Abstract #90140 Published in IGR 21-3

Automatic glaucoma screening using optic nerve head measurements and random forest classifier on fundus images

Bouacheria M; Cherfa Y; Cherfa A; Belkhamsa N
Physical and engineering sciences in medicine 2020; 43: 1265-1277

Glaucoma is an optic neuropathy that gradually steals the patient's sight by damaging the optic nerve head (which is responsible for transferring images from the eye to the brain). Causing an estimated 12.3% of global blindness, glaucoma is considered as the first leading cause of irreversible blindness in the world. This paper presents a novel eye fundus image analysis algorithm for the automatic measurement of fundus related glaucoma indicators; Cup to Disc Ratio (CDR), verification of the ISNT rule, Disc Damage Likelihood Scale (DDLS), and the classification of the input fundus into glaucoma or non-glaucoma case using a random forest model. The proposed method is applied on the public image database 'HRF', and a local database containing both, normal and glaucoma cases, and resulted sensitivity, specificity, and accuracy of 1, 0.93 and 0.97 respectively. This technique presented the highest classification accuracy compared to previous works studied in the state of the art; hence, it can be used as a computer aided glaucoma diagnosis system by ophthalmologists to assist in their screening routine.

Department of Electrical Engineering, University of Blida 1, BP 270 road soumaa, Blida, Algeria.

Full article


1.6 Prevention and screening (Part of: 1 General aspects)
6.30 Other (Part of: 6 Clinical examination methods)
6.8.2 Posterior segment (Part of: 6 Clinical examination methods > 6.8 Photography)

Issue 21-3

Change Issue