arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.06166cs.CV
收藏

B-FIRE：无分组扩散隐式神经表示用于超加速运动分辨MRI

B-FIRE: Binning-Free Diffusion Implicit Neural Representation for Hyper-Accelerated Motion-Resolved MRI

Radiation Oncology, University of California, San Francisco, California（加州大学旧金山分校放射肿瘤学系）；Radiology and Biomedical Imaging, University of California, San Francisco, California（加州大学旧金山分校放射学与生物医学成像系）；Siemens Medical Solutions USA, Inc., Cleveland, Ohio（西门子医疗解决方案美国公司，克利夫兰，俄亥俄）；Radiology at Children’s Hospital Los Angeles, Keck School of Medicine, University of Southern California, Los Angeles, California（洛杉矶儿童医院放射学，美国南加州大学凯克医学院，洛杉矶，加利福尼亚）
Di Xu, Hengjie Liu, Yang Yang, Mary Feng, Jin Ning, Xin Miao, Jessica E. Scholey, Alexandra E. Hotca-cho, William C. Chen, Michael Ohliger, Martina Descovich, H… 展开作者

Di Xu, Hengjie Liu, Yang Yang, Mary Feng, Jin Ning, Xin Miao, Jessica E. Scholey, Alexandra E. Hotca-cho, William C. Chen, Michael Ohliger, Martina Descovich, Huiming Dong, Wensha Yang, Ke Sheng

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

B-FIRE通过扩散隐式神经表示框架实现超加速MRI重建，解决运动分辨信息模糊问题，提升3D腹部解剖的即时重建精度。

摘要：

加速动态体素磁共振成像（4DMRI）对于依赖运动分辨率的应用至关重要。现有4DMRI在平均呼吸相位产生可接受的伪影，导致动态信息模糊和误表征。恢复此类信息需要新的范式来重建极低采样非Cartesian k空间数据。我们提出B-FIRE，一种无分组扩散隐式神经表示框架，用于超加速MRI重建，能够反映即时3D腹部解剖。B-FIRE采用CNN-INR编码器-解码器主干，通过扩散优化，使用综合损失强制图像域保真度和频率感知约束。运动分组图像对用于训练参考，而推断则在无分组欠采样数据上进行。实验在T1加权StarVIBE肝脏MRI队列上进行，加速比从每帧8个扇区（RV8）到RV1。B-FIRE与直接NuFFT、GRASP-CS和展开CNN方法进行比较。重建保真度、运动轨迹一致性和推断延迟被评估。

英文摘要：

Accelerated dynamic volumetric magnetic resonance imaging (4DMRI) is essential for applications relying on motion resolution. Existing 4DMRI produces acceptable artifacts of averaged breathing phases, which can blur and misrepresent instantaneous dynamic information. Recovery of such information requires a new paradigm to reconstruct extremely undersampled non-Cartesian k-space data. We propose B-FIRE, a binning-free diffusion implicit neural representation framework for hyper-accelerated MR reconstruction capable of reflecting instantaneous 3D abdominal anatomy. B-FIRE employs a CNN-INR encoder-decoder backbone optimized using diffusion with a comprehensive loss that enforces image-domain fidelity and frequency-aware constraints. Motion binned image pairs were used as training references, while inference was performed on binning-free undersampled data. Experiments were conducted on a T1-weighted StarVIBE liver MRI cohort, with accelerations ranging from 8 spokes per frame (RV8) to RV1. B-FIRE was compared against direct NuFFT, GRASP-CS, and an unrolled CNN method. Reconstruction fidelity, motion trajectory consistency, and inference latency were evaluated.

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。

↑