Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, China.
Imaging and Interventional Radiology, The Chinese University of Hong Kong, Hong Kong, China.
J Magn Reson Imaging. 2024 Sep;60(3):1165-1175. doi: 10.1002/jmri.29198. Epub 2023 Dec 27.
Cerebral microbleeds (CMB) are indicators of severe cerebral small vessel disease (CSVD) that can be identified through hemosiderin-sensitive sequences in MRI. Specifically, quantitative susceptibility mapping (QSM) and deep learning were applied to detect CMBs in MRI.
To automatically detect CMB on QSM, we proposed a two-stage deep learning pipeline.
Retrospective.
A total number of 1843 CMBs from 393 patients (69 ± 12) with cerebral small vessel disease were included in this study. Seventy-eight subjects (70 ± 13) were used as external testing.
FIELD STRENGTH/SEQUENCE: 3 T/QSM.
The proposed pipeline consisted of two stages. In stage I, 2.5D fast radial symmetry transform (FRST) algorithm along with a one-layer convolutional network was used to identify CMB candidate regions in QSM images. In stage II, the V-Net was utilized to reduce false positives. The V-Net was trained using CMB and non CMB labels, which allowed for high-level feature extraction and differentiation between CMBs and CMB mimics like vessels. The location of CMB was assessed according to the microbleeds anatomical rating scale (MARS) system.
The sensitivity and positive predicative value (PPV) were reported to evaluate the performance of the model. The number of false positive per subject was presented.
Our pipeline demonstrated high sensitivities of up to 94.9% at stage I and 93.5% at stage II. The overall sensitivity was 88.9%, and the false positive rate per subject was 2.87. With respect to MARS, sensitivities of above 85% were observed for nine different brain regions.
We have presented a deep learning pipeline for detecting CMB in the CSVD cohort, along with a semi-automated MARS scoring system using the proposed method. Our results demonstrated the successful application of deep learning for CMB detection on QSM and outperformed previous handcrafted methods.
2 TECHNICAL EFFICACY: Stage 2.
脑微出血（CMB）是严重脑小血管疾病（CSVD）的指标，可以通过 MRI 中的含铁血黄素敏感序列来识别。具体来说，定量磁化率映射（QSM）和深度学习被应用于 MRI 中的 CMB 检测。
为了自动检测 QSM 上的 CMB，我们提出了一个两阶段的深度学习管道。
回顾性。
本研究纳入了 393 例（69±12 岁）脑小血管病患者的 1843 个 CMB，78 例（70±13 岁）作为外部测试。
磁场强度/序列：3T/QSM。
所提出的管道由两个阶段组成。在第一阶段，2.5D 快速径向对称变换（FRST）算法和一层卷积网络用于识别 QSM 图像中的 CMB 候选区域。在第二阶段，使用 V-Net 减少假阳性。V-Net 使用 CMB 和非 CMB 标签进行训练，这允许进行高级特征提取，并区分 CMB 和 CMB 模拟物（如血管）。CMB 的位置根据微出血解剖评分系统（MARS）进行评估。
报告敏感性和阳性预测值（PPV）以评估模型的性能。报告了每个受试者的假阳性数量。
我们的管道在第一阶段的敏感性高达 94.9%，在第二阶段的敏感性为 93.5%。总体敏感性为 88.9%，每个受试者的假阳性率为 2.87。对于 MARS，九个不同脑区的敏感性均高于 85%。
我们提出了一种用于 CSVD 队列中 CMB 检测的深度学习管道，以及使用所提出的方法进行半自动 MARS 评分系统。我们的结果表明，深度学习在 QSM 上的 CMB 检测中得到了成功应用，并优于以前的手工制作方法。
2 技术功效：第 2 级。
