A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis

Tang, Fangyao, Wang, Xi, Ran, An-ran, Chan, Carmen K.M., Ho, Mary, Yip, Wilson, Young, Alvin L., Lok, Jerry, Szeto, Simon, Chan, Jason, Yip, Fanny, Wong, Raymond, Tang, Ziqi, Yang, Dawei, Ng, Danny S., Chen, Li Jia, Brelén, Marten, Chu, Victor, Li, Kenneth, Lai, Tracy H.T., Tan, Gavin S., Ting, Daniel S.W., Huang, Haifan, Chen, Haoyu, Ma, Jacey Hongjie, Tang, Shibo, Leng, Theodore, Kakavand, Schahrouz, Mannil, Suria S., Chang, Robert T., Liew, Gerald, Gopinath, Bamini, Lai, Timothy Y.Y., Pang, Chi Pui, Scanlon, Peter H ORCID: 0000-0001-8513-710X, Wong, Tien Yin, Tham, Clement C., Chen, Hao, Heng, Pheng-Ann and Cheung, Carol Y. (2021) A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis. Diabetes Care, 44 (9). pp. 2078-2088. doi:10.2337/dc20-3064

Full text not available from this repository.

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.

Item Type:	Article
Article Type:	Article
Uncontrolled Keywords:	Diabetic macular edema, classification; Tomography devices
Related URLs:	Dataset
Subjects:	R Medicine > RA Public aspects of medicine > RA645.A-Z Individual diseases or groups of diseases, A-Z > RA645.D54 Diabetes R Medicine > RE Ophthalmology
Research Priority Areas:	Health, Life Sciences, Sport and Wellbeing
Depositing User:	Susan Turner
Date Deposited:	02 Aug 2021 08:58
Last Modified:	22 Oct 2021 10:47
URI:	https://eprints.glos.ac.uk/id/eprint/10017

University Staff: Request a correction | Repository Editors: Update this record