Olthof Susann-Cathrin, Weiland Elisabeth, Benkert Thomas, Wessling Daniel, Leyhr Daniel, Afat Saif, Nikolaou Konstantin, Preibsch Heike
Department of Diagnostic and Interventional Radiology, University Hospital of Tuebingen, 72076 Tuebingen, Germany.
MR Application Predevelopment, Siemens Healthineers AG, 91052 Erlangen, Germany.
Diagnostics (Basel). 2024 Aug 10;14(16):1742. doi: 10.3390/diagnostics14161742.
The objective of this study was to evaluate a high-resolution deep-learning (DL)-based diffusion-weighted imaging (DWI) sequence for breast magnetic resonance imaging (MRI) in comparison to a standard DWI sequence (DWI) at 1.5 T. It is a prospective study of 38 breast cancer patients, who were scanned with DWI and DWI. Both DWI sequences were scored for image quality, sharpness, artifacts, contrast, noise, and diagnostic confidence with a Likert-scale from 1 (non-diagnostic) to 5 (excellent). The lesion diameter was evaluated on b 800 DWI, apparent diffusion coefficient (ADC), and the second subtraction (SUB) of the contrast-enhanced T1 VIBE. SNR was also calculated. Statistics included correlation analyses and paired -tests. High-resolution DWI offered significantly superior image quality, sharpness, noise, contrast, and diagnostic confidence (each < 0.02)). Artifacts were significantly higher in DWI by one reader (M = 4.62 vs. 4.36 Likert scale, < 0.01) without affecting the diagnostic confidence. SNR was higher in DWI for b 50 and ADC maps (each = 0.07). Acquisition time was reduced by 22% in DWI. The lesion diameters in DWI b 800 and and ADC and were respectively 6% lower compared to the 2nd SUB. A DL-based diffusion sequence at 1.5 T in breast MRI offers a higher resolution and a faster acquisition, including only minimally more artefacts without affecting the diagnostic confidence.
本研究的目的是评估一种基于高分辨率深度学习（DL）的扩散加权成像（DWI）序列用于1.5T乳腺磁共振成像（MRI），并与标准DWI序列（DWI）进行比较。这是一项对38例乳腺癌患者的前瞻性研究，这些患者接受了DWI和DWI扫描。对两个DWI序列的图像质量、清晰度、伪影、对比度、噪声和诊断置信度进行评分，采用李克特量表，从1（非诊断性）到5（优秀）。在b 800 DWI、表观扩散系数（ADC）和对比增强T1 VIBE的第二次减法（SUB）上评估病变直径。还计算了信噪比。统计分析包括相关性分析和配对检验。高分辨率DWI在图像质量、清晰度、噪声、对比度和诊断置信度方面具有显著优势（均P<0.02）。一位读者认为DWI中的伪影明显更高（李克特量表：M = 4.62对4.36，P<0.01），但不影响诊断置信度。在b 50和ADC图中，DWI的信噪比更高（均P = 0.07）。DWI的采集时间减少了22%。与第二次SUB相比，DWI b 800中的病变直径以及ADC和分别降低了6%。1.5T乳腺MRI中基于DL的扩散序列提供了更高的分辨率和更快的采集速度，仅产生略微更多的伪影，且不影响诊断置信度。
