PDF(Pubmed)
Abstract：
UNASSIGNED: To evaluate the value of the malignant subregion-based texture analysis in predicting Ki-67 status in breast cancer.
UNASSIGNED: The dynamic contrast-enhanced magnetic resonance imaging data of 119 histopathologically confirmed breast cancer patients (81 patients with high Ki-67 expression status) from January 2018 to February 2023 in our hospital were retrospectively collected. According to the enhancement curve of each voxel within the tumor, three subregions were divided: washout subregion, plateau subregion, and persistent subregion. The washout subregion and the plateau subregion were merged as the malignant subregion. The texture features of the malignant subregion were extracted using Pyradiomics software for texture analysis. The differences in texture features were compared between the low and high Ki-67 expression cohorts and then the receiver operating characteristic (ROC) curve analysis to evaluate the predictive performance of texture features on Ki-67 expression. Finally, a support vector machine (SVM) classifier was constructed based on differential features to predict the expression level of Ki-67, the performance of the classifier was evaluated using ROC analysis and confirmed using 10-fold cross-validation.
UNASSIGNED: Through comparative analysis, 51 features exhibited significant differences between the low and high Ki-67 expression cohorts. Following feature reduction, 5 features were selected to build the SVM classifier, which achieved an area under the ROC curve (AUC) of 0.77 (0.68-0.87) for predicting the Ki-67 expression status. The accuracy, sensitivity, and specificity were 0.76, 0.80, and 0.68, respectively. The average AUC from the 10-fold cross-validation was 0.72 ± 0.14.
UNASSIGNED: The texture features of the malignant subregion in breast cancer were potential biomarkers for predicting Ki-67 expression level in breast cancer, which might be used to precisely diagnose and guide the treatment of breast cancer.
UNASSIGNED: The dynamic contrast-enhanced magnetic resonance imaging data of 119 histopathologically confirmed breast cancer patients (81 patients with high Ki-67 expression status) from January 2018 to February 2023 in our hospital were retrospectively collected. According to the enhancement curve of each voxel within the tumor, three subregions were divided: washout subregion, plateau subregion, and persistent subregion. The washout subregion and the plateau subregion were merged as the malignant subregion. The texture features of the malignant subregion were extracted using Pyradiomics software for texture analysis. The differences in texture features were compared between the low and high Ki-67 expression cohorts and then the receiver operating characteristic (ROC) curve analysis to evaluate the predictive performance of texture features on Ki-67 expression. Finally, a support vector machine (SVM) classifier was constructed based on differential features to predict the expression level of Ki-67, the performance of the classifier was evaluated using ROC analysis and confirmed using 10-fold cross-validation.
UNASSIGNED: Through comparative analysis, 51 features exhibited significant differences between the low and high Ki-67 expression cohorts. Following feature reduction, 5 features were selected to build the SVM classifier, which achieved an area under the ROC curve (AUC) of 0.77 (0.68-0.87) for predicting the Ki-67 expression status. The accuracy, sensitivity, and specificity were 0.76, 0.80, and 0.68, respectively. The average AUC from the 10-fold cross-validation was 0.72 ± 0.14.
UNASSIGNED: The texture features of the malignant subregion in breast cancer were potential biomarkers for predicting Ki-67 expression level in breast cancer, which might be used to precisely diagnose and guide the treatment of breast cancer.
摘要：
■评估基于恶性分区的纹理分析在预测乳腺癌Ki-67状态中的价值。
■回顾性收集我院2018年1月至2023年2月119例经组织病理学证实的乳腺癌患者（81例高Ki-67表达状态患者）的动态对比增强磁共振成像数据。根据肿瘤内各体素的增强曲线,划分了三个分区:冲洗分区，高原次区域,和持久的次区域。冲洗子区域和高原子区域合并为恶性子区域。使用Pyradiomics软件提取恶性亚区域的纹理特征进行纹理分析。在低Ki-67表达组群和高Ki-67表达组群之间比较纹理特征的差异,然后进行接受者工作特征(ROC)曲线分析以评估纹理特征对Ki-67表达的预测性能。最后,基于差异特征构建支持向量机(SVM)分类器,以预测Ki-67的表达水平,使用ROC分析评估分类器的性能,并使用10倍交叉验证进行确认.
■通过对比分析，51个特征在低Ki-67表达组群和高Ki-67表达组群之间表现出显著差异。功能缩减之后，选择5个特征来构建SVM分类器,其获得的ROC曲线下面积(AUC)为0.77(0.68-0.87),用于预测Ki-67表达状态。准确性,灵敏度,特异性分别为0.76、0.80和0.68。来自10倍交叉验证的平均AUC为0.72±0.14。
■乳腺癌恶性亚区域的纹理特征是预测乳腺癌Ki-67表达水平的潜在生物标志物，可以用来精确诊断和指导乳腺癌的治疗。
■回顾性收集我院2018年1月至2023年2月119例经组织病理学证实的乳腺癌患者（81例高Ki-67表达状态患者）的动态对比增强磁共振成像数据。根据肿瘤内各体素的增强曲线,划分了三个分区:冲洗分区，高原次区域,和持久的次区域。冲洗子区域和高原子区域合并为恶性子区域。使用Pyradiomics软件提取恶性亚区域的纹理特征进行纹理分析。在低Ki-67表达组群和高Ki-67表达组群之间比较纹理特征的差异,然后进行接受者工作特征(ROC)曲线分析以评估纹理特征对Ki-67表达的预测性能。最后,基于差异特征构建支持向量机(SVM)分类器,以预测Ki-67的表达水平,使用ROC分析评估分类器的性能,并使用10倍交叉验证进行确认.
■通过对比分析，51个特征在低Ki-67表达组群和高Ki-67表达组群之间表现出显著差异。功能缩减之后，选择5个特征来构建SVM分类器,其获得的ROC曲线下面积(AUC)为0.77(0.68-0.87),用于预测Ki-67表达状态。准确性,灵敏度,特异性分别为0.76、0.80和0.68。来自10倍交叉验证的平均AUC为0.72±0.14。
■乳腺癌恶性亚区域的纹理特征是预测乳腺癌Ki-67表达水平的潜在生物标志物，可以用来精确诊断和指导乳腺癌的治疗。
