OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing
Zhu W*, Qiu P*, Dumitrascu O, Sobczak J, Farazi M, Yang Z, Nandakumar K, Wang Y
Abstract
Non-mydriatic retinal color fundus photography (CFP) is widely available due to the advantage of not requiring pupillary dilation, however, is prone to poor quality due to operators, systemic imperfec- tions, or patient-related causes. Optimal retinal image quality is man- dated for accurate medical diagnoses and automated analyses. Herein, we leveraged the Optimal Transport (OT) theory to propose an unpaired image-to-image translation scheme for mapping low-quality retinal CFPs to high-quality counterparts. Furthermore, to improve the flexibility, ro- bustness, and applicability of our image enhancement pipeline in the clinical practice, we generalized a state-of-the-art model-based image re- construction method, regularization by denoising, by plugging in pri- ors learned by our OT-guided image-to-image translation network. We named it as regularization by enhancing (RE). We validated the in- tegrated framework, OTRE, on three publicly available retinal image datasets by assessing the quality after enhancement and their perfor- mance on various downstream tasks, including diabetic retinopathy grad- ing, vessel segmentation, and diabetic lesion segmentation. The experi- mental results demonstrated the superiority of our proposed framework over some state-of-the-art unsupervised competitors and a state-of-the- art supervised method.
paper link: https://arxiv.org/abs/2302.03003
date of publication: Jun. 2023