Magnetic susceptibility source separation (χ‐separation), an advanced quantitative susceptibility mapping (QSM) method, enables the separate estimation of paramagnetic and diamagnetic susceptibility source distributions in the brain. Similar to QSM, it requires solving the ill‐conditioned problem of dipole inversion, suffering from so‐called streaking artifacts. Additionally, the method utilizes reversible transverse relaxation (R2′=R2*−R2) to complement frequency shift information for estimating susceptibility source concentrations, requiring time‐consuming data acquisition for R2 (e.g., multi‐echo spin‐echo) in addition to multi‐echo GRE data for R2*. To address these challenges, we develop a new deep learning network, χ‐sepnet, and propose two deep learning‐based susceptibility source separation pipelines, χ‐sepnet‐R2′ for inputs with multi‐echo GRE and multi‐echo spin‐echo (or turbo spin‐echo) and χ‐sepnet‐R2* for input with multi‐echo GRE only. The neural network is trained using multiple head orientation data that provide streaking artifact‐free labels, generating high‐quality χ‐separation maps. The evaluation of the pipelines encompasses both qualitative and quantitative assessments in healthy subjects, and visual inspection of lesion characteristics in multiple sclerosis patients. The susceptibility source‐separated maps of the proposed pipelines delineate detailed brain structures with substantially reduced artifacts compared to those from the conventional regularization‐based reconstruction methods. In quantitative analysis, χ‐sepnet‐R2′ achieves the best outcomes followed by χ‐sepnet‐R2*, outperforming the conventional methods. When the lesions of multiple sclerosis patients are classified into subtypes, most lesions are identified as the same subtype in the maps from χ‐sepnet‐R2′ and χ‐sepnet‐R2* (paramagnetic susceptibility: 99.6% and diamagnetic susceptibility: 98.4%; both out of 250 lesions). The χ‐sepnet‐R2* pipeline, which only requires multi‐echo GRE data, has demonstrated its potential to offer broad clinical and scientific applications, although further evaluations for various diseases and pathological conditions are necessary.
展开▼
机译：磁化率源分离 （χ-separation） 是一种先进的定量磁化率映射 （QSM） 方法，能够分别估计大脑中的顺磁和抗磁化率源分布。与 QSM 类似，它需要解决偶极子反转的病态问题，即所谓的条纹伪影。此外，该方法利用可逆横向弛豫 （R2′=R2*-R2） 来补充频移信息以估计磁化率源浓度，除了 R2* 的多回波 GRE 数据外，还需要耗时的 R2 数据采集（例如，多回波自旋回波）。为了应对这些挑战，我们开发了一种新的深度学习网络 χ-sepnet，并提出了两个基于深度学习的磁化率源分离管道，χ‐sepnet‐R2′ 用于具有多回波 GRE 和多回波自旋回波（或涡轮自旋回波）的输入，χ‐sepnet-R2* 用于仅具有多回波 GRE 的输入。神经网络使用多个头部方向数据进行训练，这些数据提供无条纹伪影的标签，生成高质量的 χ 分离图。管道的评估包括对健康受试者的定性和定量评估，以及对多发性硬化症患者的病变特征进行目视检查。与传统的基于正则化的重建方法相比，拟议管道的磁化率源分离图描绘了详细的大脑结构，大大减少了伪影。在定量分析中，χ-sepnet-R2′ 取得了最好的结果，其次是 χ-sepnet-R2*，优于传统方法。当多发性硬化症患者的病变分为亚型时，大多数病变在 χ‐sepnet‐R2′ 和 χ‐sepnet‐R2* 的图谱中被确定为相同的亚型（顺磁敏感性：99.6% 和抗磁性敏感性：98.4%;均在 250 个病变中）。只需要多回波 GRE 数据的 χ-sepnet-R2* 管道已证明其具有提供广泛的临床和科学应用的潜力，尽管需要对各种疾病和病理状况进行进一步评估。
展开▼
