Micro-aneurysm detection using vessels removal and circular Hough transform

A digital image processing system has been developed to quantify the presence of micro-aneurysms in retinal fluorescein angiographic images. Automatic detection of micro-aneurysm in retinal angiographic images provides a valuable tool for early diagnosis of diabetic retinopathy. A novel approach for detecting micro-aneurysm in retinal angiographic images is presented. The proposed scheme is based on the removal of blood vessels from the image and then classifying whether all detected circular objects are micro-aneurysms. The new technique provides significant improvement in the detection of micro-aneurysm over other currently available schemes in the literature.