Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning

Cell
Daniel S KermanyKang Zhang

Abstract

The implementation of clinical-decision support algorithms for medical imaging faces challenges with reliability and interpretability. Here, we establish a diagnostic tool based on a deep-learning framework for the screening of patients with common treatable blinding retinal diseases. Our framework utilizes transfer learning, which trains a neural network with a fraction of the data of conventional approaches. Applying this approach to a dataset of optical coherence tomography images, we demonstrate performance comparable to that of human experts in classifying age-related macular degeneration and diabetic macular edema. We also provide a more transparent and interpretable diagnosis by highlighting the regions recognized by the neural network. We further demonstrate the general applicability of our AI system for diagnosis of pediatric pneumonia using chest X-ray images. This tool may ultimately aid in expediting the diagnosis and referral of these treatable conditions, thereby facilitating earlier treatment, resulting in improved clinical outcomes. VIDEO ABSTRACT.

Associated Datasets

Citations

Aug 30, 2018·Clinical & Experimental Ophthalmology·Daniel T HogartyAlex W Hewitt
Dec 18, 2018·Asia-Pacific Journal of Ophthalmology·Zhixi LiMingguang He
Oct 27, 2018·The British Journal of Ophthalmology·Daniel Shu Wei TingTien Yin Wong
Feb 23, 2019·BioEssays : News and Reviews in Molecular, Cellular and Developmental Biology·Vincent LoubiereGiacomo Cavalli
Mar 23, 2019·JAMA Network Open·Eui Jin HwangUNKNOWN DLAD Development and Evaluation Group
Mar 30, 2019·Critical Reviews in Clinical Laboratory Sciences·Christopher Naugler, Deirdre L Church
Apr 4, 2019·The New England Journal of Medicine·Alvin RajkomarIsaac Kohane
Mar 15, 2019·Journal of the Science of Food and Agriculture·Wang DaweiHan Zhongzhi
May 28, 2019·Seminars in Ophthalmology·David J SmitsLouis R Pasquale
May 22, 2019·Proceedings of the National Academy of Sciences of the United States of America·Fei LiLinxian Li
Nov 25, 2018·The British Journal of Ophthalmology·Daniel S W TingCynthia Toth
Jun 22, 2019·Technology in Cancer Research & Treatment·Quan ChenYunpeng Li
Jul 14, 2019·Journal of Magnetic Resonance Imaging : JMRI·Lei ZhangShandong Wu
Jul 20, 2019·JAMA Network Open·Michael T LuUdo Hoffmann
Aug 3, 2019·JAMA Network Open·Matthew M EngelhardF Joseph McClernon
Jul 2, 2019·Current Opinion in Ophthalmology·Julia E Reid, Eric Eaton
Sep 7, 2019·Eye·Andrzej GrzybowskiDaniel S W Ting
Jan 22, 2020·Experimental Biology and Medicine·Xincheng YaoDevrim Toslak
Oct 28, 2019·Clinical & Experimental Ophthalmology·Jianbo MaoLijun Shen
Dec 10, 2019·Human Brain Mapping·Xiaoxiao WangBensheng Qiu
Mar 11, 2020·Cancers·Wan ZhuXiangqian Guo
Aug 28, 2019·Journal of Neuro-ophthalmology : the Official Journal of the North American Neuro-Ophthalmology Society·T Y Alvin LiuNeil R Miller
May 27, 2020·Journal of Cellular Physiology·Roghayeh SheervalilouZiba Nazarlou
May 12, 2020·Journal of Alzheimer's Disease : JAD·Qunxi DongUNKNOWN Alzheimer’s Disease Neuroimaging Initiative

❮ Previous
Next ❯

Related Concepts

Related Feeds

Brain Imaging of Neural Circuits

Neural circuits are groups of interconnected neurons which carry out specific functions when activated. Imaging these neural circuits allows researches to further elucidate their mechanisms and functions. Follow this feed to stay up to date on brain imaging of neural circuits.

Cell eTOC

Cell is a scientific journal publishing research across a broad range of disciplines within the life sciences field. Discover the latest research from Cell here.

Brain Imaging of Neural Circuits (MDS)

Neural circuits are groups of interconnected neurons which carry out specific functions when activated. Imaging these neural circuits allows researches to further elucidate their mechanisms and functions. Follow this feed to stay up to date on brain imaging of neural circuits.