深度学习超分辨率重建加速高分辨率乳腺T1和T2加权MRI
这项前瞻性研究纳入47例有乳腺MRI指征的女性患者,在1.5T设备上比较低分辨率经深度学习重建的T1加权动态增强和T2加权序列与标准序列。结果显示重建序列采集时间分别缩短51%和46%,整体图像质量评分更高,BI-RADS评估一致性极好(κ=0.962)。
要点
- 深度学习重建使T1动态增强每期采集时间从90秒降至44秒,缩短51%。
- 深度学习重建使T2加权序列采集时间从192秒降至102秒,缩短46%。
- 重建序列整体图像质量评分高于标准序列,BI-RADS评估一致性极好(κ=0.962)。
核心结论
- 深度学习去噪和分辨率提升可缩短T1加权和T2加权乳腺MRI的采集时间并改善图像质量。
研究设计与样本
- 前瞻性研究,纳入47例有乳腺MRI指征的女性患者(平均年龄58±11岁),在1.5T MRI上采集标准分辨率(T1S、T2S)和低分辨率经深度学习重建(T1DL、T2DL)的T1加权动态增强和T2加权涡轮自旋回波序列;DL重建使用Adaptive-CS-Net进行压缩感知去噪和Precise-Image-Net对预先降采样图像进行分辨率提升。
关键影像表现/征象
- T1DL和T2DL的整体图像质量评分高于对应标准序列,例如T1S为4分(IQR 4-4)vs T1DL为5分(IQR 5-5),P<0.001。
- T1DL和T2DL的表观信噪比和表观对比噪声比高于T1S和T2S,例如T2S的表观信噪比为32.35±10.23 vs T2DL为27.88±6.86,P=0.014。
诊断标准与关键数值
- 整体图像质量采用5分Likert量表评估,1分为不可诊断,5分为优秀。
- 不同序列类型间BI-RADS评估的一致性Cohen κ=0.962,P<0.001。
- T1DL和T2DL的采集时间分别较标准序列缩短51%(每期44秒 vs 90秒)和46%(102秒 vs 192秒)。
临床应用与阅片要点
- 深度学习重建可在保持BI-RADS评估一致性的同时缩短T1加权动态增强和T2加权序列的采集时间。
- 重建序列的整体图像质量评分和表观信噪比、表观对比噪声比均高于标准序列。
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
RATIONALE AND OBJECTIVES: To assess the performance of an industry-developed deep learning (DL) algorithm to reconstruct low-resolution Cartesian T1-weighted dynamic contrast-enhanced (T1w) and T2-weighted turbo-spin-echo (T2w) sequences and compare them to standard sequences.
MATERIALS AND METHODS: Female patients with indications for breast MRI were included in this prospective study. The study protocol at 1.5 Tesla MRI included T1w and T2w. Both sequences were acquired in standard resolution (T1S and T2S) and in low-resolution with following DL reconstructions (T1DL and T2DL). For DL reconstruction, two convolutional networks were used: (1) Adaptive-CS-Net for denoising with compressed sensing, and (2) Precise-Image-Net for resolution upscaling of previously downscaled images. Overall image quality was assessed using 5-point-Likert scale (from 1=non-diagnostic to 5=excellent). Apparent signal-to-noise (aSNR) and contrast-to-noise (aCNR) ratios were calculated. Breast Imaging Reporting and Data System (BI-RADS) agreement between different sequence types was assessed.
RESULTS: A total of 47 patients were included (mean age, 58±11 years). Acquisition time for T1DL and T2DL were reduced by 51% (44 vs. 90 s per dynamic phase) and 46% (102 vs. 192 s), respectively. T1DL and T2DL showed higher overall image quality (e.g., 4 [IQR, 4-4] for T1S vs. 5 [IQR, 5-5] for T1DL, P<0.001). Both, T1DL and T2DL revealed higher aSNR and aCNR than T1S and T2S (e.g., aSNR: 32.35±10.23 for T2S vs. 27.88±6.86 for T2DL, P=0.014). Cohen k agreement by BI-RADS assessment was excellent (0.962, P<0.001).
CONCLUSION: DL for denoising and resolution upscaling reduces acquisition time and improves image quality for T1w and T2w breast MRI.
引用
- Mesropyan N, Katemann C, Leutner C, et al. Accelerated High-resolution T1- and T2-weighted Breast MRI with Deep Learning Super-resolution Reconstruction. Acad Radiol. 2025. PMID: 39794159. doi:10.1016/j.acra.2024.12.055
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。