Department of Radiology, Fujita Health University School of Medicine, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake, Aichi, 470-1192, Japan.
Joint Research Laboratory of Advanced Medical Imaging, Fujita Health University, School of Medicine, Toyoake, Japan.
Eur Radiol. 2022 Oct;32(10):6658-6667. doi: 10.1007/s00330-022-08877-2. Epub 2022 Jun 10.
To compare the utility of deep learning reconstruction (DLR) for improving acquisition time, image quality, and intraductal papillary mucinous neoplasm (IPMN) evaluation for 3D MRCP obtained with parallel imaging (PI), multiple k-space data acquisition for each repetition time (TR) technique (Fast 3D mode multiple: Fast 3Dm) and compressed sensing (CS) with PI.
A total of 32 IPMN patients who had undergone 3D MRCPs obtained with PI, Fast 3Dm, and CS with PI and reconstructed with and without DLR were retrospectively included in this study. Acquisition time, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) obtained with all protocols were compared using Tukey's HSD test. Results of endoscopic ultrasound, ERCP, surgery, or pathological examination were determined as standard reference, and distribution classifications were compared among all 3D MRCP protocols by McNemar's test.
Acquisition times of Fast 3Dm and CS with PI with and without DLR were significantly shorter than those of PI with and without DLR (p < 0.05). Each MRCP sequence with DLR showed significantly higher SNRs and CNRs than those without DLR (p < 0.05). IPMN distribution accuracy of PI with and without DLR and Fast 3Dm with DLR was significantly higher than that of Fast 3Dm without DLR and CS with PI without DLR (p < 0.05).
DLR is useful for improving image quality and IPMN evaluation capability on 3D MRCP obtained with PI, Fast 3Dm, or CS with PI. Moreover, Fast 3Dm and CS with PI may play as substitution to PI for MRCP in patients with IPMN.
• Mean examination times of multiple k-space data acquisitions for each TR and compressed sensing with parallel imaging were significantly shorter than that of parallel imaging (p < 0.0001). • When comparing image quality of 3D MRCPs with and without deep learning reconstruction, deep learning reconstruction significantly improved signal-to-noise ratio and contrast-to-noise ratio (p < 0.05). • IPMN distribution accuracies of parallel imaging with and without deep learning reconstruction (with vs. without: 88.0% vs. 88.0%) and multiple k-space data acquisitions for each TR with deep learning reconstruction (86.0%) were significantly higher than those of others (p < 0.05).
比较深度学习重建（DLR）在改善采集时间、图像质量和胰胆管磁共振成像（MRCP）对胰腺导管内乳头状黏液性肿瘤（IPMN）评估方面的应用，该研究使用并行成像（PI）、每个重复时间（TR）的多次采集（Fast 3Dm）和压缩感知（CS）技术。
本研究回顾性纳入了 32 例接受 PI、Fast 3Dm 和 CS 联合 PI 成像并分别进行 DLR 重建和未重建的 IPMN 患者。使用 Tukey 的 HSD 检验比较所有协议获得的采集时间、信噪比（SNR）和对比噪声比（CNR）。使用内镜超声、ERCP、手术或病理检查结果作为标准参考，并使用 McNemar 检验比较所有 3D MRCP 方案的分布分类。
Fast 3Dm 和 CS 联合 PI 无论是否进行 DLR 重建，采集时间均明显短于 PI 联合 DLR 或未联合 DLR（p < 0.05）。每个具有 DLR 的 MRCP 序列的 SNR 和 CNR 均明显高于未进行 DLR 重建的序列（p < 0.05）。PI 联合 DLR 和 Fast 3Dm 联合 DLR 的 IPMN 分布准确率明显高于 Fast 3Dm 联合 DLR 和 CS 联合 PI 联合 DLR（p < 0.05）。
DLR 可用于改善 PI、Fast 3Dm 或 CS 联合 PI 获得的 3D MRCP 的图像质量和 IPMN 评估能力。此外，Fast 3Dm 和 CS 联合 PI 可能是 IPMN 患者 MRCP 的替代方法。
每次 TR 多次采集和并行成像的压缩感知的平均检查时间明显短于并行成像（p < 0.0001）。
比较有无深度学习重建的 3D MRCP 图像质量时，深度学习重建显著提高了信噪比和对比噪声比（p < 0.05）。
并行成像联合和不联合深度学习重建（有 vs. 无：88.0% vs. 88.0%）以及多次采集联合深度学习重建（86.0%）的 IPMN 分布准确率明显高于其他方法（p < 0.05）。
