文献速递腹部CT

基于影像组学的自动化机器学习在平扫CT上鉴别局灶性肝脏病变

Radiomics-based automated machine learning for differentiating focal liver lesions on unenhanced computed tomography.
PubMed 文献 · Abdom Radiol (NY) · 2024-11-22

本研究纳入2个医学中心2017年1月至2023年3月间行CT检查的260例患者(肝癌60例、肝血管瘤93例、肝脓肿48例、肝囊肿84例),利用Pyradiomics从平扫CT提取影像组学特征,通过MLJAR自动化机器学习框架构建临床、影像组学及融合模型。外部测试集中融合模型对肝囊肿、血管瘤、脓肿和恶性肿瘤的AUC分别为1.00、0.97、0.92和0.93,作者认为基于平扫CT无创影像组学与临床特征的融合模型对鉴别局灶性肝脏病变有较高临床价值。

要点

  • 外部测试集融合模型AUC:肝囊肿1.00、血管瘤0.97、肝脓肿0.92、恶性肿瘤0.93。
  • 外部测试集影像组学模型AUC:肝囊肿1.00、血管瘤0.90、肝脓肿0.98、恶性肿瘤0.80。
  • 外部测试集临床模型对恶性肿瘤AUC仅0.23,融合影像组学后升至0.93。

核心结论

  • 基于平扫CT无创影像组学与临床特征的融合模型对鉴别局灶性肝脏病变有较高临床价值。

研究设计与样本

  • 研究纳入2个医学中心2017年1月至2023年3月行CT检查的260例患者,包括肝癌60例、肝血管瘤93例、肝脓肿48例、肝囊肿84例;采用Pyradiomics提取平扫CT影像组学特征,通过MLJAR自动化机器学习框架构建临床、影像组学及融合模型。

诊断标准与关键数值

  • 外部测试集融合模型AUC:肝囊肿1.00、肝血管瘤0.97、肝脓肿0.92、肝恶性肿瘤0.93。
  • 外部测试集影像组学模型AUC:肝囊肿1.00、肝血管瘤0.90、肝脓肿0.98、肝恶性肿瘤0.80。
  • 外部测试集临床模型AUC:肝囊肿0.88、肝血管瘤0.81、肝脓肿0.89、肝恶性肿瘤0.23。
  • 训练集和验证集中临床、影像组学及融合模型AUC均超过0.900。
  • 外部测试集放射科医师诊断准确率:肝囊肿0.96、肝血管瘤0.60、肝恶性肿瘤0.79、肝脓肿0.66。

临床应用与阅片要点

  • 作者认为基于平扫CT无创影像组学与临床特征的融合模型对鉴别局灶性肝脏病变有较高临床价值。

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

BACKGROUND & AIMS: Enhanced computed tomography (CT) is the primary method for focal liver lesion diagnosis. We aimed to use automated machine learning (AutoML) algorithms to differentiate between benign and malignant focal liver lesions on the basis of radiomics from unenhanced CT images.

METHODS: We enrolled 260 patients from 2 medical centers who underwent CT examinations between January 2017 and March 2023. This included 60 cases of hepatic malignancies, 93 cases of hepatic hemangiomas, 48 cases of hepatic abscesses, and 84 cases of hepatic cysts. The Pyradiomics method was used to extract radiomics features from unenhanced CT images. By using the mljar-supervised (MLJAR) AutoML framework, clinical, radiomics, and fusion models combining clinical and radiomics features were established.

RESULTS: In the training and validation sets, the area under the curve (AUC) values for the clinical, radiomics, and fusion models exceeded 0.900. In the external testing set, the respective AUC values for the clinical, radiomics, and fusion models were as follows: 0.88, 1.00, and 1.00 for hepatic cysts; 0.81, 0.90, and 0.97 for hepatic hemangiomas; 0.89, 0.98, and 0.92 for hepatic abscesses; and 0.23, 0.80, and 0.93 for hepatic malignancies. The diagnostic accuracy rates for hepatic cysts, hemangiomas, malignancies, and abscesses by radiologists in the external testing cohort were 0.96, 0.60, 0.79, and 0.66, respectively.

CONCLUSION: The fusion model based on noninvasive radiomics and clinical features of unenhanced CT images has high clinical value for distinguishing focal hepatic lesions.

The preoperative diagnosis of focal liver lesions is essential for choosing appropriate treatment. Thus, we aimed to use the MLJAR AutoML framework to differentiate benign and malignant focal liver lesions on the basis of radiomics from unenhanced CT images.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Yang N, Ma Z, Zhang L, et al. Radiomics-based automated machine learning for differentiating focal liver lesions on unenhanced computed tomography. Abdom Radiol (NY). 2024. PMID: 39572431. doi:10.1007/s00261-024-04685-y

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。