| Summary: | Keratoconus (KC) is a type of eye disease that involves the thinning of the corneal layer and a change in the semispherical shape of the cornea to a bulging cone shape when viewed laterally. KC is difficult to detect in the early stages of the disease, as the patient does not feel any pain. Hence, the development of a KC detection (KD) method using a digital image processing approach is needed for the early detection of KC so that physicians can provide patients with the subsequent treatment sooner. The objective of this study was to develop a method of KD using a camera from a smart device to capture anterior and lateral segment photographed eye images (A&LSPIs). A total of 280 images comprising 140 KC and 140 normal A&LSPIs were used in this study, and all images were validated by a qualified expert. First, the corneal area of both image views was segmented so the geometric features could be extracted using the automated modified active contour model and the semiautomated spline function for the anterior and lateral images, respectively. Then, the features were selected using infinite latent feature selection (ILFS) by identifying the feature rankings based on the graph weighting that was automatically learned by the probabilistic latent semantic analysis (PLSA). The results showed that the all-combined features, where the proposed and improved features were successfully top ranked, had 96.05% accuracy, 98.41% sensitivity and 93.65% specificity with the RFn=50 classifier, outperforming the 7-NNMaha and SVMRBF classifiers. In conclusion, this study successfully developed a keratoconus detection system based on fusion features using a digital image processing approach for A&LSPIs captured with a smartphone camera.
|
|---|
