QSMRim-Net：用于在定量磁化率图上识别慢性活动性多发性硬化病变的不平衡感知学习。
QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps.
机构信息
Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA; Department of Radiology, Weill Cornell Medicine, New York, NY, USA.
Department of Radiology, Weill Cornell Medicine, New York, NY, USA.
出版信息
Neuroimage Clin. 2022;34:102979. doi: 10.1016/j.nicl.2022.102979. Epub 2022 Mar 1.
BACKGROUND AND PURPOSE
Chronic active multiple sclerosis (MS) lesions are characterized by a paramagnetic rim at the edge of the lesion and are associated with increased disability in patients. Quantitative susceptibility mapping (QSM) is an MRI technique that is sensitive to chronic active lesions, termed rim + lesions on the QSM. We present QSMRim-Net, a data imbalance-aware deep neural network that fuses lesion-level radiomic and convolutional image features for automated identification of rim + lesions on QSM.
METHODS
QSM and T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRI of the brain were collected at 3 T for 172 MS patients. Rim + lesions were manually annotated by two human experts, followed by consensus from a third expert, for a total of 177 rim + and 3986 rim negative (rim-) lesions. Our automated rim + detection algorithm, QSMRim-Net, consists of a two-branch feature extraction network and a synthetic minority oversampling network to classify rim + lesions. The first network branch is for image feature extraction from the QSM and T2-FLAIR, and the second network branch is a fully connected network for QSM lesion-level radiomic feature extraction. The oversampling network is designed to increase classification performance with imbalanced data.
RESULTS
On a lesion-level, in a five-fold cross validation framework, the proposed QSMRim-Net detected rim + lesions with a partial area under the receiver operating characteristic curve (pROC AUC) of 0.760, where clinically relevant false positive rates of less than 0.1 were considered. The method attained an area under the precision recall curve (PR AUC) of 0.704. QSMRim-Net out-performed other state-of-the-art methods applied to the QSM on both pROC AUC and PR AUC. On a subject-level, comparing the predicted rim + lesion count and the human expert annotated count, QSMRim-Net achieved the lowest mean square error of 0.98 and the highest correlation of 0.89 (95% CI: 0.86, 0.92).
CONCLUSION
This study develops a novel automated deep neural network for rim + MS lesion identification using T2-FLAIR and QSM images.
背景与目的
慢性活动性多发性硬化症（MS）病灶的特征是病灶边缘有一个顺磁性边缘，与患者的残疾增加有关。定量磁化率映射（QSM）是一种对慢性活动性病灶敏感的 MRI 技术，在 QSM 上称为边缘+病灶。我们提出了 QSMRim-Net，这是一种数据不平衡感知的深度神经网络，它融合了病灶级别的放射组学和卷积图像特征，用于自动识别 QSM 上的边缘+病灶。
方法
在 3T 对 172 例 MS 患者进行脑部 QSM 和 T2 加权液体衰减反转恢复（T2-FLAIR）MRI 采集。两名人类专家手动标记边缘+病灶，然后由第三名专家进行共识，共标记了 177 个边缘+病灶和 3986 个边缘-（rim-）病灶。我们的自动边缘+检测算法 QSMRim-Net 由两个分支的特征提取网络和一个合成少数过采样网络组成，用于分类边缘+病灶。第一个网络分支用于从 QSM 和 T2-FLAIR 中提取图像特征，第二个网络分支是用于 QSM 病灶级放射组学特征提取的全连接网络。过采样网络旨在通过不平衡数据提高分类性能。
结果
在病灶水平上，在五重交叉验证框架中，所提出的 QSMRim-Net 检测边缘+病灶的部分接收者操作特征曲线下面积（pROC AUC）为 0.760，其中考虑了小于 0.1 的临床相关假阳性率。该方法的精度-召回曲线下面积（PR AUC）为 0.704。与应用于 QSM 的其他最先进方法相比，QSMRim-Net 在 pROC AUC 和 PR AUC 上均表现出色。在个体水平上，比较预测的边缘+病灶计数和人类专家标记的计数，QSMRim-Net 的均方误差最低，为 0.98，相关性最高，为 0.89（95%CI：0.86，0.92）。
结论
本研究开发了一种新的基于 T2-FLAIR 和 QSM 图像的用于边缘+MS 病灶识别的自动深度神经网络。
Zotero 插件