当前位置: X-MOL 学术Med. Image Anal. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-contrast image super-resolution with deformable attention and neighborhood-based feature aggregation (DANCE): Applications in anatomic and metabolic MRI
Medical Image Analysis ( IF 10.7 ) Pub Date : 2024-09-30 , DOI: 10.1016/j.media.2024.103359
Wenxuan Chen, Sirui Wu, Shuai Wang, Zhongsen Li, Jia Yang, Huifeng Yao, Qiyuan Tian, Xiaolei Song

Multi-contrast magnetic resonance imaging (MRI) reflects information about human tissues from different perspectives and has wide clinical applications. By utilizing the auxiliary information from reference images (Refs) in the easy-to-obtain modality, multi-contrast MRI super-resolution (SR) methods can synthesize high-resolution (HR) images from their low-resolution (LR) counterparts in the hard-to-obtain modality. In this study, we systematically discussed the potential impacts caused by cross-modal misalignments between LRs and Refs and, based on this discussion, proposed a novel deep-learning-based method with Deformable Attention and Neighborhood-based feature aggregation to be Computationally Efficient (DANCE) and insensitive to misalignments. Our method has been evaluated in two public MRI datasets, i.e., IXI and FastMRI, and an in-house MR metabolic imaging dataset with amide proton transfer weighted (APTW) images. Experimental results reveal that our method consistently outperforms baselines in various scenarios, with significant superiority observed in the misaligned group of IXI dataset and the prospective study of the clinical dataset. The robustness study proves that our method is insensitive to misalignments, maintaining an average PSNR of 30.67 dB when faced with a maximum range of ±9°and ±9 pixels of rotation and translation on Refs. Given our method’s desirable comprehensive performance, good robustness, and moderate computational complexity, it possesses substantial potential for clinical applications.

中文翻译:


具有可变形注意力和基于邻域的特征聚合 (DANCE) 的多对比度图像超分辨率:在解剖和代谢 MRI 中的应用



多对比磁共振成像 (MRI) 从不同角度反映有关人体组织的信息,具有广泛的临床应用。通过以易于获取的方式利用参考图像 (Refs) 的辅助信息,多对比 MRI 超分辨率 (SR) 方法可以从难以获得的模式中的低分辨率 (LR) 对应物合成高分辨率 (HR) 图像。在这项研究中,我们系统地讨论了 LR 和 Ref 之间的跨模态错位引起的潜在影响,并基于此讨论,提出了一种基于深度学习的新型方法,该方法具有可变形注意力和基于邻域的特征聚合,具有计算效率 (DANCE) 和对错位不敏感。我们的方法已在两个公共 MRI 数据集中进行了评估,即 IXI 和 FastMRI,以及一个带有酰胺质子转移加权 (APTW) 图像的内部 MR 代谢成像数据集。实验结果表明,我们的方法在各种情况下始终优于基线,在 IXI 数据集的错位组和临床数据集的前瞻性研究中观察到显着的优势。鲁棒性研究证明,我们的方法对错位不敏感,当面对 Refs 上 ±9° 和 ±9 像素的最大旋转和平移范围时,平均 PSNR 保持在 30.67 dB。鉴于我们的方法理想的综合性能、良好的鲁棒性和适度的计算复杂度,它在临床应用方面具有巨大的潜力。
更新日期:2024-09-30
down
wechat
bug