Fujita Naoto, Yokosawa Suguru, Shirai Toru, Terada Yasuhiko
Institute of Pure and Applied Sciences, University of Tsukuba, Tsukuba, Japan.
FUJIFILM Corporation, Medical Systems Research and Development Center, Imaging Research Group, Minato City, Japan.
PLoS One. 2025 Jun 2;20(6):e0324496. doi: 10.1371/journal.pone.0324496. eCollection 2025.
Quantitative MRI (qMRI) requires the acquisition of multiple images with parameter changes, resulting in longer measurement times than conventional imaging. Deep learning (DL) for image reconstruction has shown a significant reduction in acquisition time and improved image quality. In qMRI, where the image contrast varies between sequences, preparing large, fully-sampled (FS) datasets is challenging. Recently, methods that do not require FS data such as self-supervised learning (SSL) and zero-shot self-supervised learning (ZSSSL) have been proposed. Another challenge is the large GPU memory requirement for DL-based qMRI image reconstruction, owing to the simultaneous processing of multiple contrast images. In this context, Kellman et al. proposed memory-efficient learning (MEL) to save the GPU memory. This study evaluated SSL and ZSSSL frameworks with MEL to accelerate qMRI. Three experiments were conducted using the following sequences: 2D T2 mapping/MSME (Experiment 1), 3D T1 mapping/VFA-SPGR (Experiment 2), and 3D T2 mapping/DESS (Experiment 3). Each experiment used the undersampled k-space data under acceleration factors of 4, 8, and 12. The reconstructed maps were evaluated using quantitative metrics. In this study, we performed three qMRI reconstruction measurements and compared the performance of the SL- and GT-free learning methods, SSL and ZSSSL. Overall, the performances of SSL and ZSSSL were only slightly inferior to those of SL, even under high AF conditions. The quantitative errors in diagnostically important tissues (WM, GM, and meniscus) were small, demonstrating that SL and ZSSSL performed comparably. Additionally, by incorporating a GPU memory-saving implementation, we demonstrated that the network can operate on a GPU with a small memory (<8GB) with minimal speed reduction. This study demonstrates the effectiveness of memory-efficient GT-free learning methods using MEL to accelerate qMRI.
定量磁共振成像(qMRI)需要采集参数变化的多幅图像,这导致测量时间比传统成像更长。用于图像重建的深度学习(DL)已显示出采集时间显著缩短且图像质量得到改善。在qMRI中,序列之间的图像对比度各不相同,因此准备大型的、全采样(FS)数据集具有挑战性。最近,已经提出了诸如自监督学习(SSL)和零样本自监督学习(ZSSSL)等不需要FS数据的方法。另一个挑战是基于DL的qMRI图像重建对GPU内存的需求量很大,这是由于要同时处理多幅对比度图像。在这种情况下,凯尔曼等人提出了内存高效学习(MEL)来节省GPU内存。本研究评估了采用MEL的SSL和ZSSSL框架以加速qMRI。使用以下序列进行了三个实验:二维T2映射/MSME(实验1)、三维T1映射/VFA-SPGR(实验2)和三维T2映射/DESS(实验3)。每个实验都使用了加速因子为4倍、8倍和12倍的欠采样k空间数据。使用定量指标对重建的图谱进行评估。在本研究中,我们进行了三次qMRI重建测量,并比较了无监督学习(SL)和无真实标签学习(GT)方法SSL和ZSSSL的性能。总体而言,即使在高加速因子条件下,SSL和ZSSSL的性能也仅略逊于SL。诊断重要组织(白质、灰质和半月板)的定量误差很小,表明SSL和ZSSSL表现相当。此外,通过采用节省GPU内存的实现方式,我们证明该网络可以在内存较小(<8GB)的GPU上运行,且速度降低最小。本研究证明了使用MEL的内存高效无GT学习方法在加速qMRI方面的有效性。