OCT-GAN: single step shadow and noise removal from optical coherence tomography images of the human optic nerve head

Cheong, Haris, Krishna Devalla, Sripad, Chuangsuwanich, Thanadet, Tun, Tin A., Wang, Xiaofei, Aung, Tin, Schmetterer, Leopold, Buist, Martin L., Boote, Craig ORCID: https://orcid.org/0000-0003-0348-6547, Thiéry, Alexandre H. and Girard, Michaël J. A. 2021. OCT-GAN: single step shadow and noise removal from optical coherence tomography images of the human optic nerve head. Biomedical Optics Express 12 (3) , pp. 1482-1498. 10.1364/BOE.412156

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Speckle noise and retinal shadows within OCT B-scans occlude important edges, fine textures and deep tissues, preventing accurate and robust diagnosis by algorithms and clinicians. We developed a single process that successfully removed both noise and retinal shadows from unseen single-frame B-scans within 10.4ms. Mean average gradient magnitude (AGM) for the proposed algorithm was 57.2% higher than current state-of-the-art, while mean peak signal to noise ratio (PSNR), contrast to noise ratio (CNR), and structural similarity index metric (SSIM) increased by 11.1%, 154% and 187% respectively compared to single-frame B-scans. Mean intralayer contrast (ILC) improvement for the retinal nerve fiber layer (RNFL), photoreceptor layer (PR) and retinal pigment epithelium (RPE) layers decreased from 0.362 ± 0.133 to 0.142 ± 0.102, 0.449 ± 0.116 to 0.0904 ± 0.0769, 0.381 ± 0.100 to 0.0590 ± 0.0451 respectively. The proposed algorithm reduces the necessity for long image acquisition times, minimizes expensive hardware requirements and reduces motion artifacts in OCT images.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Optometry and Vision Sciences
Publisher:	Optical Society of America
ISSN:	2156-7085
Date of First Compliant Deposit:	2 March 2021
Date of Acceptance:	15 January 2021
Last Modified:	25 Nov 2024 20:46
URI:	https://orca.cardiff.ac.uk/id/eprint/139022

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item