Predicting spatio-temporal radiofrequency ablation temperature using deep neural networks

Radiofrequency ablation (RFA) of the medial branch nerve is a widely used therapeutic intervention for facet joint pain. However, denervation of the multifidus muscle is an inevitable consequence of RFA. New ablation techniques with the potential to prevent muscle denervation can be designed using computational simulations. However, depending on the complexity of the model, they could be computationally expensive. As an alternative approach, deep neural networks (DNNs) can be used to predict tissue temperature during RFA procedure. The objective of this paper is to predict the tissue spatial and temporal temperature distributions during RFA using DNNs. First, finite element (FE) models with a range of distances between the probes were run to obtain the temperature readings. The measured temperatures were then used to train the DNNs that predict the spatio-temporal temperature distribution within the tissue. Finally, a separate data obtained from FE simulations were used to test the efficacy of the network. The results presented in this paper demonstrate that the network can achieve an error rate as low as 0.05%, accompanied by a 92% reduction in time compared to FE simulations. The approach proposed in this study will play a major role in the design of new RFA treatments for facet joint pain.

Design of a Novel Electrode of Radiofrequency Ablation for Large Tumors: In Vitro Validation and Evaluation

In the present study, a monopolar expandable electrode (MEE) in radiofrequency ablation (RFA) proposed in our previous study was validated and evaluated using the in vitro experiment and computer simulation. Two commercial RF electrodes (conventional electrode, CE and umbrella electrode, UE) was used to compare the ablation results with MEE using the in vitro egg white model (experiment and computer simulation) and in vivo liver tumor model (computer simulation) to verify the efficacy of MEE in the large tumor ablation. The sharp increase in impedance during RFA procedures was taken as the termination of RFA protocols. The volume and sphericity of ablation zone generated by MEE, CE, and UE in the in vitro egg white experiment were 75.3 1.6 cm3, 2.7 0.4 cm3, 12.4 1.8 cm3 (P <0.001), and 88.1 0.9%, 12.9 1.3%, 62.0 3.0% (P <0.001), respectively. Correspondingly, a similar result was obtained in the egg white simulation. In the liver tumor simulation, the volume and sphpericity of ablation zone generated by MEE, CE, and UE were 35.4 cm3 and 86.8%, 3.7 cm3 and 17.7%, and 12.7 cm3 and 59.6%, respectively. In summary, MEE has the potential to achieve complete ablation in the treatment of large tumors (>3 cm in diameter) compared with CE and UE due to the larger electrode-tissue interface and more round shape of hooks.