@article{Hou:23,
author = {Benjamin Hou},
journal = {Biomed. Opt. Express},
keywords = {Computed tomography; Image processing; Image quality; Medical imaging; Retina scanning; X ray imaging},
number = {2},
pages = {533--549},
publisher = {Optica Publishing Group},
title = {High-fidelity diabetic retina fundus image synthesis from freestyle lesion maps},
volume = {14},
month = {Feb},
year = {2023},
url = {https://opg.optica.org/boe/abstract.cfm?URI=boe-14-2-533},
doi = {10.1364/BOE.477906},
abstract = {Retina fundus imaging for diagnosing diabetic retinopathy (DR) is an efficient and patient-friendly modality, where many high-resolution images can be easily obtained for accurate diagnosis. With the advancements of deep learning, data-driven models may facilitate the process of high-throughput diagnosis especially in areas with less availability of certified human experts. Many datasets of DR already exist for training learning-based models. However, most are often unbalanced, do not have a large enough sample count, or both. This paper proposes a two-stage pipeline for generating photo-realistic retinal fundus images based on either artificially generated or free-hand drawn semantic lesion maps. The first stage uses a conditional StyleGAN to generate synthetic lesion maps based on a DR severity grade. The second stage then uses GauGAN to convert the synthetic lesion maps into high resolution fundus images. We evaluate the photo-realism of generated images using the Fr\&\#x00E9;chet inception distance (FID), and show the efficacy of our pipeline through downstream tasks, such as; dataset augmentation for automatic DR grading and lesion segmentation.},
}