Home | Publications | WEB+25a

Train Forwards, Optimize Backwards: Neural Surrogates for Personalized Medical Simulations

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 simulations to individual patients remains a major computational bottleneck, as traditional optimization requires repeated runs of costly numerical solvers. We present a differentiable system that replaces the forward simulation with a neural surrogate, providing a fast and accurate approximation of the underlying biophysical model. The surrogate’s differentiability enables efficient gradient-based inversion of patient-specific parameters, even when the original solver is non-differentiable. Applied to a 3D finite-difference model of brain tumor growth, our method achieves clinically relevant accuracy while reducing optimization time from days to seconds. This demonstrates how differentiable surrogates can serve as core components of broader differentiable systems for scientific machine learning.

inproceedings WEB+25a

DiffSys @EurIPS 2025

Workshop on Differentiable Systems and Scientific Machine Learning at the European Conference on Information Processing Systems. Copenhagen, Denmark, Dec 03-05, 2025. To be published. Preprint available.