DRGen: Domain Generalization in Diabetic Retinopathy Classification
Atwany, Mohammad Zeyad Abdulrahman
Atwany, Mohammad Zeyad Abdulrahman
Supervisor
Department
Machine Learning
Embargo End Date
Type
Thesis
Date
2022
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Domain generalization is a difficult challenge in deep learning, particularly in medical image analysis, because of the significant variation across various datasets. The majority of existing publications in the literature maximize performance on a single target domain., without regards to model generalizability on other domains or distributions. High discrepancy in the number of images and major domain shifts, can therefore cause single-source trained models to under-perform during testing. In this paper, we address the problem of domain generalization in Diabetic Retinopathy (DR) classification. The baseline for com- parison is set as joint training on different datasets, followed by testing on each dataset individually. We therefore introduce a method that encourages seeking a flatter minima during training while imposing a regularization. This reduces gradient variance from different domains and therefore yields satisfactory results on out-of-domain DR classification. We show that adopting DR-appropriate augmentations enhances model performance and in-domain generalizability. By performing our evaluation on 4 open-source DR datasets, we show that the proposed domain generalization method outperforms separate and joint training strategies as well as well-established methods.
Citation
M.Z.A. Atwany, "DRGen: Domain Generalization in Diabetic Retinopathy Classification", M.S. Thesis, Machine Learning, MBZUAI, Abu Dhabi, UAE, 2022.