An improved system for the automatic estimation of the Arteriolar-to-Venular diameter Ratio (AVR) in retinal images

Abstract

The Arteriolar-to-Venular diameter Ratio (AVR), a parameter derived from vessel caliber measurements in a specific region of retinal images, is used as a descriptor of generalized arteriolar narrowing, an eye fundus sign often seen in patients affected by hypertensive or diabetic retinopathies. We developed an improved system to compute AVR in a totally automatic way. Images are at first enhanced to highlight the vessel network, which is then traced by a vessel tracking algorithm. From the detected vessel structure, the position of the optic disc is derived and the region inside which the AVR data are to be measured is determined. Vessels within this region are classified as either arteries or veins, their caliber is estimated and the AVR parameter is eventually computed. Improvements with respect to the previous version are related to post-processing algorithms to enhance vessel tracking and a totally new artery/vein discrimination technique. Results provided by the new system have been compared with manually derived AVR values on 20 eye fundus images, resulting in a final correlation coefficient of 0.88.

Effective features for artery-vein classification in digital fundus images

“…For this reason several authors proposed methods to discriminate veins and arteries on retinal images [3,9,7] and/or complete frameworks for the automatic computation of AVR [1,4,6].…”

Automated construction of arterial and venous trees in retinal images

“…Then, we calculate P w using Eq. (15), where w p and w c are the absolute widths of the parent and child segments respectively introduced in Sec. 2.3.1.…”

“…E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 1 5 ; 3 2 6 ; 6 3 1 P w ¼ log ðw p − w c þ 1.5Þ: (15) For P i , we evaluate the cost of every child segment being connected to one parent over another parent using intensity information. Specially, for child segment v c , the cost p c is calculated using Eq.…”

“…[13][14][15][16][17][18][19][20] The common strategy is to first detect vessels as separated segments usually in terms of centerlines, and then to detect all different types of landmarks including bifurcations, crossing points and/or vessel end points. The vascular trees are built by iterating through the vessel segments and their connected landmarks.…”

Automatic Arteriovenous Ratio Computation: Emulating the Experts

“…These methods still require user assistance in some phases such as classification of vessels into arteries and veins, the location of the optic nerve or the selection of the suitable vessels for the computation. Recently, some automatic approaches have been presented [5]. However, the validation in large data sets and the testing of its prognosis capacity are currently pending tasks.…”