提升多对比度MRI超分辨率，让图像结构更对齐、细节更清晰。
SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution
- 通过动态空间扭曲实现不同对比度图像的空间对齐
- 在公开与私有数据集上达到当前最佳效果，参数更少
- 适合医学影像重建、需高精度结构对齐的研究者
多对比度磁共振成像超分辨率（MC-MRI SR）旨在利用高分辨率参考图像增强低分辨率对比度图像，缩短扫描时间并提升成像效率，同时保留解剖细节。主要挑战在于保持空间-语义一致性，确保目标与参考图像间存在结构差异和运动时，解剖结构仍能良好对齐且连贯。传统方法未能充分建模空间-语义一致性，且未有效利用频域信息，导致细粒度对齐差、高频细节恢复不足。本文提出空间-语义一致模型（SSCM），包含动态空间扭曲模块用于跨对比度空间对齐，语义感知令牌聚合块以维持长程语义一致性，以及空间-频率融合块以恢复精细结构。在公开与私有数据集上的实验表明，SSCM以更少参数实现领先性能，确保重建结果在空间与语义上高度一致。
原文摘要 · Abstract (English)
Multi-contrast Magnetic Resonance Imaging super-resolution (MC-MRI SR) aims to enhance low-resolution (LR) contrasts leveraging high-resolution (HR) references, shortening acquisition time and improving imaging efficiency while preserving anatomical details. The main challenge lies in maintaining spatial-semantic consistency, ensuring anatomical structures remain well-aligned and coherent despite structural discrepancies and motion between the target and reference images. Conventional methods insufficiently model spatial-semantic consistency and underuse frequency-domain information, which leads to poor fine-grained alignment and inadequate recovery of high-frequency details. In this paper, we propose the Spatial-Semantic Consistent Model (SSCM), which integrates a Dynamic Spatial Warping Module for inter-contrast spatial alignment, a Semantic-Aware Token Aggregation Block for long-range semantic consistency, and a Spatial-Frequency Fusion Block for fine structure restoration. Experiments on public and private datasets show that SSCM achieves state-of-the-art performance with fewer parameters while ensuring spatially and semantically consistent reconstructions.
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。