MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging
Organizations: Jagiellonian University, Poland · Warsaw University of Technology, Poland · Sano Centre for Computional Medicine, Poland · IDEAS Research Institute, Poland ·
Abstract
Multi-modal three-dimensional (3D) medical imaging data, derived from ultrasound, magnetic resonance imaging (MRI), and computed tomography (CT), provide a widely adopted approach for non-invasive anatomical visualization. However, accurate modeling depends on surface reconstruction and frame-to-frame interpolation, where traditional methods often struggle with image noise and incomplete information between sparse frames. To address these challenges, we present \our{}, a novel framework based on Gaussian Splatting (GS) designed for high-fidelity 3D anatomical reconstruction. Uniquely, \our{} employs a multi-task architecture that simultaneously performs frame interpolation and segmentation using a unified geometric representation. By coupling these tasks, the model leverages dense signals from image synthesis to regularize the geometry, enabling high-quality surface extraction even from a limited number of input frames. Specifically, medical data are modeled as Folded-Gaussians with dual color attributes, supported by an In-Between Frame Regularization (IBFR) mechanism. Experimental results demonstrate that \our{} achieves higher metric scores than implicit neural representations and improves interpolation quality. Repository: https://github.com/gmum/MedGS
Figures & tables
| Method | CD | HD95 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 65 | 66 | 67 | 68 | 69 | 70 | 65 | 66 | 67 | 68 | 69 | 70 | |
| Baseline | 0.248 | 0.206 | 0.216 | 0.214 | 0.219 | 0.236 | 0.425 | 0.353 | 0.374 | 0.369 | 0.378 | 0.411 |
| FUNSR | 0.239 | 0.216 | 0.227 | 0.217 | 0.209 | 0.249 | 0.421 | 0.384 | 0.393 | 0.374 | 0.374 | 0.426 |
| Poisson | 0.235 | 0.204 | 0.186 | 0.198 | 0.198 | 0.225 | 0.397 | 0.361 | 0.334 | 0.345 | 0.355 | 0.400 |
| MedGS s | 0.194 | 0.207 | 0.179 | 0.177 | 0.187 | 0.212 | 0.365 | 0.350 | 0.325 | 0.332 | 0.350 | 0.386 |
| MedGS | 0.194 | 0.184 | 0.172 | 0.177 | 0.186 | 0.208 | 0.365 | 0.333 | 0.318 | 0.329 | 0.350 | 0.384 |
3D Reconstruction
3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.
See all 1,013 papers