Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map

• Published in: IEEE transactions on biomedical engineering 2024-01, Vol.71 (1), p.1-12
• Main Authors: Zang, Pengxiao, Hormel, Tristan T., Wang, Jie, Guo, Yukun, Bailey, Steven T., Flaxel, Christina J., Huang, David, Hwang, Thomas S., Jia, Yali
• Format: Article
• Language: English
• Subjects: Algorithms; Angiography; Biomarkers; Classifiers; Datasets; Decision making; Deep learning; Diabetes; Diabetes Mellitus; Diabetic retinopathy; Diabetic Retinopathy - diagnostic imaging; Diagnosis; Generators; Heating systems; Humans; Interpretability; Machine learning; Optical coherence tomography; Pathology; Retina; Retina - diagnostic imaging; Retinopathy; Task analysis; Tomography, Optical Coherence - methods; Training
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2023.3290541

Objective: Deep learning classifiers provide the most accurate means of automatically diagnosing diabetic retinopathy (DR) based on optical coherence tomography (OCT) and its angiography (OCTA). The power of these models is attributable in part to the inclusion of hidden layers that provide the complexity required to achieve a desired task. However, hidden layers also render algorithm outputs difficult to interpret. Here we introduce a novel biomarker activation map (BAM) framework based on generative adversarial learning that allows clinicians to verify and understand classifiers' decision-making. Methods: A data set including 456 macular scans were graded as non-referable or referable DR based on current clinical standards. A DR classifier that was used to evaluate our BAM was first trained based on this data set. The BAM generation framework was designed by combing two U-shaped generators to provide meaningful interpretability to this classifier. The main generator was trained to take referable scans as input and produce an output that would be classified by the classifier as non-referable. The BAM is then constructed as the difference image between the output and input of the main generator. To ensure that the BAM only highlights classifier-utilized biomarkers an assistant generator was trained to do the opposite, producing scans that would be classified as referable by the classifier from non-referable scans. Results: The generated BAMs highlighted known pathologic features including nonperfusion area and retinal fluid. Conclusion/Significance: A fully interpretable classifier based on these highlights could help clinicians better utilize and verify automated DR diagnosis.