文献速递腹部MR

MRI全肝自动分割量化肝脂肪变的诊断性能

Automated MRI Liver Segmentation For Accurate Quantification Of Hepatic Steatosis.
PubMed 文献 · Acad Radiol · 2026-07-15

本研究在538例接受MRI-PDFF检查的成人中开发并验证了一种VBB-Net全肝分割模型,以肝活检组织学脂肪变分级(S0-S3)为参考标准。结果显示AI全肝分割PDFF与手动ROI-PDFF高度一致,对各级肝脂肪变具有较高诊断效能。

要点

  • AI全肝分割PDFF与手动ROI-PDFF一致性极佳,差异均值仅-0.06%
  • 该模型对S0-S3各级脂肪变的AUROC均超过0.92,诊断效能较高
  • 文中提出的截断值仅为探索性,临床使用前需进一步验证

核心结论

  • AI-WLS-PDFF模型对组织学肝脂肪变分级具有较高诊断效能,并与手动ROI-PDFF高度一致,可作为MASLD患者全肝PDFF自动量化的潜在方法

研究设计与样本

  • 研究类型为开发与验证研究,共纳入538例接受MRI-PDFF检查的成人
  • 训练队列含372例患者(418次检查),用于开发VBB-Net分割模型
  • 验证队列为166例因疑诊代谢相关脂肪性肝病而接受肝活检的连续成人
  • 参考标准为肝活检组织学脂肪变分级(S0-S3)

诊断标准与关键数值

  • 训练队列平均Dice系数为0.94±0.05,验证队列为0.93±0.04
  • AI-WLS-PDFF误差范围为0.794%,ROI-PDFF误差范围为0.821%
  • AI-WLS-PDFF诊断S0-S3的AUROC(95%CI)分别为0.995(0.989-1.000)、0.951(0.921-0.980)、0.928(0.888-0.968)
  • AI-WLS-PDFF与ROI-PDFF的ICC为0.996(95%CI:0.995-0.997),平均差异为-0.06%,95%一致性界限为-1.59%至1.47%

临床应用与阅片要点

  • AI全肝分割PDFF可替代手动ROI法进行全肝脂肪定量,减少操作者依赖性
  • 该自动方法在保持与手动法高度一致的同时具有较低的误差范围,适合临床常规使用
  • 应用于MASLD疑诊患者时,可依据组织学分级对应AUROC判断不同级别脂肪变的诊断把握度

局限性

  • 文中提出的截断值应视为探索性结果,需要进一步验证

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

RATIONALE AND OBJECTIVES: MRI-proton density fat fraction (MRI-PDFF) is widely applied in clinical practice for hepatic fat quantification. However, the conventional manual region of interest (ROI) method is time-consuming and operator-dependent, and the diagnostic accuracy of artificial intelligence (AI)-based models for hepatic steatosis assessment remains to be fully clarified. This study aimed to evaluate the diagnostic performance of an AI-based whole liver segmentation (WLS) model for histological hepatic steatosis grading, and to technically validate its segmentation performance and agreement with manual ROI-based PDFF measurement.

MATERIALS AND METHODS: A total of 538 adults who underwent MRI-PDFF examinations were enrolled. A VBB-Net segmentation model was developed in a training cohort of 372 patients (418 examinations). Validation was performed in a consecutive cohort of 166 adults who underwent liver biopsy for suspected metabolic dysfunction-associated steatotic liver disease (MASLD). Histological steatosis grading (S0-S3) was used as the reference standard.

RESULTS: The mean Dice coefficients were 0.94 ± 0.05 in the training cohort and 0.93 ± 0.04 in the validation cohort. Margins of error were 0.794% for AI-WLS-PDFF and 0.821% for ROI-PDFF. The AUROCs (95% CI) of AI-WLS-PDFF for diagnosing S0-S3 were 0.995 (95% CI: 0.989, 1.000), 0.951 (95% CI: 0.921, 0.980), and 0.928 (95% CI: 0.888, 0.968), respectively. AI-WLS-PDFF showed excellent agreement with ROI-PDFF (ICC, 0.996; 95% CI: 0.995, 0.997) with minimal bias (mean difference, -0.06%; 95% agreement limits: -1.59% to 1.47%).

CONCLUSION: The AI-WLS-PDFF model showed high diagnostic performance for histological steatosis grading and excellent agreement with manual ROI-PDFF, supporting its potential as an automated approach for whole-liver PDFF quantification in patients with MASLD. The proposed cutoff values should be considered exploratory and require further validation.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wei, Qi, Chen, et al. Automated MRI Liver Segmentation For Accurate Quantification Of Hepatic Steatosis. Acad Radiol. 2026. PMID: 42457498. doi:10.1016/j.acra.2026.06.036

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。