Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne, Switzerland; CIBM Center for Biomedical Imaging, Switzerland; Medical Image Analysis Laboratory (MIAL), Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
Signal Processing Laboratory (LTS5), Ecole Polytechnique Fédérale de Lausanne, Switzerland; CIBM Center for Biomedical Imaging, Switzerland; Medical Image Analysis Laboratory (MIAL), Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
Comput Biol Med. 2021 May;132:104297. doi: 10.1016/j.compbiomed.2021.104297. Epub 2021 Feb 26.
Compared to the conventional magnetization-prepared rapid gradient-echo imaging (MPRAGE) MRI sequence, the specialized magnetization prepared 2 rapid acquisition gradient echoes (MP2RAGE) shows a higher brain tissue and lesion contrast in multiple sclerosis (MS) patients. The goal of this work is to retrospectively generate realistic-looking MP2RAGE uniform images (UNI) from already acquired MPRAGE images in order to improve the automatic lesion and tissue segmentation.
For this task we propose a generative adversarial network (GAN). Multi-contrast MRI data of 12 healthy controls and 44 patients diagnosed with MS was retrospectively analyzed. Imaging was acquired at 3T using a SIEMENS scanner with MPRAGE, MP2RAGE, FLAIR, and DIR sequences. We train the GAN with both healthy controls and MS patients to generate synthetic MP2RAGE UNI images. These images were then compared to the real MP2RAGE UNI (considered as ground truth) analyzing the output of automatic brain tissue and lesion segmentation tools. Reference-based metrics as well as the lesion-wise true and false positives, Dice coefficient, and volume difference were considered for the evaluation. Statistical differences were assessed with the Wilcoxon signed-rank test.
The synthetic MP2RAGE UNI significantly improves the lesion and tissue segmentation masks in terms of Dice coefficient and volume difference (p-values < 0.001) compared to the MPRAGE. For the segmentation metrics analyzed no statistically significant differences are found between the synthetic and acquired MP2RAGE UNI.
Synthesized MP2RAGE UNI images are visually realistic and improve the output of automatic segmentation tools.
与传统的磁化准备快速梯度回波成像（MPRAGE）MRI 序列相比，专门的磁化准备 2 快速获取梯度回波（MP2RAGE）在多发性硬化症（MS）患者中显示出更高的脑组织和病变对比度。本研究的目的是从已经获得的 MPRAGE 图像中回顾性地生成逼真的 MP2RAGE 均匀图像（UNI），以改善自动病变和组织分割。
为此任务，我们提出了一种生成对抗网络（GAN）。回顾性分析了 12 名健康对照者和 44 名诊断为 MS 的患者的多对比度 MRI 数据。使用西门子扫描仪在 3T 上进行成像，采集 MPRAGE、MP2RAGE、FLAIR 和 DIR 序列。我们使用健康对照组和 MS 患者训练 GAN 以生成合成的 MP2RAGE UNI 图像。然后将这些图像与真实的 MP2RAGE UNI（视为真实值）进行比较，分析自动脑组织和病变分割工具的输出。评估时考虑了基于参考的指标以及病变的真阳性和假阳性、Dice 系数和体积差异。使用 Wilcoxon 符号秩检验评估统计学差异。
与 MPRAGE 相比，合成的 MP2RAGE UNI 显著改善了病变和组织分割掩模的 Dice 系数和体积差异（p 值<0.001）。对于分析的分割指标，在合成和获取的 MP2RAGE UNI 之间未发现统计学上的显著差异。
合成的 MP2RAGE UNI 图像在视觉上逼真，并改善了自动分割工具的输出。
