文献速递腹部MR

深度学习重建单次激发T2加权3T肝脏MRI:图像质量与病灶检出对比

Accelerated T2-weighted MRI of the liver at 3 T using a single-shot technique with deep learning-based image reconstruction: impact on the image quality and lesion detection.
PubMed 文献 · Abdom Radiol (NY) · 2022-09-28

本研究纳入41例连续接受3T腹部MRI的患者,对比单次激发深度学习重建脂肪抑制T2加权序列(DL HASTE-FS)与标准T2-FS序列。DL HASTE-FS采集时间显著缩短(54.93±16.69 s vs 114.00±32.98 s,p<.001),在肝脏边缘锐利度、血管边缘、胰管边缘、运动伪影、其他鬼影伪影及整体图像质量上评分均显著更高,病灶边缘锐利度评分亦更高。

要点

  • DL HASTE-FS采集时间不足标准T2-FS一半,图像质量与运动伪影控制更优
  • 肝脏边缘、肝血管及胰管边缘锐利度评分显著提升,利于管腔与病灶边界观察
  • 脂肪抑制均匀性与肝-脂肪对比度评分亦优于标准序列

关键影像表现/征象

  • DL HASTE-FS在肝脏边缘锐利度(4.3 vs 3.3,p<.001)与肝血管边缘(4.2 vs 3.3,p<.001)评分显著更高
  • 胰管边缘锐利度评分显著更高(4.0 vs 1.9,p<.001)
  • 面内运动伪影(4.0 vs 3.2,p<.001)与层间运动伪影(3.9 vs 3.4,p<.001)评分更高
  • 其他鬼影伪影评分更高(4.3 vs 2.9,p<.001),整体图像质量更优(4.0 vs 2.9,p<.001)
  • 肝脏病灶边缘锐利度评分显著更高(4.4 vs 3.7,p=.03);脂肪抑制均匀性(3.7 vs 3.4,p=.04)与肝-脂肪对比度(p=.03)亦更优

临床应用与阅片要点

  • 对运动不耐受或屏气困难患者,可优先选用DL HASTE-FS以缩短扫描时间并减少运动伪影
  • 利用其更清晰的肝血管与病灶边缘评分优势,提高小病灶及管腔边界描述的信心
  • 脂肪抑制均匀性评分提升有助于减少不均匀抑脂造成的假性信号判断

局限性

  • 单中心回顾性设计,样本量41例,可能存在选择偏倚
  • 仅3名医师评分,主观Likert量表一致性未在摘要中报告
  • 未报告病灶检出的敏感度、特异度等诊断效能指标

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: Fat-suppressed T2-weighted imaging (T2-FS) requires a long scan time and can be wrought with motion artifacts, urging the development of a shorter and more motion robust sequence. We compare the image quality of a single-shot T2-weighted MRI prototype with deep-learning-based image reconstruction (DL HASTE-FS) with a standard T2-FS sequence for 3 T liver MRI.

METHODS: 41 consecutive patients with 3 T abdominal MRI examinations including standard T2-FS and DL HASTE-FS, between 5/6/2020 and 11/23/2020, comprised the study cohort. Three radiologists independently reviewed images using a 5-point Likert scale for artifact and image quality measures, while also assessing for liver lesions.

RESULTS: DL HASTE-FS acquisition time was 54.93 ± 16.69, significantly (p < .001) shorter than standard T2-FS (114.00 ± 32.98 s). DL HASTE-FS received significantly higher scores for sharpness of liver margin (4.3 vs 3.3; p < .001), hepatic vessel margin (4.2 vs 3.3; p < .001), pancreatic duct margin (4.0 vs 1.9; p < .001); in-plane (4.0 vs 3.2; p < .001) and through-plane (3.9 vs 3.4; p < .001) motion artifacts; other ghosting artifacts (4.3 vs 2.9; p < .001); and overall image quality (4.0 vs 2.9; p < .001), in addition to receiving a higher score for homogeneity of fat suppression (3.7 vs 3.4; p = .04) and liver-fat contrast (p = .03). For liver lesions, DL HASTE-FS received significantly higher scores for sharpness of lesion margin (4.4 vs 3.7; p = .03).

CONCLUSION: Novel single-shot T2-weighted MRI with deep-learning-based image reconstruction demonstrated superior image quality compared with the standard T2-FS sequence for 3 T liver MRI, while being acquired in less than half the time.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Ginocchio, Smereka, Tong, et al. Accelerated T2-weighted MRI of the liver at 3 T using a single-shot technique with deep learning-based image reconstruction: impact on the image quality and lesion detection. Abdom Radiol (NY). 2022. PMID: 36171342. doi:10.1007/s00261-022-03687-y

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。