Department of Radiology, China-Japan Union Hospital of Jilin University, NO. 126 Xiantai Street, Changchun, 130033, China.
GE Healthcare, Beijing, China.
Radiol Med. 2022 Jul;127(7):702-713. doi: 10.1007/s11547-022-01507-3. Epub 2022 Jul 13.
To establish and validate a radiomics model based on multi-sequence magnetic resonance (MR) images for preoperative prediction of immunoscore in rectal cancer.
This retrospective study included 133 patients with pathologically confirmed rectal cancer after surgical resection who underwent MR examination before treatment within two weeks. All patients were randomly divided into training cohort (n = 92) and validation (n = 41) cohort according to a ratio of 7:3. The volumes of interest were manually delineated in the T2-weighted images (T2WI) and apparent diffusion coefficient (ADC) images, from which a total of 804 radiomics features were extracted. Thereafter, we used Spearman correlation analysis and gradient boosting decision tree (GBDT) algorithm to select the strongest features, and the radiomics scores were established using multivariate logistic regression algorithm, including two single-mode models and two dual-mode models. The predictive performance and the clinical usefulness of the model were assessed by the receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA).
Integrated model A based on T2WI and ADC images showed a better predictive performance, which yielded an AUC of 0.770 (95% CI 0.673-0.867) in the training cohort and 0.768 (95% CI 0.619-0.917) in the validation cohort. Calibration curve showed good agreement between predicted results of the model and actual events, and DCA indicated good clinical usefulness. Moreover, stratification analysis proved that the integrated model A had strong robustness.
Integrated model A based on T2WI and ADC images has the potential to be used as a non-invasive tool for preoperative prediction of immunoscore in rectal cancer. It may be useful in evaluating prognosis and guiding individualized immunotherapy of patients.
建立并验证一种基于多序列磁共振（MR）图像的放射组学模型，用于术前预测直肠癌的免疫评分。
本回顾性研究纳入了 133 例经手术切除、病理证实的直肠癌患者，这些患者在治疗前两周内行 MR 检查。所有患者按照 7:3 的比例随机分为训练队列（n=92）和验证队列（n=41）。在 T2 加权图像（T2WI）和表观扩散系数（ADC）图像上手动勾画感兴趣区，从中提取了总共 804 个放射组学特征。然后，我们使用 Spearman 相关分析和梯度提升决策树（GBDT）算法选择最强特征，并使用多元逻辑回归算法建立放射组学评分，包括两个单模态模型和两个双模态模型。通过受试者工作特征（ROC）曲线、校准曲线和决策曲线分析（DCA）评估模型的预测性能和临床实用性。
基于 T2WI 和 ADC 图像的综合模型 A 具有更好的预测性能，在训练队列中的 AUC 为 0.770（95%CI 0.673-0.867），在验证队列中的 AUC 为 0.768（95%CI 0.619-0.917）。校准曲线显示模型预测结果与实际事件具有良好的一致性，DCA 表明其具有良好的临床实用性。此外，分层分析证明综合模型 A 具有较强的稳健性。
基于 T2WI 和 ADC 图像的综合模型 A 有望成为一种术前预测直肠癌免疫评分的非侵入性工具，可能有助于评估预后和指导患者的个体化免疫治疗。
