歯学ジャーナル
オープンアクセス
ISSN: 2155-9570
ISSN: 2155-9570
Alauddin Bhuiyan, Ryo Kawasaki, Mariko Sasaki, Ecosse Lamoureux, Kotagiri Ramamohanarao, Robyn Guymer, Tien Y Wong and Kanagasingam Yogesan
Objective: To develop a method for detecting drusen and quantifying drusen size in macular region from standard color retinal images for early diagnosis of Age related Macular Degeneration (AMD).
Materials and methods: Color retinal images were used which were captured by Canon D60 non-mydriatic camera for genetic and epidemiology study. Local intensity distribution, adaptive intensity thresholding and edge information were used to detect potential drusen areas. For validation, we considered 50 images with various types of drusen. For the drusen area segmentation accuracy (DAA), 12 images were selected, and an expert grader marked the drusen regions in pixel level. We then quantified the areas and compute the sensitivity and specificity by comparing the drusen detected output images with the hand-labeled ground truth (GT) images.
Results: The proposed method detected the presence of any drusen with 100% accuracy (50/50 images). For drusen detection accuracy (pixel level), mean sensitivity and specificity values of 74.94% and 81.17%, respectively. For drusen subtypes we achieved 79.59% accuracy in intermediate drusen and 82.14% in soft drusen which is a highly significant result for early and intermediate AMD detection.
Conclusion: In this study, we applied a novel automated method for drusen detection and quantification which is ready to be used in initial screening of early stage of AMD and drusen area changes i.e., AMD progression. The method will also be highly suitable for telemedicine platforms in ophthalmology for selecting patient from rural areas using fundus imaging - for refereeing to an expert ophthalmologist.