Automated Detection of Arteriovenous Crossing Phenomenon on Retinal Images
Arteriolosclerosis is one cause of acquired blindness. Retinal fundus image examination is useful for early detection of arteriolosclerosis. In order to diagnose the presence of arteriolosclerosis,the physicians find the silver-wire arteries,the copperwire arteries and arteriovenous crossing phenomenon on retinal fundus images. The focus of this study was to develop the automated detection method of the arteriovenous crossing phenomenon on the retinal images. The blood vessel regions were detected by using a double ring filter,and the cross sections of artery and vein were detected by using a ring filter. The center of that ring was an interest point,and that point was determined as a cross section when there were over four blood vessel segments on thai ring. And two blood vessels gone through on the ring were classified into artery and vein by using the pixel values on red and blue component image. Finally,V2-to-V,ratio was measured for recognition of abnormalities. V1 was the venous diameter far from the blood vessel cross section,and V2 was the venous diameter near from the blood vessel cross section. The cross section with Vr-to-Vt ratio over 0.8 was experimentally determined as abnormality. Twenty four images,including 27 abnormalities and 54 normal cross sections,were used for preliminary evaluation of the proposed method. The proposed method was detected 73％ of cross sections when the 2.8 sections per image were mis-detected. And,59％ of abnormalities were detected by measurement of Vr-to-V2 ratio when the 1.7 sections per image were mis-detected.
Arteriolosclerosis Hypertensive retinopathy Retinal Fundus image Arteriovenous crossing phenomenon Image analysis Computer-aided diagnosis
Yuji Hatanaka Chisako Muramatsu Takeshi Hara Hiroshi Fujita
School of Engineering,The University of Shiga Prefecture,Shiga 522-8533,Japan Graduate School of Medicine,Gifu University,Gifu 501-1194,Japan
国际会议
南宁
英文
340-343
2010-12-10（万方平台首次上网日期，不代表论文的发表时间）