Deep learning-based image quality assessment for optical coherence tomography macular scans: a multicentre study.

Autor:	Tang Z; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Wang X; Zhejiang Lab, Hangzhou, Zhejiang, China.; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China., Ran AR; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Yang D; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Ling A; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Yam JC; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Zhang X; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Szeto SKH; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Chan J; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Wong CYK; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Hui VWK; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Chan CKM; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Wong TY; Tsinghua Medicine, Tsinghua University, Beijing, China.; School of Clinical Medicine, Beijing Tsinghua Changgung Hospital, Beijing, China., Cheng CY; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.; Centre for Innovation and Precision Eye Health, Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore., Sabanayagam C; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.; Ophthalmology and Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore., Tham YC; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.; Centre for Innovation and Precision Eye Health, Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore., Liew G; Department of Ophthalmology, Westmead Institute for Medical Research, University of Sydney, Sydney, New South Wales, Australia., Anantharaman G; Giridhar Eye Institute, Cochin, India., Raman R; Shri Bhagwan Mahavir Vitreoretinal Services, Sankara Nethralaya, Chennai, India., Cai Y; Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China., Che H; Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China., Luo L; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China., Liu Q; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China., Wong YL; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Ngai AKY; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Yuen VL; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Kei N; School of Life Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Lai TYY; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China., Chen H; Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China.; Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China., Tham CC; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China.; Hong Kong Eye Hospital, Hong Kong SAR, China., Heng PA; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China pheng@cse.cuhk.edu.hk carolcheung@cuhk.edu.hk.; Institute of Medical Intelligence and XR, The Chinese University of Hong Kong, Hong Kong SAR, China., Cheung CY; Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China pheng@cse.cuhk.edu.hk carolcheung@cuhk.edu.hk.
Jazyk:	angličtina
Zdroj:	The British journal of ophthalmology [Br J Ophthalmol] 2024 Oct 22; Vol. 108 (11), pp. 1555-1563. Date of Electronic Publication: 2024 Oct 22.
DOI:	10.1136/bjo-2023-323871
Abstrakt:	Aims: To develop and externally test deep learning (DL) models for assessing the image quality of three-dimensional (3D) macular scans from Cirrus and Spectralis optical coherence tomography devices. Methods: We retrospectively collected two data sets including 2277 Cirrus 3D scans and 1557 Spectralis 3D scans, respectively, for training (70%), fine-tuning (10%) and internal validation (20%) from electronic medical and research records at The Chinese University of Hong Kong Eye Centre and the Hong Kong Eye Hospital. Scans with various eye diseases (eg, diabetic macular oedema, age-related macular degeneration, polypoidal choroidal vasculopathy and pathological myopia), and scans of normal eyes from adults and children were included. Two graders labelled each 3D scan as gradable or ungradable, according to standardised criteria. We used a 3D version of the residual network (ResNet)-18 for Cirrus 3D scans and a multiple-instance learning pipline with ResNet-18 for Spectralis 3D scans. Two deep learning (DL) models were further tested via three unseen Cirrus data sets from Singapore and five unseen Spectralis data sets from India, Australia and Hong Kong, respectively. Results: In the internal validation, the models achieved the area under curves (AUCs) of 0.930 (0.885-0.976) and 0.906 (0.863-0.948) for assessing the Cirrus 3D scans and Spectralis 3D scans, respectively. In the external testing, the models showed robust performance with AUCs ranging from 0.832 (0.730-0.934) to 0.930 (0.906-0.953) and 0.891 (0.836-0.945) to 0.962 (0.918-1.000), respectively. Conclusions: Our models could be used for filtering out ungradable 3D scans and further incorporated with a disease-detection DL model, allowing a fully automated eye disease detection workflow. Competing Interests: Competing interests: None declared. (© Author(s) (or their employer(s)) 2024. No commercial re-use. See rights and permissions. Published by BMJ.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu