Department of Radiology, Jinshan Hospital, Fudan University, 1508 Longhang Road, Shanghai, 201508, China.
Departments of Radiology, Obstetrics & Gynecology Hospital, Fudan University, 128 ShenYang Road, Shanghai, 200090, China.
Eur Radiol. 2021 Jan;31(1):411-422. doi: 10.1007/s00330-020-07099-8. Epub 2020 Aug 4.
To construct a MRI radiomics model and help radiologists to improve the assessments of pelvic lymph node metastasis (PLNM) in endometrial cancer (EC) preoperatively.
During January 2014 and May 2019, 622 EC patients (age 56.6 ± 8.8 years; range 27-85 years) from five different centers (A to E) were divided into training set, validation set 1 (351 cases from center A), and validation set 2 (271 cases from centers B-E). The radiomics features were extracted basing on T2WI, DWI, ADC, and CE-T1WI images, and most related radiomics features were selected using the random forest classifier to build a radiomics model. The ROC curve was used to evaluate the performance of training set and validation sets, radiologists based on MRI findings alone, and with the aid of the radiomics model. The clinical decisive curve (CDC), net reclassification index (NRI), and total integrated discrimination index (IDI) were used to assess the clinical benefit of using the radiomics model.
The AUC values were 0.935 for the training set, 0.909 and 0.885 for validation sets 1 and 2, 0.623 and 0.643 for the radiologists 1 and 2 alone, and 0.814 and 0.842 for the radiomics-aided radiologists 1 and 2, respectively. The AUC, CDC, NRI, and IDI showed higher diagnostic performance and clinical net benefits for the radiomics-aided radiologists than for the radiologists alone.
The MRI-based radiomics model could be used to assess the status of pelvic lymph node and help radiologists improve their performance in predicting PLNM in EC.
• A total of 358 radiomics features were extracted. The 37 most important features were selected using the random forest classifier. • The reclassification measures of discrimination confirmed that the radiomics-aided radiologists performed better than the radiologists alone, with an NRI of 1.26 and an IDI of 0.21 for radiologist 1 and an NRI of 1.37 and an IDI of 0.24 for radiologist 2.
构建 MRI 放射组学模型，帮助放射科医生提高子宫内膜癌（EC）术前盆腔淋巴结转移（PLNM）的评估能力。
2014 年 1 月至 2019 年 5 月，来自五个不同中心（A 至 E）的 622 例 EC 患者（年龄 56.6±8.8 岁；27-85 岁）被分为训练集、验证集 1（来自中心 A 的 351 例）和验证集 2（来自中心 B-E 的 271 例）。基于 T2WI、DWI、ADC 和 CE-T1WI 图像提取放射组学特征，并使用随机森林分类器选择最相关的放射组学特征，以构建放射组学模型。使用 ROC 曲线评估训练集和验证集、基于 MRI 结果的放射科医生以及辅助放射组学模型的表现。临床决策曲线（CDC）、净重新分类指数（NRI）和总综合判别指数（IDI）用于评估使用放射组学模型的临床获益。
训练集的 AUC 值为 0.935，验证集 1 和 2 的 AUC 值分别为 0.909 和 0.885，放射科医生 1 和 2 的 AUC 值分别为 0.623 和 0.643，放射组学辅助放射科医生 1 和 2 的 AUC 值分别为 0.814 和 0.842。AUC、CDC、NRI 和 IDI 显示，与单独的放射科医生相比，辅助放射组学模型的诊断性能和临床净获益更高。
基于 MRI 的放射组学模型可用于评估盆腔淋巴结状态，帮助放射科医生提高预测 EC 中 PLNM 的能力。
共提取 358 个放射组学特征。使用随机森林分类器选择 37 个最重要的特征。
判别重新分类措施证实，与单独的放射科医生相比，放射组学辅助的放射科医生表现更好，放射科医生 1 的 NRI 为 1.26，IDI 为 0.21，放射科医生 2 的 NRI 为 1.37，IDI 为 0.24。
