文献速递腹部CT

基于深度学习的对比增强CT自动衰减测量诊断中重度肝脂肪变性

Diagnosis of moderate-to-severe hepatic steatosis using deep learning-based automated attenuation measurements on contrast-enhanced CT.
PubMed 文献 · Abdom Radiol (NY) · 2025-03-17

本回顾性研究纳入3620例肝捐赠者,利用深度学习算法在对比增强CT上自动测量肝脏和脾脏衰减值,以组织学为标准评估其诊断中重度肝脂肪变性(>33%)的效能。肝脾衰减差优于单纯肝衰减(AUC 0.868 vs. 0.821,P=0.001),深度学习测量经放射科医师校正前后无显著差异(P=0.13)。

要点

  • 肝脾衰减差诊断中重度肝脂肪变性优于单纯肝衰减(AUC 0.868 vs. 0.821,P=0.001)。
  • 深度学习自动测量经放射科医师校正分割错误前后效能无显著差异(P=0.13)。
  • 以95%敏感度为目标时,肝脾衰减差≤2.8 HU的敏感度为92.0%、特异度为48.5%。

核心结论

  • 基于深度学习的对比增强CT肝脏和脾脏衰减自动测量可可靠地检测中重度肝脂肪变性。

研究设计与样本

  • 回顾性研究纳入3620例肝捐赠者(男2393例,女1227例;平均年龄31.7±9.4岁),分为开发队列(n=2714)和测试队列(n=906),以组织学为参考标准。

关键影像表现/征象

  • 在对比增强CT上测量肝脏和脾脏的衰减值,分别采用手动测量和深度学习算法测量(放射科医师校正分割错误前后)。
  • 深度学习测量与手动测量在诊断中重度肝脂肪变性时,肝脾衰减差均优于单纯肝衰减。

诊断标准与关键数值

  • 中重度肝脂肪变性定义为组织学脂肪含量>33%。
  • 测试队列中,以95%敏感度为目标的标准(肝脾衰减差≤2.8 HU)敏感度为92.0%(69/75),特异度为48.5%(403/831)。
  • 以95%特异度为目标的标准(肝脾衰减差≤-18.8 HU)敏感度为53.3%(40/75),特异度为95.7%(795/831)。
  • 以最大约登指数为目标的标准(肝脾衰减差≤-8.2 HU)敏感度为82.7%(62/75),特异度为80.7%(671/831)。
  • 深度学习测量诊断中重度肝脂肪变性的AUC为0.868(肝脾衰减差)vs. 0.821(单纯肝衰减),P=0.001;手动测量AUC为0.871 vs. 0.823,P=0.001。

临床应用与阅片要点

  • 在对比增强CT阅片和报告中,可考虑使用深度学习自动测量肝脏和脾脏衰减值来辅助诊断中重度肝脂肪变性。
  • 肝脾衰减差较单纯肝衰减可能提供更好的诊断效能。
  • 深度学习自动测量结果似乎无需放射科医师常规校正分割错误即可保持诊断效能。

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

PURPOSE: To evaluate the utility of deep learning-based automated attenuation measurements on contrast-enhanced CT (CECT) for diagnosing moderate-to-severe hepatic steatosis (HS), using histology as reference standard.

METHODS: This retrospective study included 3,620 liver donors (2,393 men and 1,227 women; mean age, 31.7 ± 9.4 years), divided into the development (n = 2,714) and test (n = 906) cohorts. Attenuation values of the liver and spleen on CECT were measured both manually and using a deep learning algorithm (before and after radiologists' correction of segmentation errors). Performance of: (1) liver attenuation and (2) liver-spleen attenuation difference for diagnosing moderate-to-severe HS (> 33%) was assessed using the area under the receiver operating characteristic curve (AUC). Three different criteria targeting 95% sensitivity, 95% specificity, and the maximum Youden's index, respectively, for diagnosing moderate-to-severe HS, were developed and validated.

RESULTS: The performance of deep learning-based measurements did not differ significantly, with or without radiologists' corrections (p = 0.13). Liver-spleen attenuation difference outperformed liver attenuation alone in diagnosing moderate-to-severe HS in both deep learning-based (AUC, 0.868 vs. 0.821; p = 0.001) and manual (AUC, 0.871 vs. 0.823; p = 0.001) measurements. In the test cohort, the criterion targeting 95% sensitivity for diagnosing moderate-to-severe HS (liver-spleen attenuation difference ≤ 2.8 HU) yielded 92.0% (69/75) sensitivity and 48.5% (403/831) specificity. The criterion targeting 95% specificity (liver-spleen attenuation difference ≤ -18.8 HU) yielded 53.3% (40/75) sensitivity and 95.7% (795/831) specificity. The criterion targeting the maximum Youden's index (liver-spleen attenuation difference ≤ -8.2 HU) yielded 82.7% (62/75) sensitivity and 80.7% (671/831) specificity.

CONCLUSION: Deep learning-based automated measurements of liver and spleen attenuation on CECT can be used reliably to detect moderate-to-severe HS.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Kim HY, Lee KJ, Lee SS, et al. Diagnosis of moderate-to-severe hepatic steatosis using deep learning-based automated attenuation measurements on contrast-enhanced CT. Abdom Radiol (NY). 2025. PMID: 40095018. doi:10.1007/s00261-025-04872-5

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。