Author(s): Chen Q, Keenan TDL, Allot A, Peng Y, Agrón E, Domalpally A, Klaver CCW, Luttikhuizen DT, Colyer MH, Cukras CA, Wiley HE, Teresa Magone M, Cousineau-Krieger C, Wong WT, Zhu Y, Chew EY, Lu Z; AREDS2 Deep Learning Research Group. Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration. J Am Med Inform Assoc. 2021 Jun 12;28(6):1135-1148. doi: 10.1093/jamia/ocaa302. PMID 33792724
Journal: Journal Of The American Medical Informatics Association : Jamia, Volume 28, Issue 6, Jun 2021
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.
Published by Oxford University Press on behalf of the American Medical Informatics Association 2021. This work is written by US Government employees and is in the public domain in the US.