A CCA Approach for Multiview Analysis to Detect Rigid Gas Permeable Lens Base Curve

Abstract

Multi-view learning has been one of the focuses in medical image analysis in recent years. The combination of various image properties for medical decision making has had a high impact in the medical field. The Pentacam four refractive is one of the sources for detecting Rigid Gas Permeable (RGP) lenses properties for irregular astigmatism patients. We present a radial-sectoral segmentation approach to analyze the Pentacam four refractive maps individually. Canonical Correlation Analysis (CCA) and a two hidden layer neural network is applied as a means of multi-view learning and base curve identification. The combination of the segmentation method with CCA combinatory feature vector, results in a 0.970 coefficient of determination in RGP base curve identification. This result considerably improves current findings and confirms optometrist findings based on the importance of the image maps. The proposed method has a great impact on reducing patient chair time and optometrist and patient satisfaction.