Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks

Abstract: We address the challenge of parameter-efficient fine-tuning (PEFT)for three-dimensional (3D) U-Net-based denoising diffusion prob abilistic models (DDPMs) in magnetic resonance imaging (MRI) im age generation. Despite its practical significance, research on parameter efficient representations of 3D convolution operations remains limited. To bridge this gap, we propose Tensor Volumetric Operator (TenVOO), a novel PEFT method specifically designed for fine-tuning DDPMs with 3D convolutional backbones. Leveraging tensor network modeling, Ten VOO represents 3D convolution kernels with lower-dimensional tensors, effectively capturing complex spatial dependencies during fine-tuning with few parameters. We evaluate TenVOO on three downstream brain MRI datasets–ADNI, PPMI, and BraTS2021–by fine-tuning a DDPM pretrained on 59,830 T1-weighted brain MRI scans from the UK Biobank. Our results demonstrate that TenVOO achieves state-of-the-art perfor mance in multi-scale structural similarity index measure (MS-SSIM), outperforming existing approaches in capturing spatial dependencies while requiring only 0.3% of the trainable parameters of the original model.

Recommended citation: Binghua Li, ZiQing Chang, Tong Liang, Chao Li, Toshihisa Tanaka, Shigeki Aoki, Qibin Zhao and Zhe Sun .Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks, MICCAI 2025.
Download Paper | Download Code