Sign in Subscribe
Machine learning

Artificial Neural Network Model Predicts Thermal Lesion Size in Radiofrequency Ablation

Strategic Insights

— 1 min read

Researchers from Fudan University have developed an artificial neural network (ANN) model to predict the depth, width, and volume of ablation thermal lesions during radiofrequency cardiac ablation (RFCA). According to the study, the two-branch ANN model was able to predict thermal lesion size with errors of 0.1986 mm, 0.7891 mm, and 4.9384 mm, respectively. The model was trained on data from a finite element model of RFCA and tested on ex vivo experiments conducted on a swine model.

Key Takeaways:

  • The two-branch ANN model was able to predict the depth, width, and volume of thermal lesions during RFCA, a widely used treatment for atrial fibrillation (AF).
  • The model was trained on data from a finite element model of RFCA and tested on ex vivo experiments conducted on a swine model.
  • The model achieved errors of 0.1986 mm, 0.7891 mm, and 4.9384 mm in predicting the depth, width, and volume of ablation thermal lesions, respectively.
  • The two-branch ANN model was found to have superior predictive capabilities compared to other models regarding the depth, width, and volume of ablation thermal lesions.
  • The study introduces a two-branch ANN model as an efficient and reliable tool for predicting lesion size for RFCA, enhancing the model's ability to fit complex relationships through activation functions and nonlinear combination features.
  • Researchers Yuqi Wu, Tong Ren, Xiaomei Wu, and Shengjie Yan were involved in the study.
  • The research was published in the journal Cardiovascular Engineering and Technology in 2025.

Statistics:

  • The two-branch ANN model was trained on data from 10 sets of experiments using a swine model.
  • The neural network achieved errors of 0.1986 mm, 0.7891 mm, and 4.9384 mm in predicting the depth, width, and volume of ablation thermal lesions, respectively.
  • The model was able to simulate the process of thermal lesion formation during RFCA with a substantial amount of effective training data.
  • The ex vivo experiments provided reliable test data for the model.

Sources:

  • Prediction Model for Thermal Lesions in Radiofrequency Ablation Based on an Artificial Neural Network, Cardiovascular Engineering and Technology, 2025.
  • NewsRx, Fudan University Reports Findings in Artificial Neural Networks, Journal of Engineering, July 14, 2025; p 1179.
  • www.springer.com (Springer)
  • www.springerlink.com/content/1869-408x/ (Cardiovascular Engineering and Technology)

Read more