A Local Adaptive Segmentation of Vascular Network from Abnormal Retinal Images

Diabetes, hypertension, cerebral arteriosclerosis and other diseases have become great threats to human health, so it is urgent to explore their initial symptoms for early prevention and treatment. As an important part of small and medium-sized vessels of human body, retinal vessel is the only deep capillary that can be non-traumatic directly observed and its morphology, such as vascular diameter, shape and distribution, is deeply influenced by these diseases. So an effective vascular detection and features measurement will help make more accurate diagnosis of these diseases. This paper proposes a local adaptive segmentation to detect more accurate retinal vascular network from abnormal retinal images which contain red and bright lesions. The retinal image is firstly segmented by weighted entropy with probability segmentation to detect preliminary vascular network. Then a two-dimensional partial differential matched filter is introduced into segmentation to differentiate lesions from vascular network based on a vascular property. The algorithm has been tested and compared with other vascular network segmentation algorithms on the publicly available STARE database since it contains retinal images where the vascular structure has been precisely marked by two experts. The experiments demonstrate that our approach is capable of detecting the vascular network effectively, offering a better segmentation results, especially on abnormal cases. Because of its effectiveness, simplicity and robustness for different image conditions, it is suitable for automated vascular analysis.