文献速递腹部技术与安全CTMR

术前活检诊断为伴黏液成分的结直肠癌中黏液腺癌的预测

Prediction of mucinous adenocarcinoma in colorectal cancer with mucinous components detected in preoperative biopsy diagnosis.
PubMed 文献 · Abdom Radiol (NY) · 2024-12-12

本研究纳入312例术前内镜活检诊断为伴黏液成分的结直肠癌患者,按7:3随机分为训练集和验证集,提取影像组学特征构建radscore,并结合临床和血清学特征用9种机器学习算法建模。随机森林混合模型AUC最高为0.832,影像组学模型AUC为0.810,临床模型AUC为0.732,SHAP解释显示radscore和临床T分期贡献较大。该可解释预测模型可有效区分伴黏液成分的腺癌与黏液腺癌。

要点

  • 术前活检发现黏液成分后,影像组学模型有助于区分伴黏液成分的腺癌与黏液腺癌。
  • 随机森林混合模型AUC为0.832,高于影像组学模型0.810和临床模型0.732。
  • SHAP解释显示radscore和临床T分期对模型预测贡献较大。

核心结论

  • 该可解释预测模型可有效区分伴黏液成分的腺癌与黏液腺癌,有助于为术前活检发现黏液成分的患者制定治疗决策。

研究设计与样本

  • 研究为影像组学建模研究,推导队列纳入312例术前内镜活检诊断为伴黏液成分的结直肠癌患者,按7:3随机分为训练集和验证集。
  • 提取影像组学特征并进行特征工程构建radscore,结合radscore、临床数据和血清学特征共24个特征,用9种机器学习算法建模。
  • 采用SHAP方法解释机器学习模型并可视化个体变量预测。

诊断标准与关键数值

  • 影像组学模型AUC为0.810。
  • 随机森林模型表现最优,AUC最高为0.832,被定义为混合模型。
  • 临床模型(基于临床数据和血清学特征)AUC为0.732。
  • SHAP模型解释显示,在14个SHAP值非零的特征中,radscore和临床T分期的值明显较高。

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

OBJECTIVES: Endoscopic biopsy diagnosis for the preoperative assessment of mucinous components in patients with colorectal cancer is limited. This study investigated a radiomics model and established an explainable prediction model by using machine learning to differentiate between adenocarcinoma with mucinous components and mucinous adenocarcinoma.

METHODS: The derivation cohort included 312 patients with colorectal cancer with mucinous components detected during preoperative endoscopic biopsy diagnosis. These patients were randomly divided into training and validation sets in a 7:3 ratio. Radiomics features were extracted, followed by feature engineering, to create a radiomic score (radscore). Subsequently, 24 features, including the radscore, clinical data, and serological characteristics, were used to develop machine learning models by using nine different machine learning algorithms. The SHapley Additive exPlanation (SHAP) method was employed to elucidate the workings of the machine learning models and visualize individual variable predictions.

RESULTS: The radiomics model achieved an area under the curve (AUC) of 0.810. The random forest model outperformed the other models and had the highest AUC of 0.832; thus, this model was defined as the hybrid model. The clinical model, which was built using clinical data and serological characteristics, had an AUC of 0.732, whereas the radiomics model achieved an AUC of 0.810. SHAP model interpretation revealed that among the 14 features with non-zero SHAP values, the radscore and clinical T stage had notably higher values.

CONCLUSION: This interpretable predictive model effectively differentiates between adenocarcinoma with mucinous components and mucinous adenocarcinoma in patients with colorectal cancer, thereby facilitating informed treatment decisions for individuals in whom mucinous components are identified during preoperative biopsy diagnosis.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Ling T, Zuo Z, Huang M, et al. Prediction of mucinous adenocarcinoma in colorectal cancer with mucinous components detected in preoperative biopsy diagnosis. Abdom Radiol (NY). 2024. PMID: 39665990. doi:10.1007/s00261-024-04743-5

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。