文献速递腹部技术与安全MR

使用深度学习自动进行肝脏磁共振弹性成像质量控制和肝脏硬度测量

Automated liver magnetic resonance elastography quality control and liver stiffness measurement using deep learning.
PubMed 文献 · Abdom Radiol (NY) · 2025-03-15

本研究为回顾性单中心研究,纳入69例患者的146次二维磁共振弹性成像扫描,采用基于SqueezeNet的二分类质量控制模型和二维U-Net分割模型实现质控与肝脏硬度测量自动化。最佳质控模型准确率0.958、精确率0.982、召回率0.886;深度学习辅助法与参考标准的平均肝脏硬度测量误差为1.9%±4.6%,测量29个诊断切片耗时不到1秒,而人工需20分钟。

要点

  • 基于SqueezeNet的质控模型仅用MRE幅度图即达准确率0.958、精确率0.982、召回率0.886。
  • 深度学习辅助肝脏硬度测量与观察者参考标准的平均误差为1.9%±4.6%。
  • 深度学习辅助完成29个诊断切片硬度测量不到1秒,人工需20分钟。

核心结论

  • 基于深度学习的肝脏MRE诊断质量分类、肝脏分割和肝脏硬度测量方法表现出有前景的高性能,具有临床采用的潜力。

研究设计与样本

  • 回顾性、单中心、经IRB批准的人体研究,数据集包含69例患者(37例男性,平均年龄51.6岁)的146次二维MRE扫描的897个幅度切片,采用1.5 T和3 T MRI、二维梯度回波和二维自旋回波-回波平面成像序列;由三名独立观察者将MRE幅度图像标注为0(非诊断质量)或1(诊断质量)作为参考标准。

诊断标准与关键数值

  • 最佳质控集成模型(仅使用MRE幅度图)的准确率为0.958、精确率为0.982、召回率为0.886;深度学习辅助法与参考标准之间的平均肝脏硬度测量误差为1.9%±4.6%。

临床应用与阅片要点

  • 深度学习辅助法完成29个诊断切片的肝脏硬度测量不到1秒,而人工测量需20分钟;作者认为该方法表现出有前景的高性能,具有临床采用的潜力。

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

PURPOSE: Magnetic resonance elastography (MRE) measures liver stiffness for fibrosis staging, but its utility can be hindered by quality control (QC) challenges and measurement variability. The objective of the study was to fully automate liver MRE QC and liver stiffness measurement (LSM) using a deep learning (DL) method.

METHODS: In this retrospective, single center, IRB-approved human study, a curated dataset involved 897 MRE magnitude slices from 146 2D MRE scans [1.5 T and 3 T MRI, 2D Gradient Echo (GRE), and 2D Spin Echo-Echo Planar Imaging (SE-EPI)] of 69 patients (37 males, mean age 51.6 years). A SqueezeNet-based binary QC model was trained using combined and individual inputs of MRE magnitude slices and their 2D Fast-Fourier transforms to detect artifacts from patient motion, aliasing, and blurring. Three independent observers labeled MRE magnitude images as 0 (non-diagnostic quality) or 1 (diagnostic quality) to create a reference standard. A 2D U-Net segmentation model was trained on diagnostic slices with liver masks to support LSM. Intersection over union between the predicted segmentation and confidence masks identified measurable areas for LSM on elastograms. Cohen's unweighted Kappa coefficient, mean LSM error (%), and intra-class correlation coefficient were calculated to compare the DL-assisted approach with the observers' annotations. An efficiency analysis compared the DL-assisted vs manual LSM durations.

RESULTS: The top QC ensemble model (using MRE magnitude alone) achieved accuracy, precision, and recall of 0.958, 0.982, and 0.886, respectively. The mean LSM error between the DL-assisted approach and the reference standard was 1.9% ± 4.6%. DL-assisted approach completed LSM for 29 diagnostic slices in under 1 s, compared to 20 min manually.

CONCLUSION: An automated DL-based classification of liver MRE diagnostic quality, liver segmentation, and LSM approach demonstrates a promising high performance, with potential for clinical adoption.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Ozkaya E, Nieves-Vazquez HA, Yuce M, et al. Automated liver magnetic resonance elastography quality control and liver stiffness measurement using deep learning. Abdom Radiol (NY). 2025. PMID: 40088296. doi:10.1007/s00261-025-04883-2

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。