Real-time monitoring radiofrequency ablation using tree-based ensemble learning models

Abstract

Background: Radiofrequency ablation is a minimally-invasive treatment method that aims to destroy undesired tissue by exposing it to alternating current in the 100 kHz-800 kHz frequency range and heating it until it is destroyed via coagulative necrosis. Ablation treatment is gaining momentum especially in cancer research, where the undesired tissue is a malignant tumor. While ablating the tumor with an electrode or catheter is an easy task, real-time monitoring the ablation process is a must in order to maintain the reliability of the treatment. Common methods for this monitoring task have proven to be accurate, however, they are all time-consuming or require expensive equipment, which makes the clinical ablation process more cumbersome and expensive due to the time-dependent nature of the clinical procedure. Methods: A machine learning (ML) approach is presented that aims to reduce the monitoring time while keeping the accuracy of the conventional methods. Two different hardware setups are used to perform the ablation and collect impedance data at the same time and different ML algorithms are tested to predict the ablation depth in 3 dimensions, based on the collected data. Results: Both the random forest and adaptive boosting (adaboost) models had over 98% R 2 on the data collected with the embedded system-based hardware instrumentation setup, outperforming Neural Network-based models. Conclusions: It is shown that an optimal pair of hardware setup and ML algorithm (Adaboost) is able to control the ablation by estimating the lesion depth within a test average of 0.3mm while keeping the estimation time within 10ms on a Â86-64 workstation.

Domain Heterogeneity in Radiofrequency Therapies for Pain Relief: A Computational Study with Coupled Models

“…This compensates for the difference (error) between the set-point and the system response to the feedback control. As a result, the system can, in principle, utilize artificial intelligence (AI) and machine learning algorithms [ 40 , 41 , 42 , 43 , 44 ]. In the present computational study, the treatment time of the continuous RF procedure was set to 60 s.…”

“…Importantly, both machine learning and multiscale modeling complement each other in creating more robust predictive models in the current field of research [126,127]. Recently, several studies have been reported in the literature that have explored the application of AI and machine learning algorithms in the field of thermal therapies [40,[128][129][130][131][132][133][134][135][136]. The integration of machine learning with the coupled models could play a vital role in decision-making processes and the treatment planning stage of such procedures, e.g., by providing a priori information about electrode placement for enhancing treatment efficacy or by the real-time monitoring of the damage to the target tissue and other critical structures.…”

Thermal ablation of biological tissues in disease treatment: A review of computational models and future directions

“…The application of machine learning algorithms and models have also been explored in the thermal ablative procedures, either for the accurate and precise placement of the electrode or for the real-time monitoring of ablation volume (Besler et al, 2019a, Lötsch and Ultsch, 2018, Wang et al, 2018b, Yildiz and Özdemir, 2019, Zhang et al, 2019a, Besler et al, 2019b, Hajimolahoseini et al, 2018, Negro et al, 2019, Zhang and Chauhan, 2019. (Wang et al, 2018b) reported the application of an artificial neural network (ANN) for real-time estimation of the lesion depth and control of RFA within ex vivo animal tissue.…”

“…(Wang et al, 2018b) reported the application of an artificial neural network (ANN) for real-time estimation of the lesion depth and control of RFA within ex vivo animal tissue. Recently, (Besler et al, 2019a), reported a machine learning approach for prediction of the lesion depth during RFA utilizing a Random Forest and Adaptive Boosting model to reduce the monitoring time as compared to conventional methods. (Li et al, 2019) reported a study that incorporates the machine learning techniques with computer-assisted planning for optimizing the electrode trajectory during laser therapy of neurological disorder.…”

Design of low-cost and simple reconstruction method for Three Dimensional Electrical Impedance Tomography (3D-EIT) Imaging

“…Imaging techniques with EIT rely heavily on the instrumentation device's ability or hardware to produce accurate data and reconstruction algorithms in the reconstruction process [16][17][18]. There are still various improvements and developments, to both hardware and software, in a reconstruction algorithm to obtain maximum results [19,20].…”