TY - JOUR
T1 - Brain-inspired algorithms for retinal image analysis
AU - Romeny, Bart M. ter Haar
AU - Bekkers, Erik J.
AU - Zhang, Jiong
AU - Abbasi-Sureshjani, Samaneh
AU - Huang, Fan
AU - Duits, Remco
AU - Dashtbozorg, Behdad
AU - Berendschot, Tos T. J. M.
AU - Smit-Ockeloen, Iris
AU - Eppenhof, Koen A. J.
AU - Feng, Jinghan
AU - Hannink, Julius
AU - Schouten, Johannes
AU - Tong, Mengmeng
AU - Wu, Hanhui
AU - van Triest, Han W.
AU - Zhu, Shanshan
AU - Chen, Dali
AU - He, Wei
AU - Xu, Ling
AU - Han, Ping
AU - Kang, Yan
PY - 2016/11
Y1 - 2016/11
N2 - Retinal image analysis is a challenging problem due to the precise quantification required and the huge numbers of images produced in screening programs. This paper describes a series of innovative brain-inspired algorithms for automated retinal image analysis, recently developed for the RetinaCheck project, a large-scale screening program for diabetic retinopathy and other retinal diseases in Northeast China. The paper discusses the theory of orientation scores, inspired by cortical multi-orientation pinwheel structures, and presents applications for automated quality assessment, optic nerve head detection, crossing-preserving enhancement and segmentation of retinal vasculature, arterio-venous ratio, fractal dimension, and vessel tortuosity and bifurcations. Many of these algorithms outperform state-of-the-art techniques. The methods are currently validated in collaborating hospitals, with a rich accompanying base of metadata, to phenotype and validate the quantitative algorithms for optimal classification power.
AB - Retinal image analysis is a challenging problem due to the precise quantification required and the huge numbers of images produced in screening programs. This paper describes a series of innovative brain-inspired algorithms for automated retinal image analysis, recently developed for the RetinaCheck project, a large-scale screening program for diabetic retinopathy and other retinal diseases in Northeast China. The paper discusses the theory of orientation scores, inspired by cortical multi-orientation pinwheel structures, and presents applications for automated quality assessment, optic nerve head detection, crossing-preserving enhancement and segmentation of retinal vasculature, arterio-venous ratio, fractal dimension, and vessel tortuosity and bifurcations. Many of these algorithms outperform state-of-the-art techniques. The methods are currently validated in collaborating hospitals, with a rich accompanying base of metadata, to phenotype and validate the quantitative algorithms for optimal classification power.
KW - Retina
KW - Diabetic retinopathy
KW - Multi-orientation
KW - Orientation scores
KW - Vessel analysis
KW - Tortuosity
KW - SE(2)
KW - Screening
U2 - 10.1007/s00138-016-0771-9
DO - 10.1007/s00138-016-0771-9
M3 - Article
SN - 0932-8092
VL - 27
SP - 1117
EP - 1135
JO - Machine Vision and Applications
JF - Machine Vision and Applications
IS - 8
ER -