Identification and measurement of blood vessels in retinal images could allow quantitative evaluation of clinical features, which may allow early diagnosis and effective monitoring of therapies in retinopathy. A new system is proposed for the automatic extraction of the vascular structure in retinal images, based on a sparse tracking technique. After processing pixels on a grid of rows and columns to determine a set of starting points (seeds), the tracking procedure starts. It moves along the vessel by analyzing subsequent vessel cross sections (lines perpendicular to the vessel direction), and extracting the vessel center, calibre and direction. Vessel points in a cross section are found by means of a fuzzy c-means classifier. When tracking stops because of a critical area, e.g. low contrast, bifurcation or crossing, a "bubble technique" module is run. It grows and analyzes circular scan lines around the critical points, allowing the exploration of the vessel structure beyond the critical areas. After tracking the vessels, identified segments are connected by a greedy connection algorithm. Finally bifurcations and crossings are identified analyzing vessel end points with respect to the vessel structure. Numerical evaluation of the performances of the system compared to human expert are reported.

No abstract

Automatic tracking of blood vessels in images of retinal fundus is an important and non-invasive procedure for the diagnosis of many diseases. Tracking techniques often present a high rate of false positives. This paper presents six methods to discriminate false detections from true positives, each based on a different model of the vessel. They describe a candidate vessel in terms of its average geometric and grayscale properties considered along the full trajectory of the vessel itself. The rationale is that false vessels are caused by the small scale of the tracking algorithm necessary during the tracking phase. Once tracking has been completed, we can gather information from the full vessel trajectory and solve ambiguities that cannot be fixed during tracking. We apply Fisher linear discriminant analysis to these features to get the desired discrimination. Results on 28 images show satisfactory rejection of false positives and better results when using more complex models.

No abstract