文献速递神经技术与安全MR

深度学习加速脑扩散加权MRI联合超分辨率处理

Deep Learning Accelerated Brain Diffusion-Weighted MRI with Super Resolution Processing.
PubMed 文献 · Acad Radiol · 2024-03-22

前瞻性纳入85例临床需行3T MRI的患者,比较传统四平均DWI与深度学习DWI(含单/双平均及超分辨率重建)的图像质量和诊断信心;DL-DWI在所有参数上显著优于传统DWI,单平均DL-DWI图像质量最佳且信号强度无显著差异,超快速DWI可行。

要点

  • DL-DWI在总体图像质量、对比度、诊断信心及伪影评估上均显著优于传统DWI(P<0.001)。
  • 单平均DL-DWI图像质量最佳,80.9%为很好、14.5%为极好,传统MRI仅12.5%很好、0%极好。
  • 基底节和中央区信号强度在DL-DWI与传统DWI间无显著差异。

核心结论

  • 超分辨率深度学习扩散加权成像可行,在提高诊断图像质量的同时实现脑部高度加速成像。

研究设计与样本

  • 前瞻性研究,纳入85例连续临床需行3T MRI扫描的患者;传统DWI采用四平均采集,并重建一平均、二平均及深度学习DWI(DL-DWI);由三名经验丰富的阅片者采用5级Likert量表评估。

关键影像表现/征象

  • 35例患者检出颅内病变。
  • DL-DWI在所有定义参数上显著优于传统DWI,且不依赖于所用平均次数(P<0.001)。
  • 单平均DL-DWI图像质量最佳(P<0.001),几乎全部病例达很好(80.9%)至极好(14.5%),传统MRI为很好12.5%、极好0%(P<0.001)。
  • 诊断信心结果与图像质量相当。
  • 基底节和中央区信号强度值无显著差异。

诊断标准与关键数值

  • 图像质量采用5级Likert量表评估,评估参数包括总体图像质量、总体对比度、诊断信心、伪影发生及中央区、基底节、脑干和小脑的评估。
  • 阅片者间一致性采用Fleiss kappa(ϰ)评估,几乎所有定义参数达中等至相当一致,病变评估一致性良好(p=0.74)。

临床应用与阅片要点

  • DL-DWI在单平均采集下即可获得最佳图像质量,提示可用于超快速脑扩散加权成像。
  • DL-DWI在基底节和中央区信号强度与传统DWI无显著差异,阅片时信号解读可参照传统DWI。
  • 阅片者间对病变评估一致性良好(p=0.74),支持DL-DWI用于病变检出。

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

OBJECTIVES: To investigate the clinical feasibility and image quality of accelerated brain diffusion-weighted imaging (DWI) with deep learning image reconstruction and super resolution.

METHODS: 85 consecutive patients with clinically indicated MRI at a 3 T scanner were prospectively included. Conventional diffusion-weighted data (c-DWI) with four averages were obtained. Reconstructions of one and two averages, as well as deep learning diffusion-weighted imaging (DL-DWI), were accomplished. Three experienced readers evaluated the acquired data using a 5-point Likert scale regarding overall image quality, overall contrast, diagnostic confidence, occurrence of artefacts and evaluation of the central region, basal ganglia, brainstem, and cerebellum. To assess interrater agreement, Fleiss' kappa (ϰ) was determined. Signal intensity (SI) levels for basal ganglia and the central region were estimated via automated segmentation, and SI values of detected pathologies were measured.

RESULTS: Intracranial pathologies were identified in 35 patients. DL-DWI was significantly superior for all defined parameters, independently from applied averages (p-value <0.001). Optimum image quality was achieved with DL-DWI by utilizing a single average (p-value <0.001), demonstrating very good (80.9%) to excellent image quality (14.5%) in nearly all cases, compared to 12.5% with very good and 0% with excellent image quality for c-MRI (p-value <0.001). Comparable results could be shown for diagnostic confidence. Inter-rater Fleiss' Kappa demonstrated moderate to substantial agreement for virtually all defined parameters, with good accordance, particularly for the assessment of pathologies (p = 0.74). Regarding SI values, no significant difference was found.

CONCLUSION: Ultra-fast diffusion-weighted imaging with super resolution is feasible, resulting in highly accelerated brain imaging while increasing diagnostic image quality.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Altmann S, Grauhan NF, Mercado MAA, et al. Deep Learning Accelerated Brain Diffusion-Weighted MRI with Super Resolution Processing. Acad Radiol. 2024. PMID: 38521612. doi:10.1016/j.acra.2024.02.049

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。