Key Laboratory of Drug Addiction and Rehabilitation, National Health Commission of the Peoples' Republic of China, Kunming, Yunnan, China.
Department of Medical Imaging, The First Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China.
J Cell Physiol. 2019 Nov;234(11):20501-20509. doi: 10.1002/jcp.28650. Epub 2019 May 9.
The present study aimed to construct prospective models for tumor grading of rectal carcinoma by using magnetic resonance (MR)-based radiomics features. A set of 118 patients with rectal carcinoma was analyzed. After imbalance-adjustments of the data using Synthetic Minority Oversampling Technique (SMOTE), the final data set was randomized into the training set and validation set at the ratio of 3:1. The radiomics features were captured from manually segmented lesion of magnetic resonance imaging (MRI). The most related radiomics features were selected using the random forest model by calculating the Gini importance of initial extracted characteristics. A random forest classifier model was constructed using the top important features. The classifier model performance was evaluated via receive operator characteristic curve and area under the curve (AUC). A total of 1,131 radiomics features were extracted from segmented lesion. The top 50 most important features were selected to construct a random forest classifier model. The AUC values of grade 1, 2, 3, and 4 for training set were 0.918, 0.822, 0.775, and 1.000, respectively, and the corresponding AUC values for testing set were 0.717, 0.683, 0.690, and 0.827 separately. The developed feature selection method and machine learning-based prediction models using radiomics features of MRI show a relatively acceptable performance in tumor grading of rectal carcinoma and could distinguish the tumor subjects from the healthy ones, which is important for the prognosis of cancer patients.
本研究旨在通过基于磁共振（MR）的放射组学特征构建直肠癌肿瘤分级的前瞻性模型。对 118 例直肠癌患者进行了分析。使用 Synthetic Minority Oversampling Technique（SMOTE）对数据进行不平衡调整后，最终数据集按照 3:1 的比例随机分为训练集和验证集。从磁共振成像（MRI）手动分割的病变中提取放射组学特征。使用随机森林模型通过计算初始提取特征的基尼重要性，选择最相关的放射组学特征。使用顶级重要特征构建随机森林分类器模型。通过接收者操作特征曲线和曲线下面积（AUC）评估分类器模型性能。从分割的病变中提取了 1131 个放射组学特征。选择前 50 个最重要的特征来构建随机森林分类器模型。训练集分级 1、2、3 和 4 的 AUC 值分别为 0.918、0.822、0.775 和 1.000，测试集的 AUC 值分别为 0.717、0.683、0.690 和 0.827。开发的特征选择方法和基于放射组学特征的机器学习预测模型在直肠癌肿瘤分级中表现出相对可接受的性能，可以区分肿瘤患者和健康患者，这对癌症患者的预后很重要。
