Drusen‐aware model for age‐related macular degeneration recognition

• Published in: Ophthalmic & physiological optics Vol. 43; no. 4; pp. 668 - 679
• Main Authors: Pan, Junjun, Ho, Sharon, Ly, Angelica, Kalloniatis, Michael, Sowmya, Arcot
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.07.2023; John Wiley and Sons Inc
• Subjects: Age; age‐related macular degeneration; Algorithms; artificial intelligence; automated recognition; Classification; deep learning; drusen; Eye diseases; Humans; image classification; machine learning; Macular degeneration; Macular Degeneration - diagnosis; Original; Photography; Retina; Retinal Drusen - diagnosis; ROC Curve; deep learning; image classification; drusen; machine learning; age-related macular degeneration; artificial intelligence; automated recognition
• ISSN: 0275-5408; 1475-1313; 1475-1313
• DOI: 10.1111/opo.13108

Introduction The purpose of this study was to build an automated age‐related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age‐related changes by using drusen masks for spatial feature supervision. Methods A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre‐processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver‐operating characteristic (AUC). Fivefold cross‐validation was performed, and the results compared with four other methods. Results Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01). Conclusion The proposed drusen‐aware model outperformed baseline and other vessel feature‐based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five‐category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real‐life clinical setting.