Department of Oncology, University of Alberta, Edmonton, Canada. Author to whom correspondence should be addressed.
Phys Med Biol. 2019 Sep 23;64(19):195002. doi: 10.1088/1361-6560/ab408e.
Investigate 3D (spatial and temporal) convolutional neural networks (CNNs) for real-time on-the-fly magnetic resonance imaging (MRI) reconstruction. In particular, we investigated the applicability of training CNNs on a patient-by-patient basis for the purpose of lung tumor segmentation. Data were acquired with our 3 T Philips Achieva system. A retrospective analysis was performed on six non-small cell lung cancer patients who received fully sampled dynamic acquisitions consisting of 650 free breathing images using a bSSFP sequence. We retrospectively undersampled the six patient's data by 5× and 10× acceleration. The retrospective data was used to quantitatively compare the CNN reconstruction to gold truth data via the Dice coefficient (DC) and centroid displacement to compare the tumor segmentations. Reconstruction noise was investigated using the normalized mean square error (NMSE). We further validated the technique using prospectively undersampled data from a volunteer and motion phantom. The retrospectively undersampled data at 5× and 10× acceleration was reconstructed using patient specific trained CNNs. The patient average DCs for the tumor segmentation at 5× and 10× acceleration were 0.94 and 0.92, respectively. These DC values are greater than the inter- and intra-observer segmentations acquired by radiation oncologist experts as reported in a previous study of ours. Furthermore, the patient specific CNN can be trained in under 6 h and the reconstruction time was 65 ms per image. The prospectively undersampled CNN reconstruction data yielded qualitatively acceptable images. We have shown that 3D CNNs can be used for real-time on-the-fly dynamic image reconstruction utilizing both spatial and temporal data in this proof of concept study. We evaluated the technique using six retrospectively undersampled lung cancer patient data sets, as well as prospectively undersampled data acquired from a volunteer and motion phantom. The reconstruction speed achieved for our current implementation was 65 ms per image.
研究三维（空间和时间）卷积神经网络（CNN）在实时磁共振成像（MRI）重建中的应用。特别是，我们研究了在患者个体基础上训练 CNN 的适用性，目的是进行肺部肿瘤分割。数据是在我们的 3T 飞利浦 Achieva 系统上采集的。对 6 名非小细胞肺癌患者进行了回顾性分析，这些患者接受了使用 bSSFP 序列进行的完全采样动态采集，共采集了 650 次自由呼吸图像。我们对这 6 名患者的数据进行了 5×和 10×的回顾性欠采样。通过 Dice 系数（DC）和质心位移对回顾性数据进行定量比较，以比较肿瘤分割，从而对 CNN 重建进行定量比较。使用归一化均方误差（NMSE）来研究重建噪声。我们还使用志愿者和运动体模的前瞻性欠采样数据来验证该技术。使用患者特定训练的 CNN 对 5×和 10×加速的回顾性欠采样数据进行重建。5×和 10×加速的肿瘤分割的患者平均 DC 分别为 0.94 和 0.92。这些 DC 值大于我们之前的一项研究中报告的放射肿瘤学专家获取的组内和组间分割值。此外，患者特定的 CNN 可以在 6 小时内训练完成，重建时间为每张图像 65 毫秒。前瞻性欠采样的 CNN 重建数据产生了可接受的图像。在这项概念验证研究中，我们已经证明 3D CNN 可以用于实时动态图像重建，利用空间和时间数据。我们使用 6 个回顾性欠采样的肺癌患者数据集以及从志愿者和运动体模采集的前瞻性欠采样数据评估了该技术。我们当前实现的重建速度为每张图像 65 毫秒。
