TY - JOUR
T1 - Contrast normalization steps for increased sensitivity of a retinal image segmentation method
AU - Soomro, Toufique Ahmed
AU - Khan, Mohammad A.U.
AU - Gao, Junbin
AU - Khan, Tariq M.
AU - Paul, Manoranjan
PY - 2017/11
Y1 - 2017/11
N2 - Retinal vessel segmentation plays a major role in the detection of many eye diseases, and it is required to implement an automated algorithm for analyzing the progress of eye diseases. A variety of automated segmentation methods have been presented but almost all studies to date showed weakness in their low sensitivity toward narrow low-contrast vessels. A new segmentation method is proposed to address the issue of low sensitivity, by including modules such as principal component analysis-based color-to-gray conversion, scale normalization factors for improved narrow vessel detection, anisotropic diffusion filtering with an adequate stopping rule, and edge pixel-based hysteresis threshold. The impact of these additional steps is assessed on publicly available databases like DRIVE and STARE. For the case of DRIVE database, the sensitivity is raised from 73 to 75%, while maintaining the accuracy of 96.5%, and found to provide evidence of improved sensitivity.
AB - Retinal vessel segmentation plays a major role in the detection of many eye diseases, and it is required to implement an automated algorithm for analyzing the progress of eye diseases. A variety of automated segmentation methods have been presented but almost all studies to date showed weakness in their low sensitivity toward narrow low-contrast vessels. A new segmentation method is proposed to address the issue of low sensitivity, by including modules such as principal component analysis-based color-to-gray conversion, scale normalization factors for improved narrow vessel detection, anisotropic diffusion filtering with an adequate stopping rule, and edge pixel-based hysteresis threshold. The impact of these additional steps is assessed on publicly available databases like DRIVE and STARE. For the case of DRIVE database, the sensitivity is raised from 73 to 75%, while maintaining the accuracy of 96.5%, and found to provide evidence of improved sensitivity.
KW - Retinal images
KW - Scale normalization
KW - PCA
KW - Hysteresis threshold
UR - http://www.scopus.com/inward/record.url?scp=85019609586&partnerID=8YFLogxK
U2 - 10.1007/s11760-017-1114-7
DO - 10.1007/s11760-017-1114-7
M3 - Article
AN - SCOPUS:85019609586
SN - 1863-1703
VL - 11
SP - 1509
EP - 1517
JO - Signal, Image and Video Processing
JF - Signal, Image and Video Processing
IS - 8
ER -