PROJECT TITLE :
Red Lesion Detection Using Dynamic Shape Features for Diabetic Retinopathy Screening
The development of an automatic telemedicine system for pc-aided screening and grading of diabetic retinopathy depends on reliable detection of retinal lesions in fundus pictures. During this paper, a novel technique for automatic detection of each microaneurysms and hemorrhages in color fundus pictures is described and validated. The main contribution could be a new set of shape features, referred to as Dynamic Form Options, that do not need precise segmentation of the regions to be classified. These features represent the evolution of the form throughout image flooding and permit to discriminate between lesions and vessel segments. The strategy is validated per-lesion and per-image using six databases, four of which are publicly on the market. It proves to be robust with respect to variability in image resolution, quality and acquisition system. On the Retinopathy On-line Challenge's database, the tactic achieves a FROC score of zero.420 which ranks it fourth. On the Messidor database, when detecting images with diabetic retinopathy, the proposed methodology achieves an area below the ROC curve of zero.eighty ninenine, adore the score of human experts, and it outperforms state-of-the-art approaches.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here