Classifying Small Volumes of Tissue for Real-Time Monitoring Radiofrequency Ablation

An increasingly-popular treatment for ablation of cancerous and non-cancerous masses is thermal ablation by radiofrequency joule heating. Real-time monitoring of the thermal tissue ablation process is essential in order to maintain the reliability of the treatment technique. Common methods for monitoring the extent of ablation have proven to be accurate, though they are time-consuming and often require powerful computers to run on, which makes the clinical ablation process more cumbersome and expensive due to the time-dependent nature of the clinical procedure. In this study, a Machine Learning (ML) approach is presented to reduce the time to calculate the progress of ablation while keeping the accuracy of the conventional methods. Different setups were used to perform the ablation and collect impedance data at the same time and different ML algorithms were tested to predict the ablation depth in three dimensions, based on the collected data. In the end, it is shown that an optimal pair of hardware setup and ML algorithm were able to control the ablation by estimating the lesion depth within an average of micrometer-magnitude error range while keeping the estimation time within 5.5 s on conventional x86-64 computing hardware.