Supervised retinal vessel segmentation based on neural network using broader aging dataset

• Main Authors: Che Azemin, Mohd Zulfaezal, Abd Hamid, Fadilah, Mohd Tamrin, Mohd Izzuddin, Muhamad Amin, Anang Hudaya
• Format: Conference or Workshop Item
• Language: English; English
• Published: 2014
• Subjects: RE Ophthalmology; TK7885 Computer engineering
• Online Access: http://irep.iium.edu.my/39631/1/IWBBIO_2014_paper_131.pdf; http://irep.iium.edu.my/39631/4/IWBBIO_2014_DEFINITIVE_PROGRAM.pdf; http://irep.iium.edu.my/39631/; http://iwbbio.ugr.es/2014/papers/IWBBIO_2014_paper_131.pdf
• Institution: Universiti Islam Antarabangsa Malaysia

Retina image quality is affected by numerous factors including aging, refractive condition, and media opacity. Distracters that exist in certain age groups may not be present in another. This is evident when the retinal nerve fiber layer is more visible in younger age group, tricking the vessel segmentation algorithm to label it as vessel thus affecting the specificity performance of the supervised retinal ves-sel segmentation. This research work aims to investigate the impact of aging to the performance of the supervised vessel segmentation. The results suggest dif-ferent age groups affect different aspect of the segmentation performance. Sensi-tivity is estimated to reduce by 4.633% for every 10- year increase of age (p<0.001), and specificity is estimated to reduce by 0.543% for every 10-year decrease of age (p<0.001).