VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation

TL;DR

VS-DDPM is an efficient 3D diffusion model that accelerates medical image synthesis tasks while maintaining high quality, demonstrated on multiple challenging datasets.

Contribution

The paper introduces VS-DDPM, a novel low-cost diffusion framework that significantly speeds up inference in 3D medical image translation without sacrificing quality.

Findings

Achieved SOTA Dice scores of 0.80, 0.83, 0.88 in MRI missing tumor synthesis.

Attained RMSE of 0.053 and SSIM of 0.918 in MRI tumor removal.

Demonstrated competitive performance in MRI-to-sCT and CBCT-to-sCT tasks.

Abstract

Diffusion models produce high-quality synthetic data but suffer from slow inference. We propose 3D Variable-Step Denoising Diffusion Probabilistic Model (VS-DDPM) a framework engineered to maintain generative quality while accelerating inference by several factors. We tested our approach on four tasks (missing MRI, tumor removal, MRI-to-sCT, and CBCT-to-sCT) within the BraTS2025 and SynthRAD2025 challenges. Designed for high efficiency under hardware and time constrains imposed by both challenges. VS-DDPM achieved state-of-the-art (SOTA) performance in missing MRI synthesis, yielding Dice scores of 0.80, 0.83, and 0.88 for the enhancing tumor, tumor core, and whole tumor regions, respectively, alongside a structural similarity index (SSIM) of 0.95. For MRI tumor removal, the model attained a root mean squared error (RMSE) of 0.053, a peak signal-to-noise ratio (PSNR) of 26.77, and an SSIM of 0.918. While the framework demonstrated competitive performance in MRI-to-sCT and CBCT-to-sCT tasks, it did not reach SOTA benchmarks, potentially due to sensitivities in data pre and post-processing pipelines or specific loss function configurations. These results demonstrate that VS-DDPM provides a robust and tunable solution for high-fidelity 3D medical image synthesis. The code is available in https://github.com/andre-fs-ferreira/SynthRAD_by_Faking_it.