# FractMorph: A Fractional Fourier-Based Multi-Domain Transformer for Deformable Image Registration

Source: [FractMorph: A Fractional Fourier-Based Multi-Domain Transformer for Deformable Image Registration](<https://www.sota2.com/research/paper/68fa7acf1e209131cea853d8>)

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

Data updated: 2025-10-27T07:00:40.261Z

Authors: Shayan Kebriti, Shahabedin Nabavi, Ali Gooya

Published: 2025-08-17T17:42:10.000Z

## Abstract

Deformable image registration (DIR) is a crucial and challenging technique for aligning anatomical structures in medical images and is widely applied in diverse clinical applications. However, existing approaches often struggle to capture fine-grained local deformations and large-scale global deformations simultaneously within a unified framework. We present FractMorph, a novel 3D dual-parallel transformer-based architecture that enhances cross-image feature matching through multi-domain fractional Fourier transform (FrFT) branches. Each Fractional Cross-Attention (FCA) block applies parallel FrFTs at fractional angles of $0^\\circ$, $45^\\circ$, $90^\\circ$, along with a log-magnitude branch, to effectively extract local, semi-global, and global features at the same time. These features are fused via cross-attention between the fixed and moving image streams. A lightweight U-Net style network then predicts a dense deformation field from the transformer-enriched features. On the intra-patient ACDC cardiac MRI dataset, FractMorph achieves state-of-the-art performance with an overall Dice Similarity Coefficient (DSC) of $86.45\\%$, an average per-structure DSC of $75.15\\%$, and a 95th-percentile Hausdorff distance (HD95) of $1.54~\\mathrm{mm}$ on our data split. FractMorph-Light, a lightweight variant of our model with only 29.6M parameters, preserves high accuracy while halving model complexity. Furthermore, we demonstrate the generality of our approach with solid performance on a cerebral atlas-to-patient dataset. Our results demonstrate that multi-domain spectral-spatial attention in transformers can robustly and efficiently model complex non-rigid deformations in medical images using a single end-to-end network, without the need for scenario-specific tuning or hierarchical multi-scale networks. The source code is available at https://github.com/shayankebriti/FractMorph.

## 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.

- [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: 75.15.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.12445>)

[PDF](<https://arxiv.org/pdf/2508.12445.pdf>)
