Vesselness via Multiple Scale Orientation Scores
This work addresses a domain-specific issue in medical imaging for retinal vascular analysis, offering an incremental improvement over an established method.
The paper tackled the problem of vessel enhancement in retinal images, particularly at crossings and bifurcations where the Frangi filter fails, by using multiple scale orientation scores to disentangle structures, resulting in considerably better performance than the Frangi version on a public dataset.
The multi-scale Frangi vesselness filter is an established tool in (retinal) vascular imaging. However, it cannot cope with crossings or bifurcations, since it only looks for elongated structures. Therefore, we disentangle crossing structures in the image via (multiple scale) invertible orientation scores. The described vesselness filter via scale-orientation scores performs considerably better at enhancing vessels throughout crossings and bifurcations than the Frangi version. Both methods are evaluated on a public dataset. Performance is measured by comparing ground truth data to the segmentation results obtained by basic thresholding and morphological component analysis of the filtered images.