Automatic vessel segmentation on fundus images using vessel filtering and fuzzy entropy
- 141 Downloads
Vessel segmentation is a critical and challenging task for fundus image processing, which is precursor and essential first step to further vessel measurement and diagnosis. This paper proposes a novel hybrid automatic vessel segmentation method for the delineation of vessels on fundus images. The method consists of two main steps including Hessian-based vessel filtering and vessel segmentation. In vessel filtering, multi-scale linear filtering based on Hessian matrix is adapted to enhance vessels in the image. After vessel filtering, a novel two-dimensional histogram of filtering image is generated. Then, the thresholds are determined by the fuzzy entropic concepts. We demonstrate the effectiveness of the proposed method on real fundus images from DRIVE database. Quantification analysis is applied through three metrics with respect to manual delineated ground truth from one specialist. Compared to three other methods, the proposed method yields more complete and accurate results.
KeywordsVessel segmentation Fundus image Hessian matrix Vessel filtering Fuzzy entropic thresholding
This work is supported by the National Science Foundation of China (Grant Nos. 61471075, 61671091), National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2014BAI11B10), Chongqing Integrated Demonstration Project (CSTC2013jcsf10029), Wenfeng Innovation Foundation of CQUPT, University Innovation Team Construction Plan Funding Project of Chongqing (Smart Medical System and Key Techniques, CXTDG201602009), Chongqing Key Laboratory Improvement Plan (Chongqing Key Laboratory of Photoelectronic Information Sensing and Transmitting Technology, cstc2014pt-sy40001), Chongqing Research Program of Basic Research and Frontier Technology (cstc2017jcyjBX0057, cstc2017jcyjAX0328), Science and Technology research project of Chongqing Education Commission (KJ1704073), the Scientific Research Foundation of CQUPT(A2016-73), Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD) Fund, and Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology(CICAEET) Fund.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. In: Medical image computing and computer-assisted interventation—MICCAI’98. Springer, Berlin, pp 130–137Google Scholar
- Shanmugam V, Wahida Banu RSD (2013) Retinal blood vessel segmentation using an extreme learning machine approach. In: 2013 point-of-care healthcare technologies, pp 318–321. doi: 10.1109/PHT.2013.6461349
- Zhang L, Li Q, You J, Zhang D (2009) A modified matched filter with double-sided thresholding for screening proliferative diabetic retinopathy. IEEE Trans Inf Technol Biomed 13:528–534. doi: 10.1109/TITB.2008.2007201
- Zheng Y, Byeungwoo J, Xu D, Wu QMJ, Hui Z (2015) Image segmentation by generalized hierarchical fuzzy C-means algorithm. J Intell Fuzzy Syst 28:4024–4028Google Scholar