AUTHOR=Li Wenjing , Xiao Yalong , Hu Hangyu , Zhu Chengzhang , Wang Han , Liu Zixi , Sangaiah Arun Kumar 

TITLE=Retinal Vessel Segmentation Based on B-COSFIRE Filters in Fundus Images

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.914973

DOI=10.3389/fpubh.2022.914973

ISSN=2296-2565

ABSTRACT=Retinal vessel extraction plays an important role in the diagnosis of several medical
pathologies such as diabetic retinopathy, glaucoma and so on. In this paper, we propose an
efficient method based on B-COSFIRE filter to tackle two challanging problems in fundus
vessels segmentation, which are (i) Difficulties in improving segmentation performance and
time efficiency together and (ii) Difficulties in distinguishing the thin vessel from the vessel like noise. In the proposed method, firstly we used Contrast Limited Adaptive Histogram
Equalization (CLAHE) for contrast enhancement, then excerpted Region of Interest (ROI)
by thresholding the luminosity plane of the CIELab version of the original RGB image. We
employed a set of B-COSFIRE filters to detect vessels and morphological filters to remove
noise. Binary threshold was used for vessels segmentation. Finally, a post-processing
method based on connected domains was used to eliminate unconnected non-vessel
pixels and to obtain the final vessel image. Based on the binary vessel map obtained, we
attempt to evaluate the performance of the proposed algorithm on three publicly available
databases (DRIVE, STARE and CHASEDB1 database) of manually labeled images. The
proposed method requires little processing time (around 12 seconds for each image) and
results in the average accuracy, sensitivity and specificity of 0.9604, 0.7339 and 0.9847
for DRIVE database, 0.9558, 0.8003 and 0.9705 for STARE database respectively. The
results demonstrate that the proposed method has potential capability in computer-aided
diagnosis.