ARTIFICIAL INTELLIGENCE TECHNIQUES IN VISUAL FIELD ASSESSMENT USING HUMPHREY FIELD ANALYSIS - A SURVEY

Abdalgadir, Tasneem Idris Abdallah; Amin, Salsabil; Mohamed, Thanaa Helmy; El-Horabty, El-Sayed M.

doi:10.21608/ijicis.2025.345323.1369

ARTIFICIAL INTELLIGENCE TECHNIQUES IN VISUAL FIELD ASSESSMENT USING HUMPHREY FIELD ANALYSIS - A SURVEY

Document Type : Original Article

Authors

¹ Computer Science Department, Faculty of Computer and Information Science, Ain Shams University, Cairo, Egypt

² Faculty of Computers and Information Sciences

³ Ophthalmology Department, Faculty of Medicine, Ain Shams University, Cairo, Egypt

⁴ Computer Science Department, Faculty of Computer and Information Sciences, Ain Shams University

10.21608/ijicis.2025.345323.1369

Abstract

Abstract: Visual field assessment is a critical component in the diagnosis and management of various ocular and neurological conditions. The Humphrey Field Analyzer (HFA) is a widely used instrument for this purpose, providing accurate and reliable measurements of the visual field. This review explores the principles, methodologies and clinical applications of Humphrey field analysis in visual field assessment and pre-diagnosis of glaucoma using Artificial Intelligence and deep learning. The clinical utility of HFA is demonstrated by its application in the diagnosis and monitoring of diseases such as glaucoma, retinal diseases, and neuro-ophthalmic disorders. In this comprehensive review, the models considered include CascadeNet-5 and Linear Regression, RGC-AC. Each model was trained on a labeled dataset and evaluated using standard performance metrics. Our results demonstrate that CascadeNet-5 outperforms other models in terms of predictive accuracy and sensitivity, while Linear Regression and RGC-AC exhibit comparable performance.
Keywords: Artificial Intelligence; Deep Learning; Visual Field; Glaucoma; Humphrey Field Analyzer.

Keywords