Implantable Tumor Treating Fields (ITF) for glioblastoma is an emerging research direction and has increasingly garnered significant attention. The intricate physical environment of brain tissue and inter-patient heterogeneity present a substantial challenge in defining optimal treating parameters, severely hindering the clinical feasibility of this technology. Therefore, achieving automated personalized parameter configuration is of great importance. This study trained a deep-learning model for automatic brain tumor segmentation with BraTS dataset. The segmentation results were subsequently imported into 3D Slicer software for three-dimensional (3D) reconstruction, and the least squares method was used to fit the irregular tumor morphology parameters. The reconstructed 3D model was then imported into the COMSOL platform for finite element analysis. Through the COMSOL Livelink with Matlab interface, a genetic algorithm was utilized to optimize the objective function based on feedback from finite element simulation results, thereby generating personalized treatment parameter recommendations and achieving conformal therapy. This study integrated medical image segmentation and 3D reconstruction technologies, proposing a comprehensive workflow for personalized brain tumor 3D model reconstruction and parameter planning based on brain MRI images. It proposed the genetic optimization algorithm coupled with finite element simulation, aiming to provide individualized conformal treatment recommendations. This methodology achieved fully automated planning from MRI images to personalized parameter configuration, offering a new strategy for the precise treatment of brain tumors using ITF.