Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany.
Department of Obstetrics and Gynecology, University Hospital Würzburg, Würzburg, Germany.
J Magn Reson Imaging. 2024 Sep;60(3):1190-1200. doi: 10.1002/jmri.29139. Epub 2023 Nov 16.
For time-consuming diffusion-weighted imaging (DWI) of the breast, deep learning-based imaging acceleration appears particularly promising.
To investigate a combined k-space-to-image reconstruction approach for scan time reduction and improved spatial resolution in breast DWI.
Retrospective.
133 women (age 49.7 ± 12.1 years) underwent multiparametric breast MRI.
FIELD STRENGTH/SEQUENCE: 3.0T/T2 turbo spin echo, T1 3D gradient echo, DWI (800 and 1600 sec/mm).
DWI data were retrospectively processed using deep learning-based k-space-to-image reconstruction (DL-DWI) and an additional super-resolution algorithm (SRDL-DWI). In addition to signal-to-noise ratio and apparent diffusion coefficient (ADC) comparisons among standard, DL- and SRDL-DWI, a range of quantitative similarity (e.g., structural similarity index [SSIM]) and error metrics (e.g., normalized root mean square error [NRMSE], symmetric mean absolute percent error [SMAPE], log accuracy error [LOGAC]) was calculated to analyze structural variations. Subjective image evaluation was performed independently by three radiologists on a seven-point rating scale.
Friedman's rank-based analysis of variance with Bonferroni-corrected pairwise post-hoc tests. P < 0.05 was considered significant.
Both DL- and SRDL-DWI allowed for a 39% reduction in simulated scan time over standard DWI (5 vs. 3 minutes). The highest image quality ratings were assigned to SRDL-DWI with good interreader agreement (ICC 0.834; 95% confidence interval 0.818-0.848). Irrespective of b-value, both standard and DL-DWI produced superior SNR compared to SRDL-DWI. ADC values were slightly higher in SRDL-DWI (+0.5%) and DL-DWI (+3.4%) than in standard DWI. Structural similarity was excellent between DL-/SRDL-DWI and standard DWI for either b value (SSIM ≥ 0.86). Calculation of error metrics (NRMSE ≤ 0.05, SMAPE ≤ 0.02, and LOGAC ≤ 0.04) supported the assumption of low voxel-wise error.
Deep learning-based k-space-to-image reconstruction reduces simulated scan time of breast DWI by 39% without influencing structural similarity. Additionally, super-resolution interpolation allows for substantial improvement of subjective image quality.
4 TECHNICAL EFFICACY: Stage 1.
对于耗时的乳腺弥散加权成像（DWI），基于深度学习的成像加速技术似乎特别有前景。
研究一种联合的 k 空间到图像重建方法，用于减少乳腺 DWI 的扫描时间并提高空间分辨率。
回顾性。
133 名女性（年龄 49.7±12.1 岁）接受了多参数乳腺 MRI 检查。
磁场强度/序列：3.0T/T2 涡轮自旋回波，T1 3D 梯度回波，DWI（800 和 1600 sec/mm）。
使用基于深度学习的 k 空间到图像重建（DL-DWI）和额外的超分辨率算法（SRDL-DWI）对 DWI 数据进行回顾性处理。除了比较标准、DL 和 SRDL-DWI 之间的信噪比和表观扩散系数（ADC）外，还计算了一系列定量相似性（例如，结构相似性指数[SSIM]）和误差指标（例如，归一化均方根误差[NRMSE]、对称平均绝对百分比误差[SMAPE]、对数准确率误差[LOGAC]），以分析结构变化。三位放射科医生独立使用七点评分量表进行主观图像评估。
基于 Friedman 的等级方差分析，并用 Bonferroni 校正的两两事后检验进行比较。P＜0.05 被认为具有统计学意义。
与标准 DWI（5 分钟比 3 分钟）相比，DL 和 SRDL-DWI 均可将模拟扫描时间缩短 39%。SRDL-DWI 的图像质量评分最高，具有良好的读者间一致性（ICC 0.834；95%置信区间 0.818-0.848）。无论 b 值如何，标准和 DL-DWI 的 SNR 均优于 SRDL-DWI。SRDL-DWI 和 DL-DWI 的 ADC 值均略高于标准 DWI（分别为+0.5%和+3.4%）。对于任何 b 值，DL-/SRDL-DWI 与标准 DWI 的结构相似性均非常出色（SSIM≥0.86）。误差指标（NRMSE≤0.05，SMAPE≤0.02，LOGAC≤0.04）的计算支持低体素误差的假设。
基于深度学习的 k 空间到图像重建可将乳腺 DWI 的模拟扫描时间缩短 39%，而不会影响结构相似性。此外，超分辨率插值可显著提高主观图像质量。
4 级技术功效：1 级。
