| Identifier |
20240305_nanos_posters_425 |
| Title |
Assessing the Performance of Deep Learning in Classifying Visual Field Patterns Using Humphrey Images |
| Creator |
Shehroz Rana; Anfei Li; John Paddock; Cristiano Oliveira; Marc Dinkin |
| Affiliation |
(SR) Weill Cornell Medical College in Qatar; (AL) (CO) Weill Cornell Medicine, Department of Ophthalmology; (JP) (MD) Weill Cornell Medicine, Department of Ophthalmology and Neurology |
| Subject |
Visual Fields; Perimetry; Diagnostic Tests (ERG, VER, OCT, HRT, mfERG, etc); Eyelid & Adnexal Disease |
| Description |
Recognizing patterns of vision loss is crucial in diagnosing and monitoring a wide array of ocular and neurological diseases. We utilized artificial intelligence algorithms to classify visual field defects (VFDs) using a type of deep neural network called convolutional neural networks (CNNs), which are particularly well-suited for image classification. We classified VFDs into 13 distinct patterns: "Altitudinal field defect", "Arcuate defect", "Cecocentral scotoma", "Central scotoma", "Blind-spot enlargement", "Peripheral field constriction", "Nasal step", "Homonymous hemianopia", "Superior quadrantanopia", "Inferior quadrantanopia", "Bitemporal hemianopia", "Nonspecific defect", and "No defect". |
| Date |
2024-03 |
| References |
Li, Wang, Qu, Song, Yuan; Automatic differentiation of Glaucoma visual field from non-glaucoma visual field using deep convolutional neural network, BMC Med Imaging 18, 35, 2018. Abu, Zahri, Amir, Ismail, Yaakub, Fukumoto, Suzuki; Analysis of the Effectiveness of Metaheuristic Methods on Bayesian Optimization in the Classification of Visual Field Defects, Diagnostics, 13, 1946, 2023. Abu, Zahri, Amir, Ismail, Kamarudin; Classification of multiple visual field defects using Deep Learning, Journal of Physics: Conference Series, 1755, 01, 2021. Saeedi, Boland, D'Acunto, Swamy, Hegde; Development and comparison of machine learning algorithms to determine visual field progression, Translational Vision Science & Technology, 10, 27, 2021. Simonyan, Zisserman; Very deep convolutional networks for large-scale image recognition, arXiv,1409, 1556, 2014. |
| Language |
eng |
| Format |
application/pdf |
| Type |
Text |
| Source |
2024 North American Neuro-Ophthalmology Society Annual Meeting |
| Relation is Part of |
NANOS Annual Meeting 2024: Poster Session: Analytical Studies: New Diagnostic Measurement Techniques |
| Collection |
Neuro-Ophthalmology Virtual Education Library: NANOS Annual Meeting Collection: https://novel.utah.edu/collection/nanos-annual-meeting-collection/ |
| Publisher |
North American Neuro-Ophthalmology Society |
| Holding Institution |
Spencer S. Eccles Health Sciences Library, University of Utah |
| Rights Management |
Copyright 2024. For further information regarding the rights to this collection, please visit: https://NOVEL.utah.edu/about/copyright |
| ARK |
ark:/87278/s62rqh3g |
| Setname |
ehsl_novel_nam |
| ID |
2594252 |
| Reference URL |
https://collections.lib.utah.edu/ark:/87278/s62rqh3g |
