Blood Vessel Extraction Using Combination of Kirsch's Templates and Fuzzy C-Means (FCM) on Retinal Images

1st International Conference on Mechanical Electronic and Biosystem Engineering

Azani Mustafa, Wan^1 ; Syauqi Mahmud, Ahmad^1 ; Khairunizam, Wan^2 ; Razlan, Z.M.^2 ; Shahriman, A.B.^2 ; Zunaidi, I.^3

Department of Electrical Technology Engineering, Faculty of Engineering Technology, Universiti Malaysia Perlis, UniCITI Alam Campus, Sungai Chuchuh, Padang Besar, Perlis

02100, Malaysia^1

School of Mechatronics Engineering, Universiti Malaysia Perlis, Arau

02600, Malaysia^2

Faculty of Technology, University of Sunderland, St Peter's Campus, SR6 0DD, Sunderland, United Kingdom^3

关键词: Blood vessel detection;    Blood vessel extraction;    Effective performance;    High blood pressures;    Image quality assessment (IQA);    New medical technologies;    Retinal image analysis;    Sensitivity and specificity;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/557/1/012009/pdf
DOI  :  10.1088/1757-899X/557/1/012009

来源: IOP

【 摘 要 】

Disease diagnosis based on retinal image analysis is very popular in order to detect a few critical diseases such as diabetic retinopathy, high blood pressure, cancer and glaucoma. The important part in the retinal is a blood vessel. Besides, the blood vessel study plays an important part in different medical areas such as ophthalmology, oncology, and neurosurgery. The significance of the vessel analysis was helped by the continuous overview in clinical studies of new medical technologies intended for improving the visualization of vessels. In this paper, a new blood vessel detection based on a combination of Kirsch's templates and Fuzzy C-Means (FCM) was proposed. The main objective of this study is to improve the detection result of FCM and achieved more effective performance compared to the Kirsch's templates result. The proposed method experimented on 20 images is utilized namely from Digital Retina Images for Vessel Extraction (DRIVE) dataset. The resulting images are compared with the benchmark images based on a few image quality assessment (IQA) such as accuracy, sensitivity and specificity. The total average of accuracy is 92.64%, while sensitivity and specificity got 95.73% and 60.45% respectively.