Monitoring of irrigated lesion formation with single fiber based multispectral system using machine learning

Abstract

In radiofrequency ablation (RFA) treatment of cardiac arrhythmias, intraprocedural assessment of treatment efficacy relies on indirect measures of adequate tissue destruction. Direct sensing of diffuse reflectance spectral changes at the ablation site using optically integrated RFA catheters has been shown to enable accurate prediction of lesion dimensions, ex vivo. Challenges of optical guidance can be due to obtaining reliable measurements under various catheter-tissue contact orientations. In this work, addressed this limitation by assessing the feasibility of monitoring lesion progression using single-fiber reflectance spectroscopy (SFRS). A total of 110 endocardial lesions of various sizes were generated in freshly excised swine right ventricular tissue using a custom-built, irrigated SFRS-RFA catheter. Models were developed for assessing catheter-tissue contact, the presence of nontransmural or transmural lesions and lesion depth percentage. These results support the use of SFRS-based catheters for irrigated lesion assessment and motivate further exploration of using multi-SFRS catheters for omnidirectionality.

Keywords: cardiac ablation therapy; machine learning; near infrared spectroscopy; radio frequency ablation.