Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration

Qingyu Chen*, Tiarnan D.L. Keenan, Alexis Allot, Yifan Peng, Elvira Agrón, Amitha Domalpally, Caroline C.W. Klaver, Daniel T. Luttikhuizen, Marcus H. Colyer, Catherine A. Cukras, Henry E. Wiley, M. Teresa Magone, Chantal Cousineau-Krieger, Wai T. Wong, Yingying Zhu, Emily Y. Chew, Zhiyong Lu

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Objective: Reticular pseudodrusen (RPD), a key feature of age-related macular degeneration (AMD), are poorly detected by human experts on standard color fundus photography (CFP) and typically require advanced imaging modalities such as fundus autofluorescence (FAF). The objective was to develop and evaluate the performance of a novel multimodal, multitask, multiattention (M3) deep learning framework on RPD detection. Materials and Methods: A deep learning framework (M3) was developed to detect RPD presence accurately using CFP alone, FAF alone, or both, employing >8000 CFP-FAF image pairs obtained prospectively (Age-Related Eye Disease Study 2). The M3 framework includes multimodal (detection from single or multiple image modalities), multitask (training different tasks simultaneously to improve generalizability), and multiattention (improving ensembled feature representation) operation. Performance on RPD detection was compared with state-of-the-art deep learning models and 13 ophthalmologists; performance on detection of 2 other AMD features (geographic atrophy and pigmentary abnormalities) was also evaluated. Results: For RPD detection, M3 achieved an area under the receiver-operating characteristic curve (AUROC) of 0.832, 0.931, and 0.933 for CFP alone, FAF alone, and both, respectively. M3 performance on CFP was very substantially superior to human retinal specialists (median F1 score = 0.644 vs 0.350). External validation (the Rotterdam Study) demonstrated high accuracy on CFP alone (AUROC, 0.965). The M3 framework also accurately detected geographic atrophy and pigmentary abnormalities (AUROC, 0.909 and 0.912, respectively), demonstrating its generalizability. Conclusions: This study demonstrates the successful development, robust evaluation, and external validation of a novel deep learning framework that enables accessible, accurate, and automated AMD diagnosis and prognosis.

Original languageEnglish
Pages (from-to)1135-1148
Number of pages14
JournalJournal of the American Medical Informatics Association
Volume28
Issue number6
Early online date1 Apr 2021
DOIs
Publication statusPublished - 1 Jun 2021

Bibliographical note

Funding Information:
The work was supported by the intramural program funds and contracts from the National Center for Biotechnology Information/National Library of Medicine/National Institutes of Health, the National Eye Institute/National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland (Contract HHS-N-260-2005-00007-C; ADB contract NO1-EY-5-0007; Grant No K99LM013001). Funds were generously contributed to these contracts by the following National Institutes of Health: Office of Dietary Supplements, National Center for Complementary and Alternative Medicine; National Institute on Aging; National Heart, Lung, and Blood Institute; and National Institute of Neurological Disorders and Stroke.

Publisher Copyright:
© 2021 Published by Oxford University Press on behalf of the American Medical Informatics Association.

Fingerprint

Dive into the research topics of 'Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration'. Together they form a unique fingerprint.

Cite this