Autonomous assessment of spontaneous retinal venous pulsations in fundus videos using a deep learning framework.

Autor: Panahi A; Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran., Rezaee A; Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran. arrezaee@ut.ac.ir., Hajati F; Intelligent Technology Innovation Lab (ITIL) Group, Institute for Sustainable Industries and Liveable Cities, Victoria University, Footscray, Australia., Shariflou S; Vision Science Group, Graduate School of Health, University of Technology Sydney, Ultimo, Australia., Agar A; Ophthalmology Department, Prince of Wales Hospital, Sydney, NSW, Australia.; Department of Ophthalmology, University of New South Wales, Sydney, NSW, Australia.; Marsden Eye Specialists, Sydney, NSW, Australia., Golzan SM; Vision Science Group, Graduate School of Health, University of Technology Sydney, Ultimo, Australia.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2023 Sep 02; Vol. 13 (1), pp. 14445. Date of Electronic Publication: 2023 Sep 02.
DOI: 10.1038/s41598-023-41110-8
Abstrakt: The presence or absence of spontaneous retinal venous pulsations (SVP) provides clinically significant insight into the hemodynamic status of the optic nerve head. Reduced SVP amplitudes have been linked to increased intracranial pressure and glaucoma progression. Currently, monitoring for the presence or absence of SVPs is performed subjectively and is highly dependent on trained clinicians. In this study, we developed a novel end-to-end deep model, called U3D-Net, to objectively classify SVPs as present or absent based on retinal fundus videos. The U3D-Net architecture consists of two distinct modules: an optic disc localizer and a classifier. First, a fast attention recurrent residual U-Net model is applied as the optic disc localizer. Then, the localized optic discs are passed on to a deep convolutional network for SVP classification. We trained and tested various time-series classifiers including 3D Inception, 3D Dense-ResNet, 3D ResNet, Long-term Recurrent Convolutional Network, and ConvLSTM. The optic disc localizer achieved a dice score of 95% for locating the optic disc in 30 milliseconds. Amongst the different tested models, the 3D Inception model achieved an accuracy, sensitivity, and F1-Score of 84 ± 5%, 90 ± 8%, and 81 ± 6% respectively, outperforming the other tested models in classifying SVPs. To the best of our knowledge, this research is the first study that utilizes a deep neural network for an autonomous and objective classification of SVPs using retinal fundus videos.
(© 2023. Springer Nature Limited.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje