文献速递泌尿生殖MR

深度学习重建的前列腺快速双参数MRI:图像质量提升且诊断效能相当

Enhanced Image Quality and Comparable Diagnostic Performance of Prostate Fast Bi-MRI with Deep Learning Reconstruction.
PubMed 文献 · Acad Radiol · 2025-07-18

这项前瞻性研究纳入61例成年男性泌尿科患者,比较标准方案、快速方案及深度学习重建(DLR)的前列腺双参数MRI。快速方案扫描时间较标准方案缩短近一半;DLR较快速T2WI和快速DWI显著改善信噪比、对比噪声比及图像锐度,而PI-RADS评分、ADC值及ADC鉴别良恶性病变的ROC曲线下面积、敏感度和特异度在各组间无显著差异。

要点

  • 快速前列腺双参数MRI扫描时间较标准方案缩短近一半。
  • DLR可显著改善快速T2WI和快速DWI的信噪比、对比噪声比及图像锐度。
  • 各组PI-RADS评分、ADC值及ADC诊断效能无显著差异。

核心结论

  • DLR可提升快速前列腺双参数MRI的图像质量,同时保持PI-RADS分类准确性和ADC诊断效能。

研究设计与样本

  • 前瞻性研究纳入61例成年男性泌尿科患者,行标准方案和快速方案前列腺MRI,序列包括T2WI、DWI和ADC图,DLR图像由快速数据集生成,比较标准方案、快速方案和DLR三组,以组织病理学确诊者测量ADC值并分析诊断效能。

关键影像表现/征象

  • 快速扫描方案较标准扫描方案采集时间缩短近一半。
  • 与快速T2WI相比,DLR显著改善信噪比、对比噪声比、病变斜率轮廓和背侧包膜边缘上升距离(P < 0.05)。
  • 与快速DWI相比,DLR显著提升信噪比、对比噪声比和图像锐度(P < 0.05)。

诊断标准与关键数值

  • 各组间PI-RADS评分无显著差异(P > 0.05)。
  • 各组间ADC值无显著差异(P > 0.05)。
  • ADC值鉴别良恶性病变的ROC曲线下面积、敏感度和特异度在各组间保持一致(P > 0.05)。

临床应用与阅片要点

  • DLR可用于改善快速前列腺双参数MRI的图像质量,同时保持PI-RADS分类准确性和ADC诊断效能。

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

RATIONAL AND OBJECTIVES: To evaluate image quality and diagnostic performance of prostate biparametric MRI (bi-MRI) with deep learning reconstruction (DLR).

MATERIALS AND METHODS: This prospective study included 61 adult male urological patients undergoing prostate MRI with standard-of-care (SOC) and fast protocols. Sequences included T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. DLR images were generated from FAST datasets. Three groups (SOC, FAST, DLR) were compared using: (1) five-point Likert scale, (2) signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), (3) lesion slope profiles, (4) dorsal capsule edge rise distance (ERD). PI-RADS scores were assigned to dominant lesions. ADC values were measured in histopathologically confirmed cases. Diagnostic performance was analyzed via receiver operating characteristic (ROC) curves (accuracy/sensitivity/specificity). Statistical tests included Friedman test, one-way ANOVA with post hoc analyses, and DeLong test for ROC comparisons (P<0.05).

RESULTS: FAST scanning protocols reduced acquisition time by nearly half compared to the SOC scanning protocol. When compared to T2WIFAST, DLR significantly improved SNR, CNR, slope profile, and ERD (P < 0.05). Similarly, DLR significantly enhanced SNR, CNR, and image sharpness when compared to DWIFAST (P < 0.05). No significant differences were observed in PI-RADS scores and ADC values between groups (P > 0.05). The areas under the ROC curves, sensitivity, and specificity of ADC values for distinguishing benign and malignant lesions remained consistent (P > 0.05).

CONCLUSION: DLR enhances image quality in fast prostate bi-MRI while preserving PI-RADS classification accuracy and ADC diagnostic performance.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Shen L, Yuan Y, Liu J, et al. Enhanced Image Quality and Comparable Diagnostic Performance of Prostate Fast Bi-MRI with Deep Learning Reconstruction. Acad Radiol. 2025. PMID: 40683764. doi:10.1016/j.acra.2025.06.059

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。