Format

Send to

Choose Destination
Cell. 2018 Feb 22;172(5):1122-1131.e9. doi: 10.1016/j.cell.2018.02.010.

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

Author information

1
Guangzhou Women and Children's Medical Center, Guangzhou Medical University, 510005 Guangzhou, China; Shiley Eye Institute, Institute for Engineering in Medicine, Institute for Genomic Medicine, University of California, San Diego, La Jolla, CA 92093, USA.
2
Shiley Eye Institute, Institute for Engineering in Medicine, Institute for Genomic Medicine, University of California, San Diego, La Jolla, CA 92093, USA.
3
Guangzhou Women and Children's Medical Center, Guangzhou Medical University, 510005 Guangzhou, China.
4
Heidelberg Engineering, Heidelberg, Germany.
5
Molecular Medicine Research Center, State Key Laboratory of Biotherapy, The National Clinical Research Center of Senile Disease, West China Hospital, Sichuan University, Chengdu, China.
6
Guangzhou Women and Children's Medical Center, Guangzhou Medical University, 510005 Guangzhou, China; Guangzhou KangRui Biological Pharmaceutical Technology Company, 510005 Guangzhou, China.
7
YouHealth AI, 510005 Guangzhou, China.
8
Guangzhou KangRui Biological Pharmaceutical Technology Company, 510005 Guangzhou, China.
9
Beihai Hospital, Dalian, 116021, China.
10
Department of Ophthalmology, University of Texas Health Science Center, San Antonio, TX 78229, USA.
11
Shanghai Key Laboratory of Ocular Fundus Diseases, Shanghai General Hospital, Shanghai JiaoTong University, 200080 Shanghai, China.
12
Beijing Instute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
13
Qualcomm, San Diego, CA 92121, USA.
14
Guangzhou Women and Children's Medical Center, Guangzhou Medical University, 510005 Guangzhou, China; Shiley Eye Institute, Institute for Engineering in Medicine, Institute for Genomic Medicine, University of California, San Diego, La Jolla, CA 92093, USA; Molecular Medicine Research Center, State Key Laboratory of Biotherapy, The National Clinical Research Center of Senile Disease, West China Hospital, Sichuan University, Chengdu, China; Guangzhou Regenerative Medicine and Health Guangdong Laboratory, 510005 Guangzhou, China; Veterans Administration Healthcare System, San Diego, CA 92037, USA. Electronic address: kang.zhang@gmail.com.

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.

KEYWORDS:

age-related macular degeneration; artificial intelligence; choroidal neovascularization; deep learning; diabetic macular edema; diabetic retinopathy; optical coherence tomography; pneumonia; screening; transfer learning

PMID:
29474911
DOI:
10.1016/j.cell.2018.02.010
[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center