LaTIM, INSERM, UMR 1101, Université de Bretagne Occidentale, 22 rue Camille Desmoulins, 29238, Brest, France.
Department of Digestive and Hepatobiliary Surgery - Liver transplantation, University Hospital Clermont-Ferrand, Clermont-Ferrand, France.
Eur Radiol. 2022 Jan;32(1):405-414. doi: 10.1007/s00330-021-08104-4. Epub 2021 Jun 25.
To assess the value of contrast-enhanced (CE) diagnostic CT scans characterized through radiomics as predictors of recurrence for patients with stage II and III colorectal cancer in a two-center context.
This study included 193 patients diagnosed with stage II and III colorectal adenocarcinoma from 1 July 2008 to 15 March 2017 in two different French University Hospitals. To compensate for the variability in two-center data, a statistical harmonization method Bootstrapped ComBat (B-ComBat) was used. Models predicting disease-free survival (DFS) were built using 3 different machine learning (ML): (1) multivariate regression (MR) with 10-fold cross-validation after feature selection based on least absolute shrinkage and selection operator (LASSO), (2) random forest (RF), and (3) support vector machine (SVM), both with embedded feature selection.
The performance for both balanced and 95% sensitivity models was systematically higher after our proposed B-ComBat harmonization compared to the use of the original untransformed data. The most clinically relevant performance was achieved by the multivariate regression model combining a clinical variable (postoperative chemotherapy) with two radiomics shape descriptors (compactness and least axis length) with a BAcc of 0.78 and an MCC of 0.6 associated with a required sensitivity of 95%. The resulting stratification in terms of DFS was significant (p = 0.00021), especially compared to the use of unharmonized original data (p = 0.17).
Radiomics models derived from contrast-enhanced CT could be trained and validated in a two-center cohort with a good predictive performance of recurrence in stage II et III colorectal cancer patients.
• Adjuvant therapy decision in colorectal cancer can be a challenge in medical oncology. • Radiomics models, derived from diagnostic CT, trained and validated in a two-center cohort, could predict recurrence in stage II and III colorectal cancer patients. • Identifying patients with a low risk of recurrence, these models could facilitate treatment optimization and avoid unnecessary treatment.
评估通过放射组学特征描述的增强（CE）诊断 CT 扫描在预测 II 期和 III 期结直肠癌患者复发方面的价值，该研究在两个中心进行。
本研究纳入了 2008 年 7 月 1 日至 2017 年 3 月 15 日期间在法国两家不同大学附属医院诊断为 II 期和 III 期结直肠腺癌的 193 例患者。为了补偿两个中心数据的可变性，使用了一种统计协调方法 Bootstrapped ComBat（B-ComBat）。使用 3 种不同的机器学习（ML）方法构建了预测无病生存（DFS）的模型：（1）基于最小绝对值收缩和选择算子（LASSO）的特征选择后的 10 折交叉验证的多变量回归（MR），（2）随机森林（RF）和（3）支持向量机（SVM），两者都具有嵌入式特征选择。
与使用原始未转换数据相比，我们提出的 B-ComBat 协调后，平衡和 95%灵敏度模型的性能都得到了系统提高。多变量回归模型将临床变量（术后化疗）与两个放射组学形状描述符（紧密度和最小轴长）相结合，具有最高的临床相关性，其 BAcc 为 0.78，MCC 为 0.6，需要的灵敏度为 95%。DFS 的分层具有显著意义（p = 0.00021），尤其是与使用未协调的原始数据相比（p = 0.17）。
来自增强 CT 的放射组学模型可以在具有良好预测性能的 II 期和 III 期结直肠癌患者的两个中心队列中进行训练和验证。
结直肠癌的辅助治疗决策在肿瘤内科可能是一个挑战。
来自诊断 CT 的放射组学模型，在两个中心队列中进行训练和验证，可以预测 II 期和 III 期结直肠癌患者的复发。
确定复发风险低的患者，这些模型可以促进治疗优化并避免不必要的治疗。
