From the Medical Physics Unit, Department of Oncology (T.L.L., A.C., M.V., I.R.L., J.S.), Department of Diagnostic Radiology (Y.U., S.S., R.F., P. Savadjiev, C.R.), and School of Computer Science (P. Savadjiev), McGill University, Montreal General Hospital Site, 1650 Cedar Ave, Montreal, QC, Canada H3G 1A4; Cancer Research UK Cambridge Institute, University of Cambridge, Cambridge, England (T.L.L.); Department of Radiology, Kobe University Graduate School of Medicine, Kobe, Japan (Y.U.); Department of Radiology, Cochin Hospital, AP-HP.Centre, Paris, France (A.D., P. Soyer); Université de Paris, Faculté de Médecine, Paris, France (A.D., P. Soyer); Department of Precision Medicine, GROW-School for Oncology and Developmental Biology, Maastricht University, Maastricht, the Netherlands (A.C.); Department of Computer Science, Université de Sherbrooke, Sherbrooke, Quebec, Canada (M.V.); Augmented Intelligence & Precision Health Laboratory (E.W.R., R.F., C.R.), Research Institute of the McGill University Health Centre, Montreal, Quebec, Canada; Department of Obstetrics and Gynecology, McGill University Health Centre, Montreal, Quebec, Canada (X.Z.Z.); and Montreal Imaging Experts, Montreal, Quebec, Canada (R.F., C.R.).
Radiology. 2022 Nov;305(2):375-386. doi: 10.1148/radiol.212873. Epub 2022 Jul 12.
Background Stratifying high-risk histopathologic features in endometrial carcinoma is important for treatment planning. Radiomics analysis at preoperative MRI holds potential to identify high-risk phenotypes. Purpose To evaluate the performance of multiparametric MRI three-dimensional radiomics-based machine learning models for differentiating low- from high-risk histopathologic markers-deep myometrial invasion (MI), lymphovascular space invasion (LVSI), and high-grade status-and advanced-stage endometrial carcinoma. Materials and Methods This dual-center retrospective study included women with histologically proven endometrial carcinoma who underwent 1.5-T MRI before hysterectomy between January 2011 and July 2015. Exclusion criteria were tumor diameter less than 1 cm, missing MRI sequences or histopathology reports, neoadjuvant therapy, and malignant neoplasms other than endometrial carcinoma. Three-dimensional radiomics features were extracted after tumor segmentation at MRI (T2-weighted, diffusion-weighted, and dynamic contrast-enhanced MRI). Predictive features were selected in the training set with use of random forest (RF) models for each end point, and trained RF models were applied to the external test set. Five board-certified radiologists conducted MRI-based staging and deep MI assessment in the training set. Areas under the receiver operating characteristic curve (AUCs) were reported with balanced accuracies, and radiologists' readings were compared with radiomics with use of McNemar tests. Results In total, 157 women were included: 94 at the first institution (training set; mean age, 66 years ± 11 [SD]) and 63 at the second institution (test set; 67 years ± 12). RF models dichotomizing deep MI, LVSI, high grade, and International Federation of Gynecology and Obstetrics (FIGO) stage led to AUCs of 0.81 (95% CI: 0.68, 0.88), 0.80 (95% CI: 0.67, 0.93), 0.74 (95% CI: 0.61, 0.86), and 0.84 (95% CI: 0.72, 0.92), respectively, in the test set. In the training set, radiomics provided increased performance compared with radiologists' readings for identifying deep MI (balanced accuracy, 86% vs 79%; = .03), while no evidence of a difference was observed in performance for advanced FIGO stage (80% vs 78%; = .27). Conclusion Three-dimensional radiomics can stratify patients by using preoperative MRI according to high-risk histopathologic end points in endometrial carcinoma and provide nonsignificantly different or higher performance than radiologists in identifying advanced stage and deep myometrial invasion, respectively. © RSNA, 2022 See also the editorial by Kido and Nishio in this issue.
背景 对子宫内膜癌进行高危组织病理学特征分层对治疗计划很重要。术前 MRI 的放射组学分析有可能识别高危表型。
目的 旨在评估多参数 MRI 三维放射组学基于机器学习模型区分低风险和高风险组织病理学标志物——深层肌层浸润（MI）、脉管间隙浸润（LVSI）和高级别状态——和晚期子宫内膜癌的性能。
材料与方法 本研究为双中心回顾性研究，纳入了 2011 年 1 月至 2015 年 7 月期间在接受子宫切除术前行 1.5-T MRI 检查且组织学证实为子宫内膜癌的女性。排除标准为肿瘤直径小于 1cm、缺少 MRI 序列或组织病理学报告、新辅助治疗以及除子宫内膜癌以外的恶性肿瘤。在 MRI（T2 加权、扩散加权和动态对比增强 MRI）上对肿瘤进行分割后提取三维放射组学特征。在每个终点处使用随机森林（RF）模型在训练集中选择预测特征，并将训练的 RF 模型应用于外部测试集。五名经过董事会认证的放射科医生在训练集中进行基于 MRI 的分期和深层 MI 评估。报告受试者工作特征曲线（AUC）下面积（AUC）和平衡准确率，并使用 McNemar 检验比较放射科医生的阅读结果和放射组学结果。
结果 共纳入 157 名女性：94 名来自第一家机构（训练集；平均年龄 66 岁±11[标准差]）和 63 名来自第二家机构（测试集；67 岁±12）。将深度 MI、LVSI、高级别和国际妇产科联盟（FIGO）分期进行二分类的 RF 模型得出的 AUC 分别为 0.81（95%CI：0.68，0.88）、0.80（95%CI：0.67，0.93）、0.74（95%CI：0.61，0.86）和 0.84（95%CI：0.72，0.92），在测试集中。在训练集中，与放射科医生的阅读结果相比，放射组学在识别深层 MI 方面具有更高的性能（平衡准确率，86%比 79%； =.03），而在识别晚期 FIGO 分期方面未观察到性能差异（80%比 78%； =.27）。
结论 术前 MRI 的三维放射组学可以根据子宫内膜癌的高危组织病理学终点对患者进行分层，并在识别高级别和深层肌层浸润方面提供与放射科医生阅读结果相比差异无统计学意义或更高的性能。
