fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpainting
Alicia Durrer, Florentin Bieder, Paul Friedrich, Bjoern Menze, Philippe C. Cattin, Florian Kofler

TL;DR
fastWDM3D introduces a rapid and precise 3D healthy tissue inpainting method that significantly outperforms existing models in speed while maintaining high quality, enabling practical applications in medical imaging.
Contribution
This work adapts a 2D diffusion approach to 3D inpainting using a wavelet diffusion model without GANs, achieving high speed and quality in tissue inpainting.
Findings
Achieved SSIM of 0.8571, MSE of 0.0079, PSNR of 22.26.
Completed inpainting in 1.81 seconds per image with only two steps.
Up to 800x faster than previous DDPM-based methods.
Abstract
Healthy tissue inpainting has significant applications, including the generation of pseudo-healthy baselines for tumor growth models and the facilitation of image registration. In previous editions of the BraTS Local Synthesis of Healthy Brain Tissue via Inpainting Challenge, denoising diffusion probabilistic models (DDPMs) demonstrated qualitatively convincing results but suffered from low sampling speed. To mitigate this limitation, we adapted a 2D image generation approach, combining DDPMs with generative adversarial networks (GANs) and employing a variance-preserving noise schedule, for the task of 3D inpainting. Our experiments showed that the variance-preserving noise schedule and the selected reconstruction losses can be effectively utilized for high-quality 3D inpainting in a few time steps without requiring adversarial training. We applied our findings to a different…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topics3D Shape Modeling and Analysis · Advanced Numerical Analysis Techniques
