FermatSyn: 基于改进双向Mamba的多模态医学图像合成方法
FermatSyn: SAM2-Enhanced Bidirectional Mamba with Isotropic Spiral Scanning for Multi-Modal Medical Image Synthesis
AI总结：
FermatSyn通过改进的双向Mamba结合Fermat螺旋扫描策略，解决多模态医学图像合成中全局一致性与局部细节的平衡问题，提升合成图像质量与临床应用价值。
摘要：
多模态医学图像合成对于缓解临床数据稀缺至关重要，但现有方法未能在保持全局解剖一致性与高保真局部细节之间取得平衡。我们提出了FermatSyn，解决了三个持续存在的限制：(1) 一种基于SAM2的先验编码器，通过Lo-RA$^{+}$高效微调冻结的SAM2视觉变换器，注入领域感知的解剖知识；(2) 一种带有跨尺度集成网络(CIN)的分层残差下采样模块(HRDM)，保留高频病变细节并自适应融合全局-局部表示；(3) 一种在双向Fermat扫描Mamba(BFS-Mamba)中受连续性约束的Fermat螺旋扫描策略，构建近似各向同性的感受野，显著减少栅格或螺旋序列化的方向偏差。在SynthRAD2023、BraTS2019、BraTS-MEN和BraTS-MET上的实验表明，FermatSyn在PSNR、SSIM、FID和3D结构一致性方面均优于现有方法。在合成图像上的下游分割结果与真实图像训练无显著差异（p>0.05），证实了临床实用性。代码将在发表后发布。\keywords{医学图像合成 \and SAM2 \and Mamba \and Fermat螺旋扫描 \and 解剖先验 \and 跨模态}
英文摘要：
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) SAM2-based Prior Encoder that injects domain-aware anatomical knowledge via LoRA$^{+}$ efficient fine-tuning of a frozen SAM2 Vision Transformer; (2) 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) 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 is available at https://github.com/gatina-yone/FermatSyn.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
