Fully Automated Artery-Vein ratio and vascular tortuosity measurement in retinal fundus images
This work addresses the need for automated and comprehensive vascular feature extraction in medical imaging for conditions like diabetic retinopathy, but it appears incremental as it builds on prior vessel topology estimation.
The paper tackled the problem of measuring artery-vein ratio and vascular tortuosity in retinal fundus images by developing a fully automated technique that uses extracted vessel topology, achieving state-of-the-art artery-vein classification and complete vascular structure extraction.
Accurate measurements of abnormalities like Artery-Vein ratio and tortuosity in fundus images is an actively researched task. Most of the research seems to compute such features independently. However, in this work, we have devised a fully automated technique to measure any vascular abnormalities. This paper is a follow-up paper on vessel topology estimation and extraction, we use the extracted topology to perform A-V state-of-the-art Artery-Vein classification, AV ratio calculation, and vessel tortuosity measurement, all fully automated. Existing techniques tend to only work on the partial region, but we extract the complete vascular structure. We have shown the usability of this topology by extracting two of the most important vascular features; Artery-Vein ratio, and vessel tortuosity.