Funded by: National Cancer Institute (US)
                Award ID: R21CA179327-01
                Award Recipient :
                Funded by: National Institute of Diabetes and Digestive and Kidney Diseases (US)
                Award ID: R01DK098503-02
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/100000050, National Heart, Lung, and Blood Institute;
                Award ID: R01-HL105993
                Award Recipient :
                Funded by: DOD Prostate Cancer Synergistic Idea Development Award
                Award ID: PC120857
                Award Recipient :
                Funded by: DOD Lung Cancer Idea Development New Investigator Award
                Award ID: LC130463
                Award Recipient :
                Funded by: NIH The National Center for Advancing Translational Sciences
                Award ID: TL1TR001880
                Award Recipient :
                Funded by: National Institute of Diabetes and Digestive and Kidney Diseases (US)
                Award ID: 5T32DK007470
                Award Recipient :
                Funded by: DOD Peer Reviewed Cancer Research Program
                Award ID: W81XWH-16-1-0329
                Award Recipient :
                Funded by: The Ohio Third Frontier Technology Validation Fund
                Funded by: The Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering
                Funded by: The Clinical and Translational Science Award Program (CTSA) at Case Western Reserve University
                Funded by: National Center for Research Resources under award number
                Award ID: 1 C06 RR12463-01
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/100000054, National Cancer Institute;
                Award ID: R01CA202752-01A1
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/100000054, National Cancer Institute;
                Award ID: R01CA208236-01A1
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/100000054, National Cancer Institute;
                Award ID: R01 CA216579-01A1
                Award Recipient :
                Research reported in this publication was supported by the National Cancer Institute of the National Institutes of Health under award numbers (R01CA202752-01A1, R01CA208236-01A1, R01 CA216579-01A1, R21CA179327-01, R21CA195152-01 and U24CA199374-01) the National Institute of Diabetes and Digestive and Kidney Diseases under award number R01DK098503-02, The National Center for Advancing Translational Sciences under award number TL1TR001880, the National Heart Lung and Blood Institute under award number R01-HL105993, the DOD Prostate Cancer Synergistic Idea Development Award (PC120857); the National Institute of Diabetes and Digestive and Kidney Diseases (US) under award number 5T32DK007470, the National Center for Research Resources under award number under the award number 1 C06 RR12463-01, the DOD Lung Cancer Idea Development New Investigator Award (LC130463), the DOD Prostate Cancer Synergistic Idea Development Award (PC120857); the DOD Peer Reviewed Cancer Research Program (W81XWH-16-1-0329), the Case Comprehensive Cancer Center Pilot Grant, The Ohio Third Frontier Technology Validation Fund, the VelaSano Grant from the Cleveland Clinic the Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering at Case Western Reserve University, the Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering, the The Clinical and Translational Science Award Program (CTSA) at Case Western Reserve University, and the I-Corps@Ohio Program. JJN was supported by NINDS F30NS092227. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Research Article
                Medicine and Health Sciences
                Cardiology
                Heart Failure
                People and Places
                Population Groupings
                Professions
                Medical Personnel
                Medical Doctors
                Pathologists
                Medicine and Health Sciences
                Health Care
                Health Care Providers
                Medical Doctors
                Pathologists
                Medicine and Health Sciences
                Pathology and Laboratory Medicine
                Anatomical Pathology
                Histopathology
                Medicine and Health Sciences
                Pathology and Laboratory Medicine
                Clinical Pathology
                Computer and Information Sciences
                Neural Networks
                Biology and Life Sciences
                Neuroscience
                Neural Networks
                Biology and Life Sciences
                Anatomy
                Cardiovascular Anatomy
                Heart
                Medicine and Health Sciences
                Anatomy
                Cardiovascular Anatomy
                Heart
                Research and Analysis Methods
                Imaging Techniques
                Image Analysis
                Computer and Information Sciences
                Artificial Intelligence
                Machine Learning
                Custom metadata
                WND-CHARM is open-source and hosted at https://github.com/wnd-charm/wnd-charm. The deep learning procedure used here follows the method described in Janowczyk and Madabhushi 2016; a deep learning tutorial with source code is hosted at http://www.andrewjanowczyk.com/deep-learning. The image data that support the findings of this study can be found using the following accession number from the Image Data Resource: idr0042.

                Uncategorized
                Uncategorized

                Comments

                Comment on this article