Detection of Fundus Lesions Using Classifier Selection

A system for detecting fundus lesions caused by diabetic retinopathy from fundus images is being developed. The system can screen the images in advance in order to reduce the inspection workload on doctors. One of the difficulties that must be addressed in completing this system is how to remove false positives (which tend to arise nearby blood vessels) without decreasing the detection rate of lesions in other areas. To overcome this difficulty, we developed so-called “dynamic selection” of a classifier according to the position of a candidate lesion, and we introduced new features that can distinguish true lesions from false positives. The system—incorporating dynamic selection and these new features—was tested in experiments using 55 fundus images with some lesions and 223 images without lesions. The results of the experiments confirm the effectiveness of the proposed system, namely, degrees of sensitivity and specificity of 98% and 81%, respectively.

• Type: Conference
• Year: 2007
• Where: MVA
• Authors: Hiroto Nagayoshi, Yoshitaka Hiramatsu, Hiroshi Sako, Mitsutoshi Himaga, Satoshi Kato
• Keywords: Computer Vision, Fundus Images, Fundus Lesions, Lesions, MVA 2007