Automatic pterygium detection on cornea images to enhance computer-aided cortical cataract grading system

In this paper, we present a new method to detect pterygiums using cornea images. Due to the similarity of appearances and spatial locations between pterygiums and cortical cataracts, pterygiums are often falsely detected as cortical cataracts on retroillumination images by a computer-aided grading system. The proposed method can be used to filter out the pterygium which improves the accuracy of cortical cataract grading system. This work has three major contributions. First, we propose a new pupil segmentation method for visible wavelength images. Second, an automatic detection method of pterygiums is proposed. Third, we develop an enhanced compute-aided cortical cataract grading system that excludes pterygiums. The proposed method is tested using clinical data and the experimental results demonstrate that the proposed method can improve the existing automatic cortical cataract grading system.