Retinal Tracking Using Image Processing. Automated Retinal Vasculature Tracking In Gray-scale & Color Digital Fundus Images

      Аннотация: Some of the most common blinding conditions are caused by choroidal neovascularization (CNV). At present, the only proven modality of effective treatment is the application of laser energy to the CNV to cauterize the vessels. The current rate of success of this procedure is less than 50% for eradication of the CNV following one treatment session with a recurrence and/or persistence rate of about 50%. The latter condition requires re-treatment and each re-treatment, in turn, has a 50% failure rate. The visual recovery declines with each successive treatment. Indeed, several studies indicate that incomplete treatment was associated with poorer prognosis than no treatment. Because the eye and hence the retina is a moving object, a motion tracking method is required to update the position of laser shots according to the movements of the retina. A new computer-controlled instrument was developed in an attempt to minimize the above-mentioned failure rate. In this book, we designed many of the feature extraction and detection of motion parameters algorithms that may be required in the process of retinal vasculature tracking.

Ключевые слова: Feature extraction, Feature extraction, detection of motion parameters algorithms, retinal vasculature tracking, registeration