Automatic detection of pathological myopia using variational level set

Pathological myopia, the seventh leading cause of legal blindness in United States, is a condition caused by pathological axial elongation and eyes that deviates from the normal distribution curve of axial length, resulting in impaired vision. Studies have shown that ocular risks associated with myopia should not be underestimated, and there is a public health need to prevent the onset or progression of myopia. Peripapillary atrophy (PPA) is one of the clinical indicators for pathological myopia. In this paper, we introduce a novel method, to detect pathological myopia via peripapaillary atrophy feature by means of variational level set. This method is a core algorithm of our system, PAMELA, an automated system for the detection of pathological myopia. The proposed method has been tested on 40 images from Singapore Cohort study Of the Risk factors for Myopia (SCORM), producing a 95% accuracy of correct assessment, and a sensitivity and specificity of 0.9 and 1 respectively. The results highlight the potential of PAMELA as a possible clinical tool for objective mass screening of pathological myopia.