arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.08226cs.CVcs.LG
收藏

基于深度学习的高效脑肿瘤生长模型正向求解器

Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models

Technical University of Munich(慕尼黑技术大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);University of Zurich(苏黎世大学)

Zeineb Haouari, Jonas Weidner, Yeray Martin-Ruisanchez, Ivan Ezhov, Aswathi Varma, Daniel Rueckert, Bjoern Menze, Benedikt Wiestler

AI总结:

针对胶质母细胞瘤模型校准计算成本高的问题,本文比较多种神经网络正向求解器,发现nnU-Net在精度和Dice分数上最优,显著提升求解性能。

摘要:

胶质母细胞瘤是一种高度侵袭性的脑肿瘤,因其预后差和发病率高而带来重大挑战。基于偏微分方程的模型通过模拟患者特异性肿瘤行为以改进放射治疗计划,有望提升治疗效果。然而,由于蒙特卡洛采样和进化算法等优化方法计算需求高,模型校准仍是瓶颈。为解决此问题,我们近期引入了一种方法,利用神经正向求解器结合基于梯度的优化,显著缩短校准时间。该方法需要高度精确且完全可微的正向模型。我们研究了多种架构,包括(i)增强版TumorSurrogate,(ii)改进的nnU-Net,以及(iii)3D视觉Transformer(ViT)。其中,nnU-Net取得了最佳整体结果,在肿瘤轮廓匹配和肿瘤细胞浓度的体素级预测方面均表现优异。与真实数值模拟相比,它在肿瘤细胞浓度上获得了最低的均方误差(MSE),并在所有肿瘤细胞浓度阈值下取得了最高的Dice分数。我们的研究展示了正向求解器性能的显著提升,并指出了重要的未来研究方向。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑