Improving Consistency in Cardiovascular Disease Risk Assessment: Cross-Camera Adaptation for Retinal Images

Abstract

This paper introduces a novel cross-camera domain adaptation method to address the challenges associated with achieving consistency and adaptability in cardiovascular disease (CVD) risk assessment using retinal images captured by conventional and portable cameras. The proposed method leverages an enhanced ordinal CVD risk classification approach to predict CVD risk levels, effectively capturing the ordinal relationship and implicit information embedded within retinal images. Additionally, a plug-and-play risk consistency loss is incorporated into the image translation model to ensure alignment in risk assessment between different image domains. Experimental evaluations on diverse datasets demonstrate the effectiveness and superiority of the proposed method in achieving consistent CVD risk assessment across various camera models. The results highlight the potential of the proposed approach to enhance early detection and intervention of CVD, utilizing the convenience and cost-effectiveness of portable retinal imaging technology. Overall, this research contributes to the field of computer-aided medical imaging by providing a robust and adaptable solution for CVD risk assessment, ultimately benefiting patients and healthcare providers in their efforts to combat CVD.