Barquero Germán, La Rosa Francesco, Kebiri Hamza, Lu Po-Jui, Rahmanzadeh Reza, Weigel Matthias, Fartaria Mário João, Kober Tobias, Théaudin Marie, Du Pasquier Renaud, Sati Pascal, Reich Daniel S, Absinta Martina, Granziera Cristina, Maggi Pietro, Bach Cuadra Meritxell
Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne, Switzerland; Medical Image Analysis Laboratory (MIAL), Center for Biomedical Imaging (CIBM), University of Lausanne, Switzerland; Department of Radiology, Lausanne University Hospital and University of Lausanne, Switzerland.
Medical Image Analysis Laboratory (MIAL), Center for Biomedical Imaging (CIBM), University of Lausanne, Switzerland; Department of Radiology, Lausanne University Hospital and University of Lausanne, Switzerland.
Neuroimage Clin. 2020;28:102412. doi: 10.1016/j.nicl.2020.102412. Epub 2020 Sep 4.
In multiple sclerosis (MS), the presence of a paramagnetic rim at the edge of non-gadolinium-enhancing lesions indicates perilesional chronic inflammation. Patients featuring a higher paramagnetic rim lesion burden tend to have more aggressive disease. The objective of this study was to develop and evaluate a convolutional neural network (CNN) architecture (RimNet) for automated detection of paramagnetic rim lesions in MS employing multiple magnetic resonance (MR) imaging contrasts.
Imaging data were acquired at 3 Tesla on three different scanners from two different centers, totaling 124 MS patients, and studied retrospectively. Paramagnetic rim lesion detection was independently assessed by two expert raters on T2*-phase images, yielding 462 rim-positive (rim+) and 4857 rim-negative (rim-) lesions. RimNet was designed using 3D patches centered on candidate lesions in 3D-EPI phase and 3D FLAIR as input to two network branches. The interconnection of branches at both the first network blocks and the last fully connected layers favors the extraction of low and high-level multimodal features, respectively. RimNet's performance was quantitatively evaluated against experts' evaluation from both lesion-wise and patient-wise perspectives. For the latter, patients were categorized based on a clinically relevant threshold of 4 rim+ lesions per patient. The individual prediction capabilities of the images were also explored and compared (DeLong test) by testing a CNN trained with one image as input (unimodal).
The unimodal exploration showed the superior performance of 3D-EPI phase and 3D-EPI magnitude images in the rim+/- classification task (AUC = 0.913 and 0.901), compared to the 3D FLAIR (AUC = 0.855, Ps < 0.0001). The proposed multimodal RimNet prototype clearly outperformed the best unimodal approach (AUC = 0.943, P < 0.0001). The sensitivity and specificity achieved by RimNet (70.6% and 94.9%, respectively) are comparable to those of experts at the lesion level. In the patient-wise analysis, RimNet performed with an accuracy of 89.5% and a Dice coefficient (or F1 score) of 83.5%.
The proposed prototype showed promising performance, supporting the usage of RimNet for speeding up and standardizing the paramagnetic rim lesions analysis in MS.
在多发性硬化症（MS）中，非钆增强病变边缘存在顺磁性边缘表明病变周围存在慢性炎症。具有较高顺磁性边缘病变负荷的患者往往患有更具侵袭性的疾病。本研究的目的是开发并评估一种卷积神经网络（CNN）架构（RimNet），用于利用多种磁共振（MR）成像对比自动检测MS中的顺磁性边缘病变。
在3台不同的扫描仪上于3特斯拉采集了来自两个不同中心的124例MS患者的成像数据，并进行回顾性研究。两名专家评估者在T2*期图像上独立评估顺磁性边缘病变检测情况，共得到462个边缘阳性（rim+）病变和4857个边缘阴性（rim-）病变。RimNet的设计是将以3D-EPI期和3D FLAIR中的候选病变为中心的3D图像块作为输入，输入到两个网络分支中。在第一个网络模块和最后一个全连接层，分支之间的互连分别有利于提取低级和高级多模态特征。从病变层面和患者层面两个角度，根据专家评估对RimNet的性能进行定量评估。对于患者层面的评估，根据每位患者4个rim+病变这一临床相关阈值对患者进行分类。还通过测试以一幅图像作为输入进行训练的CNN（单模态）来探索和比较图像的个体预测能力（DeLong检验）。
单模态探索显示，在rim+/-分类任务中，3D-EPI期和3D-EPI幅度图像的性能优于3D FLAIR（AUC分别为0.913和0.901，而3D FLAIR的AUC为0.855，P<0.0001）。所提出的多模态RimNet原型明显优于最佳单模态方法（AUC = 0.943，P < 0.0001）。RimNet实现的灵敏度和特异性（分别为70.6%和94.9%）在病变水平上与专家相当。在患者层面分析中，RimNet的准确率为89.5%，Dice系数（或F1分数）为83.5%。
所提出的原型表现出了有前景的性能，支持使用RimNet来加速和规范MS中顺磁性边缘病变的分析。
