Introduction:Recurrence after pelvic exenteration remains a significant concern in patients with locally advanced rectal cancer (LARC). Therefore, there is a need for improved non-invasive predictive tools to aid in patient selection. Radiomics, which extracts quantitative imaging features, may help identify patients at greater risk of recurrence. This study aimed to develop and validate a radiomics-based nomogram using pre-treatment MRI to predict postoperative recurrence risk in LARC.Methods:The largest multicenter retrospective radiomics analysis of 191 patients with pathologically confirmed LARC treated at fourteen centres (2016–2018) was performed. All patients received neoadjuvant chemoradiotherapy followed by curative-intent exenterative surgery. Manual tumour segmentation was performed on pre-treatment T2-weighted MRI. Feature selection employed LASSO regression with 5-fold cross-validation across 1000 bootstrap samples. The most frequently selected features were used to construct a logistic regression model via stepwise backward selection. Model performance was assessed using ROC analysis, calibration plots, decision curve analysis, and internal validation with 1000 bootstraps. A nomogram was generated to enable individualized recurrence risk estimation.Results:Postoperative recurrence occurred in 51% (n= 98) of cases. Five radiomic features reflecting tumour heterogeneity, morphology, and texture were included in the final model. In multivariable analysis, all selected features were significantly associated with recurrence, with odds ratios ranging from 0.63 to 1.64. The model achieved an optimism-adjusted AUC of 0.70, indicating fair discrimination. Calibration plots showed good agreement between predicted and observed recurrence probabilities. Decision curve analysis confirmed clinical utility across relevant thresholds. A clinically interpretable nomogram was developed based on the final model.Conclusions:A radiomics-based model using preoperative MRI can predict recurrence in LARC. The derived nomogram provides a practical tool for preoperative risk assessment. Prospective validation is necessary.
引言：对于局部进展期直肠癌（LARC）患者，盆腔廓清术后的复发仍是重要临床问题。因此，需要改进无创预测工具以辅助患者选择。影像组学通过提取定量影像特征，可能有助于识别复发风险较高的患者。本研究旨在开发并验证基于治疗前MRI的影像组学列线图，用于预测LARC患者术后复发风险。 方法：本研究对191例经病理确诊的LARC患者（2016-2018年间在14个中心接受治疗）进行了最大规模的多中心回顾性影像组学分析。所有患者均接受新辅助放化疗后行根治性廓清手术。在治疗前T2加权MRI图像上进行手动肿瘤分割。特征筛选采用LASSO回归，通过1000次自助抽样进行5折交叉验证。通过逐步向后选择法，将最常被选中的特征用于构建逻辑回归模型。采用ROC分析、校准曲线、决策曲线分析及1000次自助抽样的内部验证评估模型性能，并构建可个体化评估复发风险的列线图。 结果：术后复发率为51%（98例）。最终模型纳入5个反映肿瘤异质性、形态学及纹理特征的影像组学特征。多变量分析显示，所有入选特征均与复发显著相关，比值比范围为0.63-1.64。模型经乐观校正后的曲线下面积为0.70，表明具有中等区分度。校准曲线显示预测与观察复发概率具有良好一致性。决策曲线分析证实其在相关阈值范围内具有临床实用性。基于最终模型开发了具有临床可解释性的列线图。 结论：基于术前MRI的影像组学模型能够预测LARC患者复发风险。所构建的列线图为术前风险评估提供了实用工具，但需进行前瞻性验证。
肿瘤(癌症)患者之家