Department of Radiology, The Third Affiliated Hospital of Zhengzhou University, No.7 Kangfu front street, Zhengzhou 450052, China; Institute of Neuroscience, Zhengzhou University, Zhengzhou 450052, China.
Institute of Neuroscience, Zhengzhou University, Zhengzhou 450052, China; College of Chemistry, Zhengzhou University, Zhengzhou, Zhengzhou 450052, China.
Magn Reson Imaging. 2022 Jun;89:70-76. doi: 10.1016/j.mri.2022.03.002. Epub 2022 Mar 23.
This study aims to establish a MRI-based classifier to distinguish early stages of cervical cancer with improved diagnostic performance to assist clinical diagnosis and treatment. 57 patients with pathological diagnosis of cervical cancer from January 2018 to May 2019 were enrolled in this study. MRI examinations, including T1-weighted image(T1WI), T2-weighted image(T2W), diffusion weighted imaging (DWI) and dynamic contrast enhanced (DCE), were performed before surgery. MR images from patients of stage Ib or IIa cervical cancer with tumor segmented were used as input. Feature extraction process extracted first-order statistics and texture and applied filters. The dimensionality of the radiomic features was reduced using the least absolute shrinkage and selection operator (LASSO). Models were trained by three machine-learning (k-nearest neighbor (KNN), support vector machine (SVM), and logistic regression (LR)) and diagnostic performance in differentiating stage Ib and stage IIa cases was evaluated. A total of 27 features were extracted to establish models, including 2 features from T1WI, 5 features from T2WI, 5 features from DWI (b = 50), 4 features from DWI (b = 800), 5 features from DCE, and 6 features from ADC. For each machine learning (ML) classifier, six sequences of training set and testing set are modeled and analyzed. Among all the models, the training set and testing set of T2WI model built by SVM classifier were the best (Area under the curve (AUC) 0.915) / (AUC 0.907). Radiomic analysis of ML-based texture features and first-order statistics features can be used to stage the early cervical cancer pre-operatively.
本研究旨在建立一种基于 MRI 的分类器，以提高诊断性能，辅助临床诊断和治疗，从而区分宫颈癌的早期阶段。本研究纳入了 57 名经病理诊断为宫颈癌的患者，这些患者均于 2018 年 1 月至 2019 年 5 月接受了 MRI 检查，包括 T1 加权像（T1WI）、T2 加权像（T2WI）、弥散加权成像（DWI）和动态对比增强（DCE）。将 Ib 期或 IIa 期宫颈癌患者的肿瘤分割后的 MRI 图像作为输入。特征提取过程提取了一阶统计和纹理特征，并应用了滤波器。使用最小绝对收缩和选择算子（LASSO）降低放射组学特征的维数。通过三种机器学习（k-最近邻（KNN）、支持向量机（SVM）和逻辑回归（LR））训练模型，并评估其区分 Ib 期和 IIa 期病例的诊断性能。共提取了 27 个特征来建立模型，其中 T1WI 有 2 个特征，T2WI 有 5 个特征，DWI（b=50）有 5 个特征，DWI（b=800）有 4 个特征，DCE 有 5 个特征，ADC 有 6 个特征。对于每种机器学习（ML）分类器，都对训练集和测试集的 6 个序列进行了建模和分析。在所有模型中，SVM 分类器构建的 T2WI 模型的训练集和测试集表现最佳（曲线下面积（AUC）0.915/（AUC 0.907）。基于 ML 的纹理特征和一阶统计特征的放射组学分析可用于术前分期早期宫颈癌。
