Ground-truth-free deep learning approach for accelerated quantitative parameter mapping with memory efficient learning

• Published in: PloS one Vol. 20; no. 6; p. e0324496
• Main Authors: Fujita, Naoto, Yokosawa, Suguru, Shirai, Toru, Terada, Yasuhiko
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 02.06.2025; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Biology and Life Sciences; Brain - diagnostic imaging; Computer and Information Sciences; Datasets; Deep Learning; Humans; Image acquisition; Image contrast; Image processing; Image Processing, Computer-Assisted - methods; Image quality; Image reconstruction; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Mapping; Medical imaging; Medicine and Health Sciences; Memory; Methods; Neural networks; Parameters; Performance evaluation; Research and Analysis Methods; Self-supervised learning; Social Sciences; Japan; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0324496

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.