从更快帧到完美聚焦:深度学习HASTE在腹部手术后单序列MRI中的应用
回顾性分析76例腹部手术后疑似感染灶行3-T MRI的患者,比较深度学习加速HASTE(HASTE-DL)与常规HASTE序列。HASTE-DL扫描时间缩短46%,整体图像质量、对比度、锐利度及关键结构显示均显著提高(p<0.001),积液检出读者间一致性极佳(κ=0.960),作者认为其可作为标准HASTE的有效替代及术后影像流程的补充工具。
要点
- HASTE-DL较常规HASTE扫描时间缩短46%,图像质量、对比度、锐利度均显著提高(p<0.001)。
- HASTE-DL对积液检出与表征评分更高,读者间一致性极佳(κ=0.960),积液检出完全一致(κ=1.0)。
- HASTE-DL对引流管、血管、胆管及胰管等关键结构显示显著增强(p<0.001),两序列均未见相关伪影。
核心结论
- HASTE-DL图像质量更优、关键结构显示更好且采集时间缩短,是标准HASTE序列的有效替代,并有望成为术后影像工作流程的补充工具。
研究设计与样本
- 回顾性分析76例腹部手术后疑似感染灶行3-T MRI的患者(平均年龄65±11.69岁),比较HASTE-DL与常规HASTE序列的图像质量、对比度、锐利度、伪影、积液检出及关键结构显示。
关键影像表现/征象
- HASTE-DL整体图像质量、对比度及锐利度均显著优于常规HASTE(p<0.001)。
- HASTE-DL积液检出与表征评分高于常规HASTE,关键结构(引流管、血管、胆管及胰管)显示显著增强(p<0.001)。
- 两序列均未观察到相关伪影。
诊断标准与关键数值
- HASTE-DL读者间一致性极佳(κ=0.960),整体图像质量与积液检出完全一致(κ=1.0)。
- HASTE-DL较常规HASTE扫描时间缩短46%。
临床应用与阅片要点
- 作者认为HASTE-DL可作为标准HASTE序列的有效替代,并作为术后影像工作流程中有前景的补充工具。
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
BACKGROUND: This study evaluates the feasibility of a novel deep learning-accelerated half-fourier single-shot turbo spin-echo sequence (HASTE-DL) compared to the conventional HASTE sequence (HASTES) in postoperative single-sequence MRI for the detection of fluid collections following abdominal surgery. As small fluid collections are difficult to visualize using other techniques, HASTE-DL may offer particular advantages in this clinical context.
MATERIALS AND METHODS: A retrospective analysis was conducted on 76 patients (mean age 65±11.69 years) who underwent abdominal MRI for suspected septic foci following abdominal surgery. Imaging was performed using 3-T MRI scanners, and both sequences were analyzed in terms of image quality, contrast, sharpness, and artifact presence. Quantitative assessments focused on fluid collection detectability, while qualitative assessments evaluated visualization of critical structures. Inter-reader agreement was measured using Cohen's kappa coefficient, and statistical significance was determined with the Mann-Whitney U test.
RESULTS: HASTE-DL achieved a 46% reduction in scan time compared to HASTES, while significantly improving overall image quality (p<0.001), contrast (p<0.001), and sharpness (p<0.001). The inter-reader agreement for HASTE-DL was excellent (κ=0.960), with perfect agreement on overall image quality and fluid collection detection (κ=1.0). Fluid detectability and characterization scores were higher for HASTE-DL, and visualization of critical structures was significantly enhanced (p<0.001). No relevant artifacts were observed in either sequence.
CONCLUSION: HASTE-DL offers superior image quality, improved visualization of critical structures, such as drainages, vessels, bile and pancreatic ducts, and reduced acquisition time, making it an effective alternative to the standard HASTE sequence, and a promising complementary tool in the postoperative imaging workflow.
引用
- Hosse C, Fehrenbach U, Pivetta F, et al. From Faster Frames to Flawless Focus: Deep Learning HASTE in Postoperative Single Sequence MRI. Acad Radiol. 2025. PMID: 40562676. doi:10.1016/j.acra.2025.05.039
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。