# FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images

Source: [FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images](<https://www.sota2.com/research/paper/68fa701c1e209131cea4911c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T13:23:01.375Z

Authors: Yi Qin, Xiaomeng Li

Published: 2023-07-22T10:09:22.000Z

## Abstract

Unsupervised deformable image registration is one of the challenging tasks in medical imaging. Obtaining a high-quality deformation field while preserving deformation topology remains demanding amid a series of deep-learning-based solutions. Meanwhile, the diffusion model's latent feature space shows potential in modeling the deformation semantics. To fully exploit the diffusion model's ability to guide the registration task, we present two modules: Feature-wise Diffusion-Guided Module (FDG) and Score-wise Diffusion-Guided Module (SDG). Specifically, FDG uses the diffusion model's multi-scale semantic features to guide the generation of the deformation field. SDG uses the diffusion score to guide the optimization process for preserving deformation topology with barely any additional computation. Experiment results on the 3D medical cardiac image registration task validate our model's ability to provide refined deformation fields with preserved topology effectively. Code is available at: https://github.com/xmed-lab/FSDiffReg.git.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Registration on ACDC (test)](<https://www.sota2.com/research/sota/image-registration-on-acdc-test.md>): Image Registration; ACDC (test); Dice LV: 0.809.

- [Unsupervised Cardiac MR Registration on ACDC ES→ED](<https://www.sota2.com/research/sota/unsupervised-cardiac-mr-registration-on-acdc-es-ed.md>): Unsupervised Cardiac MR Registration; ACDC ES→ED; Mean Dice Score: 81.06.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.12035>)

[PDF](<https://arxiv.org/pdf/2307.12035.pdf>)

[Implementation](<https://github.com/xmed-lab/FSDiffReg.git>)
