Saved in:
Bibliographic Details
Main Author: Yuan, Feng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.07687
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917297698897920
author Yuan, Feng
author_facet Yuan, Feng
contents Multi-modal medical image synthesis is pivotal for alleviating clinical data scarcity, yet existing methods fail to reconcile global anatomical consistency with high-fidelity local detail. We propose FermatSyn, which addresses three persistent limitations: (1)~a SAM2-based Prior Encoder that injects domain-aware anatomical knowledge via Lo-RA$^{+}$ efficient fine-tuning of a frozen SAM2 Vision Transformer; (2)~a Hierarchical Residual Downsampling Module (HRDM) coupled with a Cross-scale Integration Network (CIN) that preserves high-frequency lesion details and adaptively fuses global--local representations; and (3)~a continuity constrained Fermat Spiral Scanning strategy within a Bidirectional Fermat Scan Mamba (BFS-Mamba), constructing an approximately isotropic receptive field that substantially reduces the directional bias of raster or spiral serialization. Experiments on SynthRAD2023, BraTS2019, BraTS-MEN, and BraTS-MET show FermatSyn surpasses state-of-the-art methods in PSNR, SSIM, FID, and 3D structural consistency. Downstream segmentation on synthesized images yields no significant difference from real-image training ($p{>}0.05$), confirming clinical utility. Code will be released upon publication. \keywords{Medical image synthesis \and SAM2 \and Mamba \and Fermat spiral scanning \and Anatomical prior \and Cross-modal}
format Preprint
id arxiv_https___arxiv_org_abs_2505_07687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FermatSyn: SAM2-Enhanced Bidirectional Mamba with Isotropic Spiral Scanning for Multi-Modal Medical Image Synthesis
Yuan, Feng
Image and Video Processing
Computer Vision and Pattern Recognition
Multi-modal medical image synthesis is pivotal for alleviating clinical data scarcity, yet existing methods fail to reconcile global anatomical consistency with high-fidelity local detail. We propose FermatSyn, which addresses three persistent limitations: (1)~a SAM2-based Prior Encoder that injects domain-aware anatomical knowledge via Lo-RA$^{+}$ efficient fine-tuning of a frozen SAM2 Vision Transformer; (2)~a Hierarchical Residual Downsampling Module (HRDM) coupled with a Cross-scale Integration Network (CIN) that preserves high-frequency lesion details and adaptively fuses global--local representations; and (3)~a continuity constrained Fermat Spiral Scanning strategy within a Bidirectional Fermat Scan Mamba (BFS-Mamba), constructing an approximately isotropic receptive field that substantially reduces the directional bias of raster or spiral serialization. Experiments on SynthRAD2023, BraTS2019, BraTS-MEN, and BraTS-MET show FermatSyn surpasses state-of-the-art methods in PSNR, SSIM, FID, and 3D structural consistency. Downstream segmentation on synthesized images yields no significant difference from real-image training ($p{>}0.05$), confirming clinical utility. Code will be released upon publication. \keywords{Medical image synthesis \and SAM2 \and Mamba \and Fermat spiral scanning \and Anatomical prior \and Cross-modal}
title FermatSyn: SAM2-Enhanced Bidirectional Mamba with Isotropic Spiral Scanning for Multi-Modal Medical Image Synthesis
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.07687