Sorby-Adams Annabel J, Guo Jennifer, Laso Pablo, Kirsch John E, Zabinska Julia, Garcia Guarniz Ana-Lucia, Schaefer Pamela W, Payabvash Seyedmehdi, de Havenon Adam, Rosen Matthew S, Sheth Kevin N, Gomez-Isla Teresa, Iglesias J Eugenio, Kimberly W Taylor
Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, USA.
Nat Commun. 2024 Dec 2;15(1):10488. doi: 10.1038/s41467-024-54972-x.
Portable, low-field magnetic resonance imaging (LF-MRI) of the brain may facilitate point-of-care assessment of patients with Alzheimer's disease (AD) in settings where conventional MRI cannot. However, image quality is limited by a lower signal-to-noise ratio. Here, we optimize LF-MRI acquisition and develop a freely available machine learning pipeline to quantify brain morphometry and white matter hyperintensities (WMH). We validate the pipeline and apply it to outpatients presenting with mild cognitive impairment or dementia due to AD. We find hippocampal volumes from ≤ 3 mm isotropic LF-MRI scans have agreement with conventional MRI and are more accurate than anisotropic counterparts. We also show WMH volume has agreement between manual segmentation and the automated pipeline. The increased availability and reduced cost of LF-MRI, in combination with our machine learning pipeline, has the potential to increase access to neuroimaging for dementia.
便携式低场磁共振成像（LF-MRI）脑部扫描，可在传统MRI无法使用的场景中，为阿尔茨海默病（AD）患者提供即时医疗评估。然而，其图像质量受限于较低的信噪比。在此，我们优化了LF-MRI采集流程，并开发了一个免费的机器学习管道，用于量化脑形态学和脑白质高信号（WMH）。我们对该管道进行了验证，并将其应用于因AD导致轻度认知障碍或痴呆的门诊患者。我们发现，各向同性≤3毫米的LF-MRI扫描获得的海马体积，与传统MRI结果一致，且比各向异性扫描更准确。我们还表明，WMH体积在手动分割和自动化管道之间具有一致性。LF-MRI可用性的提高和成本的降低，再加上我们的机器学习管道，有可能增加痴呆症患者获得神经成像检查的机会。
