Scholarlink

Background <p>Transarterial chemoembolization (TACE) is an effective treatment for patients with unresectable intrahepatic cholangiocarcinoma (iCCA), but tumor heterogeneity affects the efficacy of treatment. This study aimed to construct a Clinical-Radiomics (CR) model for predicting tumor response after the first TACE in patients with unresectable iCCA.</p> Methods <p>A total of 107 unresectable iCCA patients who received TACE as the first treatment with available contrast-enhanced MRI (CEMRI) were retrospectively enrolled. Patients were randomly assigned to the training (N&#xa0;=&#xa0;75) and validation cohorts (N&#xa0;=&#xa0;32) in a 7:3 ratio. Radiomics features were extracted from CEMRI (arterial, portal venous, and delayed phases) for tumor, peritumor 5&#xa0;mm, and peritumor 10&#xa0;mm, respectively, and then the features were selected by random forest before constructing the radiomics model. Radiomics model score and clinical variables were analyzed using univariate and multivariate logistic regression to construct the CR model. Kaplan–Meier method was utilized to assess OS.</p> Results <p>The radiomics model constructed based on the tumor plus peritumor 10&#xa0;mm demonstrated the best performance. The CR model developed by combining with CA19.9 showed excellent performance in both the training (AUC = 0.941) and the validation cohorts (AUC = 0.903). Dividing groups based on the model predicted tumor responses, the Kaplan–Meier curves demonstrated a significant difference in OS between the two groups (<i>P</i>&#xa0;&lt;&#xa0;0.011). The main limitations of this study include the use of a single-center cohort, which lacks external validation, and the inherent characteristics of a retrospective design, leading to an unavoidable selection bias.</p> Conclusion <p>The model in this study demonstrated excellent performance in predicting tumor response after first TACE in patients with unresectable iCCA. The model could support clinicians to make more scientific guidance on the treatment of patients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Clinical MRI-radiomics model based on support vector machine to predict the efficacy of first transarterial chemoembolization for unresectable intrahepatic cholangiocarcinoma

  • 期刊论文

  • 发表日期：

    2025年11月8日

查看全文
  • Ze Zhang,
  • Anhui Xu,
  • Yi Zhang,
  • Nan Jiang,
  • Yonghong Hao,
  • Ruibing Zhou,
  • Ketao Mu,
  • Xiaoxv Yin

摘要

Background

Transarterial chemoembolization (TACE) is an effective treatment for patients with unresectable intrahepatic cholangiocarcinoma (iCCA), but tumor heterogeneity affects the efficacy of treatment. This study aimed to construct a Clinical-Radiomics (CR) model for predicting tumor response after the first TACE in patients with unresectable iCCA.

Methods

A total of 107 unresectable iCCA patients who received TACE as the first treatment with available contrast-enhanced MRI (CEMRI) were retrospectively enrolled. Patients were randomly assigned to the training (N = 75) and validation cohorts (N = 32) in a 7:3 ratio. Radiomics features were extracted from CEMRI (arterial, portal venous, and delayed phases) for tumor, peritumor 5 mm, and peritumor 10 mm, respectively, and then the features were selected by random forest before constructing the radiomics model. Radiomics model score and clinical variables were analyzed using univariate and multivariate logistic regression to construct the CR model. Kaplan–Meier method was utilized to assess OS.

Results

The radiomics model constructed based on the tumor plus peritumor 10 mm demonstrated the best performance. The CR model developed by combining with CA19.9 showed excellent performance in both the training (AUC = 0.941) and the validation cohorts (AUC = 0.903). Dividing groups based on the model predicted tumor responses, the Kaplan–Meier curves demonstrated a significant difference in OS between the two groups (P < 0.011). The main limitations of this study include the use of a single-center cohort, which lacks external validation, and the inherent characteristics of a retrospective design, leading to an unavoidable selection bias.

Conclusion

The model in this study demonstrated excellent performance in predicting tumor response after first TACE in patients with unresectable iCCA. The model could support clinicians to make more scientific guidance on the treatment of patients.