Yardimci Aytul Hande, Kocak Burak, Sel Ipek, Bulut Hasan, Bektas Ceyda Turan, Cin Merve, Dursun Nevra, Bektas Hasan, Mermut Ozlem, Yardimci Veysi Hakan, Kilickesmez Ozgur
Department of Radiology, University of Health Sciences, Basaksehir Cam and Sakura City Hospital, Basaksehir, Istanbul, 34480, Turkey.
Department of Radiology, University of Health Sciences, Istanbul Training and Research Hospital, Istanbul, Turkey.
Jpn J Radiol. 2023 Jan;41(1):71-82. doi: 10.1007/s11604-022-01325-7. Epub 2022 Aug 13.
Variable response to neoadjuvant chemoradiotherapy (nCRT) is observed among individuals with locally advanced rectal cancer (LARC), having a significant impact on patient management. In this work, we aimed to investigate the potential value of machine learning (ML)-based magnetic resonance imaging (MRI) radiomics in predicting therapeutic response to nCRT in patients with LARC.
Seventy-six patients with LARC were included in this retrospective study. Radiomic features were extracted from pre-treatment sagittal T2-weighted MRI images, with 3D segmentation. Dimension reduction was performed with a reliability analysis, pair-wise correlation analysis, analysis of variance, recursive feature elimination, Kruskal-Wallis, and Relief methods. Models were created using four different algorithms. In addition to radiomic models, clinical only and different combined models were developed and compared. The reference standard was tumor regression grade (TRG) based on the Modified Ryan Scheme (TRG 0 vs TRG 1-3). Models were compared based on net reclassification index (NRI). Clinical utility was assessed with decision curve analysis (DCA).
Number of features with excellent reliability is 106. The best result was achieved with radiomic only model using eight features. The area under the curve (AUC), accuracy, sensitivity, and specificity for validation were 0.753 (standard deviation [SD], 0.082), 81.1%, 83.8%, and 75.0%; for testing, 0.705 (SD, 0.145), 73.9%, 81.2%, and 57.1%, respectively. Based on the clinical only model as reference, NRI for radiomic only model was the best. DCA also showed better clinical utility for radiomic only model.
ML-based T2-weighted MRI radiomics might have a potential in predicting response to nCRT in patients with LARC.
局部晚期直肠癌（LARC）患者对新辅助放化疗（nCRT）的反应存在差异，这对患者管理有重大影响。在本研究中，我们旨在探讨基于机器学习（ML）的磁共振成像（MRI）放射组学在预测LARC患者对nCRT治疗反应方面的潜在价值。
本回顾性研究纳入了76例LARC患者。通过三维分割从治疗前矢状位T2加权MRI图像中提取放射组学特征。采用可靠性分析、成对相关性分析、方差分析、递归特征消除、Kruskal-Wallis检验和Relief方法进行降维。使用四种不同算法创建模型。除了放射组学模型外，还开发并比较了仅临床因素模型和不同的联合模型。参考标准是基于改良Ryan方案的肿瘤退缩分级（TRG）（TRG 0与TRG 1-3）。基于净重新分类指数（NRI）对模型进行比较。通过决策曲线分析（DCA）评估临床实用性。
具有极佳可靠性的特征数量为106个。仅使用8个特征的放射组学模型取得了最佳结果。验证时的曲线下面积（AUC）、准确率、灵敏度和特异度分别为0.753（标准差[SD]，0.082）、81.1%、83.8%和75.0%；测试时分别为0.705（SD，0.145）、73.9%、81.2%和57.1%。以仅临床因素模型为参考，仅放射组学模型的NRI最佳。DCA也显示仅放射组学模型具有更好的临床实用性。
基于ML的T2加权MRI放射组学在预测LARC患者对nCRT的反应方面可能具有潜力。
