A novel real-time efficacy assessment method for tumor treating fields

Abstract

Tumor treating fields (TTFields) is a promising non-invasive cancer treatment that uses alternating electric fields to disrupt tumor cell division. Despite its potential, there is a significant lack of precise and reliable methods for evaluating the efficacy of TTFields in clinical settings. The aim of this study is to develop and validate a new method for real-time assessment of the efficacy of TTFields. We proposed a novel neural network based on a collaborative fusion strategy of dual-branch (CFS-DB) to reconstruct the conductivity of tumor region for real-time assessment of the efficacy of TTFields. The proposed CFS-DB includes two independent branches: a conductivity branch and a structure branch. The conductivity branch employs FC-UNet to learn the mapping from measured boundary voltages to conductivity. The structural branch uses the results reconstructed by Gaussian-Newton method as the input for image-to-image training. Finally, the features from both branches are fused for coordinated end-to-end training. The simulation and experimental results show that the proposed CFS-DB has superior performance compared to five state-of-the-art deep learning networks. The CFS-DB method offers a novel and precise approach for evaluating the efficacy of TTFields, providing a new paradigm for clinical assessment.