Sadikov Amir, Pan Xinlei, Choi Hannah, Cai Lanya T, Mukherjee Pratik
Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States.
Graduate Group in Bioengineering, University of California, San Francisco, CA, United States.
Imaging Neurosci (Camb). 2024 Jun 13;2. doi: 10.1162/imag_a_00193. eCollection 2024.
We use generative AI to enable rapid diffusion MRI (dMRI) with high fidelity, reproducibility, and generalizability across clinical and research settings. We employ a Swin UNEt Transformers (SWIN) model, trained on Human Connectome Project (HCP) data (n = 1021) and conditioned on registered T1 scans, to perform generalized dMRI denoising. We also qualitatively demonstrate super-resolution with artificially downsampled HCP data. Remarkably, SWIN can be fine-tuned for an out-of-domain dataset with a single example scan, as we demonstrate on dMRI of children with neurodevelopmental disorders (n = 40), adults with acute traumatic brain injury (n = 40), and adolescents with intracerebral hemorrhage due to vascular malformations undergoing resection (n = 8), each cohort scanned on different scanner models with different imaging protocols at different sites. This robustness to scan acquisition parameters, patient populations, scanner types, and sites eliminates the advantages of self-supervised methods over our fully supervised generative AI approach. We exceed current state-of-the-art denoising methods in accuracy and test-retest reliability of rapid diffusion tensor imaging (DTI) requiring only 90 seconds of scan time. SWIN denoising also achieves dramatic improvements over the state-of-the-art for test-retest reliability of intracellular volume fraction and free water fraction measurements and can remove heavy-tail noise, improving biophysical modeling fidelity. SWIN enables rapid diffusion MRI with unprecedented accuracy and reliability, especially at high diffusion weighting for probing biological tissues at microscopic spatial scales. The code and model are publicly available athttps://github.com/ucsfncl/dmri-swin.
我们使用生成式人工智能，以实现高保真、可重复性和跨临床及研究环境的通用性的快速扩散磁共振成像（dMRI）。我们采用了基于人类连接组计划（HCP）数据（n = 1021）训练并以配准的T1扫描为条件的Swin UNEt Transformers（SWIN）模型，来执行通用的dMRI去噪。我们还用人为下采样的HCP数据定性地展示了超分辨率。值得注意的是，SWIN可以通过单个示例扫描针对域外数据集进行微调，正如我们在患有神经发育障碍的儿童（n = 40）、患有急性创伤性脑损伤的成年人（n = 40）以及因血管畸形接受切除的脑出血青少年（n = 8）的dMRI上所展示的那样，每个队列在不同地点使用不同的扫描仪模型和不同的成像协议进行扫描。这种对扫描采集参数、患者群体、扫描仪类型和地点的鲁棒性消除了自监督方法相对于我们的完全监督生成式人工智能方法的优势。在仅需90秒扫描时间的快速扩散张量成像（DTI）的准确性和重测可靠性方面，我们超过了当前的先进去噪方法。SWIN去噪在细胞内体积分数和自由水分数测量的重测可靠性方面也比现有技术有了显著改进，并且可以去除重尾噪声，提高生物物理建模的保真度。SWIN以前所未有的准确性和可靠性实现了快速扩散MRI，特别是在高扩散权重下用于在微观空间尺度探测生物组织。代码和模型可在https://github.com/ucsfncl/dmri-swin上公开获取。
