文献速递乳腺MR

3T 乳腺 MRI 中深度学习重建的 T2 加权 Dixon 序列:更快采集与更优图像质量的前瞻性研究

Faster Acquisition and Improved Image Quality of T2-Weighted Dixon Breast MRI at 3T Using Deep Learning: A Prospective Study.
PubMed 文献 · Korean J Radiol · 2025-01-01

前瞻性纳入 140 例女性(85 个囊肿、31 例乳腺癌),在 3T 扫描仪上对比深度学习重建的 T2 加权快速自旋回波 Dixon 序列(T2DL)与常规 T2 加权 FSE Dixon 序列(T2STD)。T2DL 采集时间为 110 秒,较 T2STD 的 266 秒缩短 58%,信噪比和对比噪声比显著更高(P < 0.001),图像质量评分更高、噪声和伪影更少,对囊肿和乳腺癌的显示及诊断信心更优。作者认为 T2DL 可行,有潜力替代常规 T2 加权序列用于乳腺 MRI 检查。

要点

  • T2DL 采集时间 110 秒,较 T2STD 的 266 秒缩短 58%。
  • T2DL 信噪比和对比噪声比显著高于 T2STD(P < 0.001)。
  • 除骨髓外,T2DL 各解剖区域、植入物及骨边缘评分均更高(P ≤ 0.008)。

核心结论

  • T2DL 有效补偿了加速采集导致的信噪比损失,采集时间较 T2STD 缩短 58%,伪影更少、整体图像质量更优,可行且有潜力替代常规 T2 加权序列用于乳腺 MRI 检查。

研究设计与样本

  • 前瞻性研究,2022 年 11 月至 2023 年 4 月使用 3T 扫描仪,对每例患者均采集 T2DL 和 T2STD 两套序列;共纳入 151 例女性,最终分析 140 例(平均年龄 52 ± 14 岁;85 个囊肿、31 例乳腺癌);定量分析基于感兴趣区测量信噪比和对比噪声比,定性分析由两名放射科医师独立采用 Likert 量表评估。

关键影像表现/征象

  • T2DL 图像质量评分更高、噪声更少、伪影更少(P < 0.001)。
  • 乳腺和腋窝所有评估解剖区域、乳腺植入物及骨边缘在 T2DL 评分更高(P ≤ 0.008),但骨髓在 T2STD 评分更高(P < 0.001)。
  • 囊肿和乳腺癌的可见度、锐利度/边缘及微结构评分在 T2DL 更高(P ≤ 0.002)。
  • 囊肿诊断信心在 T2DL 更高(P < 0.001)。
  • 医师在并排比较中显著更偏好 T2DL(P < 0.001)。

诊断标准与关键数值

  • T2DL 采集时间 110 秒 ± 0,T2STD 采集时间 266 秒 ± 0,T2DL 较 T2STD 缩短 58%。
  • T2DL 信噪比和对比噪声比显著高于 T2STD(P < 0.001)。
  • 定性评估采用 Likert 量表,由两名放射科医师独立完成,并分析读者间可靠性。

临床应用与阅片要点

  • 作者认为 T2DL 可行,有潜力替代常规 T2 加权序列用于乳腺 MRI 检查。
  • 阅片时可关注 T2DL 在乳腺和腋窝解剖、植入物及骨边缘显示上的优势,但骨髓信号评估仍以 T2STD 评分更高。

局限性

  • 原文未报告局限性。

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

OBJECTIVE: The aim of this study was to compare image quality features and lesion characteristics between a faster deep learning (DL) reconstructed T2-weighted (T2-w) fast spin-echo (FSE) Dixon sequence with super-resolution (T2DL) and a conventional T2-w FSE Dixon sequence (T2STD) for breast magnetic resonance imaging (MRI).

MATERIALS AND METHODS: This prospective study was conducted between November 2022 and April 2023 using a 3T scanner. Both T2DL and T2STD sequences were acquired for each patient. Quantitative analysis was based on region-of-interest (ROI) measurements of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Qualitative analysis was performed independently by two radiologists using Likert scales to evaluate various image quality features, morphology, and diagnostic confidence for cysts and breast cancers. Reader preference between T2DL and T2STD was assessed via side-by-side comparison, and inter-reader reliability was also analyzed.

RESULTS: Total of 151 women were enrolled, with 140 women (mean age: 52 ± 14 years; 85 cysts and 31 breast cancers) included in the final analysis. The acquisition time was 110 s ± 0 for T2DL compared to 266 s ± 0 for T2STD. SNR and CNR were significantly higher in T2DL (P < 0.001). T2DL was associated with higher image quality scores, reduced noise, and fewer artifacts (P < 0.001). All evaluated anatomical regions (breast and axilla), breast implants, and bone margins were rated higher in T2DL (P ≤ 0.008), except for bone marrow, which scored higher in T2STD (P < 0.001). Scores for conspicuity, sharpness/margins, and microstructure of cysts and breast cancers were higher in T2DL (P ≤ 0.002). Diagnostic confidence for cysts was improved with T2DL (P < 0.001). Readers significantly preferred T2DL over T2STD in side-by-side comparisons (P < 0.001).

CONCLUSION: T2DL effectively corrected for SNR loss caused by accelerated image acquisition and provided a 58% reduction in acquisition time compared to T2STD. This led to fewer artifacts and improved overall image quality. Thus, T2DL is feasible and has the potential to replace conventional T2-w sequences for breast MRI examinations.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Wilpert C, Schneider H, Rau A, et al. Faster Acquisition and Improved Image Quality of T2-Weighted Dixon Breast MRI at 3T Using Deep Learning: A Prospective Study. Korean J Radiol. 2025. PMID: 39780629. doi:10.3348/kjr.2023.1303

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。