Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models
This work addresses the challenge of patient-specific radiotherapy planning for glioblastoma by reducing calibration time, though it is incremental as it builds on existing neural forward solver approaches.
The paper tackled the computational bottleneck in calibrating brain tumor growth models by developing efficient deep learning-based forward solvers, with the nnU-Net achieving the lowest MSE in tumor cell concentration and highest Dice score compared to ground truth simulations.
Glioblastoma, a highly aggressive brain tumor, poses major challenges due to its poor prognosis and high morbidity rates. Partial differential equation-based models offer promising potential to enhance therapeutic outcomes by simulating patient-specific tumor behavior for improved radiotherapy planning. However, model calibration remains a bottleneck due to the high computational demands of optimization methods like Monte Carlo sampling and evolutionary algorithms. To address this, we recently introduced an approach leveraging a neural forward solver with gradient-based optimization to significantly reduce calibration time. This approach requires a highly accurate and fully differentiable forward model. We investigate multiple architectures, including (i) an enhanced TumorSurrogate, (ii) a modified nnU-Net, and (iii) a 3D Vision Transformer (ViT). The nnU-Net achieved the best overall results, excelling in both tumor outline matching and voxel-level prediction of tumor cell concentration. It yielded the lowest MSE in tumor cell concentration compared to ground truth numerical simulation and the highest Dice score across all tumor cell concentration thresholds. Our study demonstrates significant enhancement in forward solver performance and outlines important future research directions.