MRNet通过融合SAM与U-Net，提升医学影像转换的解剖准确性。
MRNet: Multifaceted Resilient Networks for Medical Image-to-Image Translation
- 用SAM提取频域特征，结合U-Net多尺度信息进行融合
- 双掩码动态注意力使解剖结构与组织细节保留更佳
- 适合需要高保真影像转换的临床研究与数据增强
我们提出一种新型多面韧性网络（MRNet），用于医学图像到图像的转换，在MRI转CT和MRI转MRI任务中优于现有先进方法。MRNet利用分割一切模型（SAM）提取频域特征，构建强大的医学图像变换方法。该架构通过强大的SAM图像编码器从多样化数据集中提取全面的多尺度特征，并执行分辨率感知的特征融合，将U-Net编码器输出与SAM生成特征一致集成。这种融合优化了传统U-Net跳跃连接，同时利用基于Transformer的上下文分析。翻译过程还引入创新的双掩码配置，包含动态注意力模式和专门设计的损失函数，以解决区域映射不匹配问题，有效保留整体解剖结构与组织细节。大量验证表明，MRNet在保持解剖保真度和最小化转换伪影方面显著优于现有架构。
原文摘要 · Abstract (English)
We propose a Multifaceted Resilient Network(MRNet), a novel architecture developed for medical image-to-image translation that outperforms state-of-the-art methods in MRI-to-CT and MRI-to-MRI conversion. MRNet leverages the Segment Anything Model (SAM) to exploit frequency-based features to build a powerful method for advanced medical image transformation. The architecture extracts comprehensive multiscale features from diverse datasets using a powerful SAM image encoder and performs resolution-aware feature fusion that consistently integrates U-Net encoder outputs with SAM-derived features. This fusion optimizes the traditional U-Net skip connection while leveraging transformer-based contextual analysis. The translation is complemented by an innovative dual-mask configuration incorporating dynamic attention patterns and a specialized loss function designed to address regional mapping mismatches, preserving both the gross anatomy and tissue details. Extensive validation studies have shown that MRNet outperforms state-of-the-art architectures, particularly in maintaining anatomical fidelity and minimizing translation artifacts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。