Ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs.

Autor:	Pandey PU; School of Biomedical Engineering, The University of British Columbia, Vancouver, British Columbia, Canada., Ballios BG; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.; Krembil Research Institute, University Health Network, Toronto, Ontario, Canada.; Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada., Christakis PG; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.; Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada., Kaplan AJ; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada., Mathew DJ; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.; Krembil Research Institute, University Health Network, Toronto, Ontario, Canada.; Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada., Ong Tone S; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.; Sunnybrook Research Institute, Toronto, Ontario, Canada., Wan MJ; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada., Micieli JA; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.; Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada.; Department of Ophthalmology, St. Michael's Hospital, Unity Health, Toronto, Ontario, Canada., Wong JCY; Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada jovi.wong@mail.utoronto.ca.
Jazyk:	angličtina
Zdroj:	The British journal of ophthalmology [Br J Ophthalmol] 2024 Feb 21; Vol. 108 (3), pp. 417-423. Date of Electronic Publication: 2024 Feb 21.
DOI:	10.1136/bjo-2022-322183
Abstrakt:	Aims: To develop an algorithm to classify multiple retinal pathologies accurately and reliably from fundus photographs and to validate its performance against human experts. Methods: We trained a deep convolutional ensemble (DCE), an ensemble of five convolutional neural networks (CNNs), to classify retinal fundus photographs into diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and normal eyes. The CNN architecture was based on the InceptionV3 model, and initial weights were pretrained on the ImageNet dataset. We used 43 055 fundus images from 12 public datasets. Five trained ensembles were then tested on an 'unseen' set of 100 images. Seven board-certified ophthalmologists were asked to classify these test images. Results: Board-certified ophthalmologists achieved a mean accuracy of 72.7% over all classes, while the DCE achieved a mean accuracy of 79.2% (p=0.03). The DCE had a statistically significant higher mean F1-score for DR classification compared with the ophthalmologists (76.8% vs 57.5%; p=0.01) and greater but statistically non-significant mean F1-scores for glaucoma (83.9% vs 75.7%; p=0.10), AMD (85.9% vs 85.2%; p=0.69) and normal eyes (73.0% vs 70.5%; p=0.39). The DCE had a greater mean agreement between accuracy and confident of 81.6% vs 70.3% (p<0.001). Discussion: We developed a deep learning model and found that it could more accurately and reliably classify four categories of fundus images compared with board-certified ophthalmologists. This work provides proof-of-principle that an algorithm is capable of accurate and reliable recognition of multiple retinal diseases using only fundus photographs. Competing Interests: Competing interests: None declared. (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu