文献速递腹部MR

基于钆增强MRI的深度学习三维超分辨率影像组学模型用于改善肝细胞癌病理分级术前预测

Deep learning 3D super-resolution radiomics model based on Gd-enhanced MRI for improving preoperative prediction of HCC pathological grading.
PubMed 文献 · Abdom Radiol (NY) · 2025-07-08

本研究纳入197例肝细胞癌患者(训练队列157例、测试队列40例),利用深度学习三维超分辨率技术从常规分辨率肝胆期图像生成超分辨率图像并提取影像组学特征建模。结果显示,基于超分辨率图像的二分类模型在区分中低分化与高分化肝细胞癌时AUC为0.849,优于常规分辨率图像的AUC 0.603(P=0.039)。作者认为该技术可能改善基于肝胆期图像的影像组学模型对肝细胞癌术前病理分级的预测性能。

要点

  • 基于超分辨率肝胆期图像的影像组学模型在预测肝细胞癌病理分级上可能优于常规分辨率图像。
  • 二分类模型(高分化 vs 中低分化)超分辨率图像AUC 0.849,常规分辨率图像AUC 0.603(P=0.039)。
  • 决策曲线分析提示模型具有临床价值。

核心结论

  • 基于深度学习的三维超分辨率技术可能改善利用肝胆期图像的影像组学模型对肝细胞癌术前病理分级的预测性能。

研究设计与样本

  • 回顾性纳入197例肝细胞癌患者,分为训练队列157例和测试队列40例。
  • 采用基于深度学习的三维超分辨率技术从常规分辨率肝胆期图像生成超分辨率肝胆期图像。
  • 在常规分辨率与超分辨率肝胆期图像的手工分割感兴趣体积中提取高维定量特征。
  • 使用梯度提升、轻量梯度提升机和支撑向量机开发三分类(高分化 vs 中分化 vs 低分化)及二分类(高分化 vs 中分化与低分化)影像组学模型。

诊断标准与关键数值

  • 二分类模型(高分化 vs 中分化与低分化):超分辨率图像AUC=0.849、敏感度=77.8%、特异度=76.9%、准确率=77.5%;常规分辨率图像AUC=0.603、敏感度=48.1%、特异度=76.9%、准确率=57.5%;P=0.039。
  • 三分类模型:所有基于超分辨率图像的三分类模型AUC值均高于基于常规分辨率图像的模型。

临床应用与阅片要点

  • 作者认为基于深度学习的三维超分辨率技术可能改善利用肝胆期图像的影像组学模型对肝细胞癌术前病理分级的预测性能。

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: The histological grade of hepatocellular carcinoma (HCC) is an important factor associated with early tumor recurrence and prognosis after surgery. Developing a valuable tool to assess this grade is essential for treatment. This study aimed to evaluate the feasibility and efficacy of a deep learning-based three-dimensional super-resolution (SR) magnetic resonance imaging radiomics model for predicting the pathological grade of HCC.

METHODS: A total of 197 HCC patients were included and divided into a training cohort (n = 157) and a testing cohort (n = 40). Three-dimensional SR technology based on deep learning was used to obtain SR hepatobiliary phase (HBP) images from normal-resolution (NR) HBP images. High-dimensional quantitative features were extracted from manually segmented volumes of interest in NRHBP and SRHBP images. The gradient boosting, light gradient boosting machine, and support vector machine were used to develop three-class (well-differentiated vs. moderately differentiated vs. poorly differentiated) and binary radiomics (well-differentiated vs. moderately and poorly differentiated) models, and the predictive performance of these models was evaluated using several measures.

RESULTS: All the three-class models using SRHBP images had higher area under the curve (AUC) values than those using NRHBP images. The binary classification models developed with SRHBP images also outperformed those with NRHBP images in distinguishing moderately and poorly differentiated HCC from well-differentiated HCC (AUC = 0.849, sensitivity = 77.8%, specificity = 76.9%, accuracy = 77.5% vs. AUC = 0.603, sensitivity = 48.1%, specificity = 76.9%, accuracy = 57.5%; p = 0.039). Decision curve analysis revealed the clinical value of the models.

CONCLUSIONS: Deep learning-based three-dimensional SR technology may improve the performance of radiomics models using HBP images for predicting the preoperative pathological grade of HCC.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Jia F, Wu B, Wang Z, et al. Deep learning 3D super-resolution radiomics model based on Gd-enhanced MRI for improving preoperative prediction of HCC pathological grading. Abdom Radiol (NY). 2025. PMID: 40627133. doi:10.1007/s00261-025-05085-6

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。