Brains Don't Wait for Solvers: Fast Tumor Inversion Through Differentiable Simulation

MCML Authors

Jonas Weidner

→ Group Benedikt Wiestler
 AI for Image-Guided Diagnosis and Therapy

Daniel Rückert

Prof. Dr.

Director

Artificial Intelligence in Healthcare and Medicine

Benedikt Wiestler

Prof. Dr.

Principal Investigator

AI for Image-Guided Diagnosis and Therapy

Abstract

Personalizing biophysical brain tumor models to individual patients is computationally expensive due to the need for numerous iterative evaluations of slow numerical solvers to identify optimal patient-specific parameters. We address this by introducing a differentiable neural surrogate that replaces the traditional forward model. Unlike the original solver, this surrogate is fully differentiable, allowing us to solve the inverse problem using highly efficient gradient-based optimization. This approach ensures that the solution learns the biophysical constraints of tumor growth while accelerating the process by orders of magnitude. In a 3D brain tumor growth setting, our framework achieves accuracy competitive with classical optimization while reducing runtime from days to seconds. Crucially, we demonstrate that our method, though trained on synthetic data, generalizes effectively to real patient scans. These findings establish differentiable surrogates as a powerful tool for accelerating scientific machine learning in medical imaging and beyond.

misc WZE+25

---

Preprint

Nov. 2025

---

Authors

J. Weidner • I. Ezhov • L. Zimmer • M. Balcerak • B. Menze • D. Rückert • B. Wiestler

---

Links

URL

---

Research Area

 C1 | Medicine