基于临床-影像组学模型术前预测结直肠癌BRAF突变状态
本研究回顾性纳入140例结直肠癌患者,基于CT影像特征构建影像组学标签,并结合临床危险因素建立临床-影像组学模型,用于术前预测BRAF突变状态。影像组学标签在训练集和验证集的AUC分别为0.93和0.87,联合模型AUC提升至0.95和0.88,预测准确率高于临床模型(0.70至0.89)。
要点
- 基于5个CT影像组学特征构建的radscore可预测结直肠癌BRAF突变,训练集AUC 0.93、验证集AUC 0.87。
- 联合radscore与临床危险因素的列线图模型诊断效能更优,训练集AUC 0.95、验证集AUC 0.88。
- 联合模型预测准确率高于临床模型,范围为0.70至0.89。
核心结论
- 基于CT的影像组学标签与结直肠癌BRAF突变相关,联合临床危险因素的模型可能用于术前个体化预测BRAF突变状态。
研究设计与样本
- 回顾性研究,纳入140例结直肠癌患者,基于肿瘤病灶CT影像特征采用最小绝对收缩和选择算子算法构建影像组学标签,应用逐步逻辑回归筛选变量建立临床-影像组学模型,通过受试者工作特征曲线、校准曲线和决策曲线分析评估预测性能。
诊断标准与关键数值
- radscore由5个所选影像组学特征生成,预测BRAF突变的AUC在训练集为0.93、验证集为0.87。
- 联合radscore与临床危险因素的列线图模型AUC在训练集为0.95、验证集为0.88。
- 联合模型预测BRAF突变的准确率高于临床模型,范围为0.70至0.89。
临床应用与阅片要点
- 作者认为,基于CT的影像组学标签对结直肠癌BRAF状态显示出满意的诊断意义,联合临床模型可能应用于术前个体化预测BRAF突变。
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
RATIONALE AND OBJECTIVES: This study aimed to develop a clinically practical model to predict V-raf murine sarcoma viral oncogene homolog B1 (BRAF) mutation in colorectal cancer according to radiomic signatures based on computed tomography (CT) and clinical risk factors, and to determine the model's diagnostic accuracy for BRAF mutation status.
MATERIALS AND METHODS: This retrospective study included 140 patients with colorectal cancer. The significant clinical risk factors were used to build the clinical model; the least absolute shrinkage and selection operator algorithm was adopted to construct a radiomics signature according to imaging features of the tumor lesion, and stepwise logistic regression was applied to select the significant variables to develop the clinical-radiomics model. The predictive performance was evaluated by receiver operating characteristic curve analysis, calibration curve analysis, and decision curve analysis.
RESULTS: The radscore, generated by 5 selected radiomics features, demonstrated a favorable ability to predict BRAF mutation in both the training (area under the receiver operating characteristic curve [AUC] 0.93) and validation (AUC 0.87) cohorts. Subsequently, integrating two independent predictors (including the radscore and clinical risk factors) into a nomogram exhibited more favorable discriminatory performance, with the AUC improved to 0.95 and 0.88 in both cohorts. Moreover, the accuracy for predicting BRAF mutations was higher than that of the clinical model, ranging from 0.70 to 0.89.
CONCLUSION: The proposed CT-based radiomics signature is associated with BRAF mutations. The present study also proposes a combined model can potentially be applied in the individual preoperative prediction of BRAF mutation status in colorectal cancer.
ADVANCES IN KNOWLEDGE: CT-based radiomics showed satisfactory diagnostic significance for the BRAF status in colorectal cancer, the clinical-combined model may be applied in the individual preoperative prediction of BRAF mutation.
引用
- Xue, Peng, Chen, et al. Preoperative Prediction of BRAF Mutation Status in Colorectal Cancer Using a Clinical-radiomics Model. Acad Radiol. 2022. PMID: 35033450. doi:10.1016/j.acra.2021.12.016
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。