Yin Fu, Zhang Haijie, Qi Anqi, Zhu Zexuan, Yang Liyang, Wen Ge, Xie Weixin
College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China.
Medical Imaging Department, Nanfang Hospital, Southern Medical University, Guangzhou, China.
Front Oncol. 2022 Oct 27;12:979613. doi: 10.3389/fonc.2022.979613. eCollection 2022.
To explore the feasibility of predicting the World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade and progression-free survival (PFS) of clear cell renal cell cancer (ccRCC) using the radiomics features (RFs) based on the differential network feature selection (FS) method using the maximum-entropy probability model (MEPM).
175 ccRCC patients were divided into a training set (125) and a test set (50). The non-contrast phase (NCP), cortico-medullary phase, nephrographic phase, excretory phase phases, and all-phase WHO/ISUP grade prediction models were constructed based on a new differential network FS method using the MEPM. The diagnostic performance of the best phase model was compared with the other state-of-the-art machine learning models and the clinical models. The RFs of the best phase model were used for survival analysis and visualized using risk scores and nomograms. The performance of the above models was tested in both cross-validated and independent validation and checked by the Hosmer-Lemeshow test.
The NCP RFs model was the best phase model, with an AUC of 0.89 in the test set, and performed superior to other machine learning models and the clinical models (all 0.05). Kaplan-Meier survival analysis, univariate and multivariate cox regression results, and risk score analyses showed the NCP RFs could predict PFS well (almost all < 0.05). The nomogram model incorporated the best two RFs and showed good discrimination, a C-index of 0.71 and 0.69 in the training and test set, and good calibration.
The NCP CT-based RFs selected by differential network FS could predict the WHO/ISUP grade and PFS of RCC.
探讨基于最大熵概率模型（MEPM）的差异网络特征选择（FS）方法，利用影像组学特征（RFs）预测透明细胞肾细胞癌（ccRCC）的世界卫生组织/国际泌尿病理学会（WHO/ISUP）分级及无进展生存期（PFS）的可行性。
将175例ccRCC患者分为训练集（125例）和测试集（50例）。基于使用MEPM的新差异网络FS方法构建非增强期（NCP）、皮髓质期、肾实质期、排泄期以及全期WHO/ISUP分级预测模型。将最佳期相模型的诊断性能与其他先进的机器学习模型和临床模型进行比较。使用最佳期相模型的RFs进行生存分析，并通过风险评分和列线图进行可视化。上述模型的性能在交叉验证和独立验证中进行测试，并通过Hosmer-Lemeshow检验进行检查。
NCP RFs模型是最佳期相模型，在测试集中AUC为0.89，其性能优于其他机器学习模型和临床模型（均P<0.05）。Kaplan-Meier生存分析、单因素和多因素cox回归结果以及风险评分分析表明，NCP RFs能够很好地预测PFS（几乎所有P<0.05）。列线图模型纳入了最佳的两个RFs，显示出良好的区分度，在训练集和测试集中的C指数分别为0.71和0.69，且校准良好。
通过差异网络FS选择的基于NCP CT的RFs能够预测RCC的WHO/ISUP分级和PFS。
