发表机构
TUM, Munich, Germany; Munich Center for Machine Learning (MCML), Munich, Germany; University of Zurich, Switzerland; Chair for AI in Healthcare and Medicine, TUM, Munich, Germany; Institute of Continuum Mechanics and Biomechanics, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany（慕尼黑工业大学; 慕尼黑机器学习中心; 苏黎世大学; 慕尼黑工业大学医疗保健与医学人工智能讲席; 埃尔朗根-纽伦堡大学连续力学与生物力学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种可微分的势-弹簧模型求解脑肿瘤占位效应，以单一全局参数替代逐患者反演，在134名BraTS患者上实现最大局部重叠改善，计算时间缩短至百分之一，且保持物理合理性。
AI 中文摘要
生长中的脑肿瘤通过占位效应机械性地使周围健康脑组织发生变形。这种组织的压缩和位移影响患者的预后和治疗规划，因此肿瘤生长的生物物理模型必须考虑这种变形。已有的占位效应模型是偏微分方程（PDE）求解器，将生长与弹性耦合，并针对每位患者校准参数，这带来了巨大的实现、运行和校准成本。我们探讨一个完全可微分的基于能量的模型能够恢复多少这种变形，并引入一个势-弹簧模型：一个覆盖大脑的规则网格在肿瘤浓度势的驱动下向外移动，并由具有组织特异性刚度的弹性弹簧晶格所约束。该模型与连续介质弹性力学的肿瘤梯度驱动力一致，但仅使用一个全局参数，无需逐患者反演，通过梯度下降进行端到端最小化。我们将其与已有求解器进行基准比较，方法是将每个位移场应用于健康图谱，并测量与患者自身分割在134名BraTS患者上的组织重叠。我们的模型在高达100倍更短的计算时间内实现了最大的总体局部重叠改善，建立了一个用于肿瘤占位效应的轻量级、可微分求解器。由于我们的模型遵循力学定律并反映肿瘤诱导的组织载荷，它保持物理合理性，这是临床使用的先决条件。
英文摘要
A growing brain tumor mechanically deforms the surrounding healthy brain through mass effect. This compression and displacement of tissue affects both patient prognosis and treatment planning, so biophysical models of tumor growth must account for this deformation. Established mass-effect models are partial differential equation (PDE) solvers that couple growth to elasticity and calibrate parameters per patient, at substantial implementation, runtime, and calibration cost. We ask how much of this deformation a fully differentiable energy-based model can recover, and introduce a potential-spring model: a regular grid over the brain is driven outward by a tumor-concentration potential and held by an elastic spring lattice with tissue-specific stiffness. It shares the tumor-gradient driving force of continuum elasticity but uses a single global parameter and no per-patient inversion, minimized end-to-end by gradient descent. We benchmark it against established solvers by applying each displacement field to a healthy atlas and measuring tissue overlap with the patient's own segmentation on 134 BraTS patients. Our model yields the largest overall local overlap improvement at up to 100$\times$ shorter computation time, establishing a lightweight, differentiable solver for tumor mass effect. Because our model obeys mechanical laws and reflects the tumor-induced tissue loading, it remains physically plausible, a prerequisite for clinical use.
Comments9 pages, 3 figures, 2 tables, MICCAI CMMCA workshop
