Biomarker identification and sorting for diabetic retinopathy

摘要

Diabetic retinopathy is a leading cause of blindness in the world. Diabetic patients can prevent their severe visual lost by attending regular eye examinations and receiving timely treatments. Standard protocols have been developed and refined over years to provide better screening procedures and evaluations of the fundus images. Due to the emerging number of diabetic retinopathy cases, accurate and efficient evaluations of the fundus images have become a serious burden for the ophthalmologists or service providers. In this paper, a sorting system, based upon a standardized ETDRS biomarker, is developed to aid the professional graders. The raw fundus images will be screened and assigned to different graders according to their skill levels and experiences. The developed hierarchical sorting process will greatly support the graders and to enhance their efficiency and throughput. The Hybrid Intelligent System with multi-level knowledge representation is used to construct this sorting system. The results obtained from the case study show a promising future.