Deep Biomechanically-Guided Interpolation for Keypoint-Based Brain Shift Registration
By: Tiago Assis , Ines P. Machado , Benjamin Zwick and more
Potential Business Impact:
Helps surgeons see inside the brain better.
Accurate compensation of brain shift is critical for maintaining the reliability of neuronavigation during neurosurgery. While keypoint-based registration methods offer robustness to large deformations and topological changes, they typically rely on simple geometric interpolators that ignore tissue biomechanics to create dense displacement fields. In this work, we propose a novel deep learning framework that estimates dense, physically plausible brain deformations from sparse matched keypoints. We first generate a large dataset of synthetic brain deformations using biomechanical simulations. Then, a residual 3D U-Net is trained to refine standard interpolation estimates into biomechanically guided deformations. Experiments on a large set of simulated displacement fields demonstrate that our method significantly outperforms classical interpolators, reducing by half the mean square error while introducing negligible computational overhead at inference time. Code available at: \href{https://github.com/tiago-assis/Deep-Biomechanical-Interpolator}{https://github.com/tiago-assis/Deep-Biomechanical-Interpolator}.
Similar Papers
Biomechanical Constraints Assimilation in Deep-Learning Image Registration: Application to sliding and locally rigid deformations
CV and Pattern Recognition
Makes medical scans match body parts better.
Rule-based Key-Point Extraction for MR-Guided Biomechanical Digital Twins of the Spine
Image and Video Processing
Creates body models from scans for better health plans.
Topology Aware Neural Interpolation of Scalar Fields
Machine Learning (CS)
Makes computer models guess missing data accurately.