在3特斯拉场强下，深度学习加速的具有增强去噪功能的单次激发快速自旋回波序列用于胰腺磁共振成像的临床可行性。

Clinical feasibility of deep learning-accelerated single-shot turbo spin echo sequence with enhanced denoising for pancreas MRI at 3 Tesla.

作者信息

Kim Jeong Woo, Park Bit Na, Nickel Dominik, Paek Mun Young, Lee Chang Hee

机构信息

Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, Seoul, South Korea.

MR Applications Predevelopment, Siemens Healthineers AG, Erlangen, Germany.

出版信息

Eur J Radiol. 2024 Dec;181:111737. doi: 10.1016/j.ejrad.2024.111737. Epub 2024 Sep 15.

DOI:10.1016/j.ejrad.2024.111737

PMID:39305750

Abstract

PURPOSE

To assess the feasibility of the single-shot turbo spin echo sequence using deep learning-based reconstruction (DLR) (HASTE) with enhanced denoising for pancreas MRI.

METHODS

Patients who underwent pancreas MRI from March to April 2021 were included. Four T2-weighted images (non-FS conventional HASTE vs. HASTE with enhanced denoising and FS HASTE with enhanced denoising vs. HASTE) were acquired. Two readers independently assessed the image quality parameters of the two non-FS image sets using a 4-point Likert scale. The signal-to-noise ratio (SNR) of the cystic lesions and pancreatic parenchyma and the contrast-to-noise ratio between the cystic lesion and pancreatic parenchyma were calculated for all four image sets. The size of the largest cystic lesion and the diameter of pancreatic duct were measured.

RESULTS

A total of 63 patients were included, 48 (76.2 %) of whom had 136 pancreatic cystic lesion(s). The acquisition times of conventional HASTE and HASTE were 69 and 18 sec, respectively. All image quality parameters except artifacts for reader 2 were significantly better for HASTE with enhanced denoising. Those images also received scores for overall image quality that were significantly higher than those for the conventional HASTE (3.26 ± 0.54 vs. 2.47 ± 0.56, p < 0.001). The SNR of the pancreatic cystic lesion and pancreatic parenchyma was significantly higher in the HASTE with enhanced denoising (p < 0.001 for both). Inter-reader variability for measuring the pancreatic cyst size (ICC, 0.999 vs. 0.995; 95 % LoA, -0.13481 to 0.14743 vs. -0.24097 to 0.27404) and duct diameter (ICC, 0.994 vs. 0.969; 95 % LoA, -0.11684 to 0.36026 vs. -0.45544 to 0.44664) was lower in HASTE with enhanced denoising than in the conventional HASTE.

CONCLUSION

HASTE with enhanced denoising could be useful for reducing the acquisition time of pancreas MRI while improving the image quality for the evaluation of pancreatic cystic lesions.

摘要

目的

评估基于深度学习重建（DLR）的单次激发涡轮自旋回波序列（HASTE）在胰腺MRI中增强去噪的可行性。

方法

纳入2021年3月至4月接受胰腺MRI检查的患者。采集了四张T2加权图像（非脂肪抑制常规HASTE与增强去噪的HASTE以及脂肪抑制增强去噪的HASTE与HASTE）。两名阅片者使用4分李克特量表独立评估两组非脂肪抑制图像集的图像质量参数。计算所有四张图像集的囊性病变和胰腺实质的信噪比（SNR）以及囊性病变与胰腺实质之间的对比噪声比。测量最大囊性病变的大小和胰管直径。

结果

共纳入63例患者，其中48例（76.2%）有136个胰腺囊性病变。常规HASTE和HASTE的采集时间分别为69秒和18秒。除阅片者2的伪影外，增强去噪的HASTE的所有图像质量参数均显著更好。这些图像的整体图像质量评分也显著高于常规HASTE（3.26±0.54对2.47±0.56，p<0.001）。增强去噪的HASTE中胰腺囊性病变和胰腺实质的SNR显著更高（两者均p<0.001）。增强去噪的HASTE中测量胰腺囊肿大小（组内相关系数，0.999对0.995；95%一致性界限，-0.13481至0.14743对-0.24097至0.27404）和导管直径（组内相关系数，0.994对0.969；95%一致性界限，-0.11684至0.36026对-0.45544至0.44664）的阅片者间变异性低于常规HASTE。