A multitask deep-learning system to classify diabetic macular edema for different optical coherence tomography devices: a multicenter analysis

Fangyao Tang, Xi Wang, An-ran Ran, Carmen K. M. Chan, Mary Ho, Wilson Yip, Alvin L. Young, Jerry Lok, Simon Szeto, Jason Chan, Fanny Yip, Raymond Wong, Ziqi Tang, Dawei Yang, Danny S. Ng, Li Jia Chen, Marten Brelén, Victor Chu, Kenneth Li, Tracy H. T. LaiGavin S. Tan, Daniel S. W. Ting, Haifan Huang, Haoyu Chen, Jacey Hongjie Ma, Shibo Tang, Theodore Leng, Schahrouz Kakavand, Suria S. Mannil, Robert T. Chang, Gerald Liew, Bamini Gopinath, Timothy Y. Y. Lai, Chi Pui Pang, Peter H. Scanlon, Tien Yin Wong, Clement C. Tham, Hao Chen, Pheng-Ann Heng, Carol Y. Cheung*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
9 Downloads (Pure)

Abstract

OBJECTIVE: Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices.

RESEARCH DESIGN AND METHODS: We trained and validated two versions of a multitask convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume scans and 2D B-scans, respectively. For both 3D and 2D CNNs, we used the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent data sets from Singapore, Hong Kong, the U.S., China, and Australia.

RESULTS: In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920-0.954), 0.958 (0.930-0.977), and 0.965 (0.948-0.977) for the primary data set obtained from CIRRUS, SPECTRALIS, and Triton OCTs, respectively, in addition to AUROCs >0.906 for the external data sets. For further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940-0.995), 0.951 (0.898-0.982), and 0.975 (0.947-0.991) for the primary data set and >0.894 for the external data sets.

CONCLUSIONS: We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics.

Original languageEnglish
Pages (from-to)2078-2088
Number of pages11
JournalDiabetes Care
Volume44
Issue number9
Early online date27 Jul 2021
DOIs
Publication statusPublished - Sep 2021

Fingerprint

Dive into the research topics of 'A multitask deep-learning system to classify diabetic macular edema for different optical coherence tomography devices: a multicenter analysis'. Together they form a unique fingerprint.

Cite this