logo
ResearchBunny Logo
Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

Medicine and Health

Convolutional neural network-based classification of glaucoma using optic radiation tissue properties

J. Kruper, A. Richie-halford, et al.

This groundbreaking study explores how glaucoma affects brain connections, utilizing diffusion MRI to compare 905 glaucoma patients with 5292 healthy individuals. The authors found that convolutional neural networks focusing on optic radiations outperform traditional models in classifying glaucoma, revealing a unique signature in optic radiation tissue. Conducted by a multidisciplinary team from universities and hospitals, this research sheds light on an unexpected link between eye health and brain connectivity.

00:00
00:00
Playback language: English
Abstract
This study investigates the link between glaucoma and alterations in brain connections using diffusion MRI measurements of white matter tissue in 905 glaucoma patients and 5292 healthy individuals from the UK Biobank. Convolutional neural networks (CNNs) focusing on optic radiations showed higher accuracy in classifying glaucoma compared to CNNs using non-visual brain connections or regularized linear regression models. The CNN did not generalize to age-group or age-related macular degeneration classification, suggesting a distinct glaucoma signature in optic radiation tissue properties.
Publisher
Communications Medicine
Published On
Apr 11, 2024
Authors
John Kruper, Adam Richie-Halford, Noah C. Benson, Sendy Caffarra, Julia Owen, Yue Wu, Catherine Egan, Aaron Y. Lee, Cecilia S. Lee, Jason D. Yeatman, Ariel Rokem, UK Biobank Eye and Vision Consortium
Tags
glaucoma
brain connections
diffusion MRI
optic radiations
convolutional neural networks
UK Biobank
white matter
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny