• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SPIE Medical Imaging Conference >Quantitative diffusion weighted imaging parameters in tumor and peritumoral stroma for prediction of molecular subtypes in breast cancer
【24h】

Quantitative diffusion weighted imaging parameters in tumor and peritumoral stroma for prediction of molecular subtypes in breast cancer

机译：肿瘤和肿瘤周围基质中定量扩散加权成像参数预测乳腺癌分子亚型

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Breast cancer can be classified into four molecular subtypes of Luminal A, Luminal B, HER2 and Basal-like, which have significant differences in treatment and survival outcomes. We in this study aim to predict immunohistochemistry (IHC) determined molecular subtypes of breast cancer using image features derived from tumor and peritumoral stroma region based on diffusion weighted imaging (DWI). A dataset of 126 breast cancer patients were collected who underwent preoperative breast MR1 with a 3T scanner. The apparent diffusion coefficients (ADCs) were recorded from DWI, and breast image was segmented into regions comprising the tumor and the surrounding stromal. Statistical characteristics in various breast tumor and peritumoral regions were computed, including mean, minimum, maximum, variance, interquartile range, range, skewness, and kurtosis of ADC values. Additionally, the difference of features between each two regions were also calculated. The univariate logistic based classifier was performed for evaluating the performance of the individual features for discriminating subtypes. For multi-class classification, multivariate logistic regression model was trained and validated. The results showed that the tumor boundary and proximal peritumoral stroma region derived features have a higher performance in classification compared to that of the other regions. Furthermore, the prediction model using statistical features, difference features and all the features combined from these regions generated AUC values of 0.774, 0.796 and 0.811, respectively. The results in this study indicate that ADC feature in tumor and peritumoral stromal region would be valuable for estimating the molecular subtype in breast cancer.
机译：乳腺癌可分为Luminal A，Luminal B，HER2和Basal-like的四种分子亚型，它们在治疗和生存结果上有显着差异。我们在这项研究中的目的是基于弥散加权成像（DWI），使用源自肿瘤和肿瘤周围基质区域的图像特征来预测乳腺癌的免疫组织化学（IHC）确定的分子亚型。收集了126名乳腺癌患者的数据集，这些患者使用3T扫描仪进行了术前乳房MR1检查。从DWI记录表观扩散系数（ADC），并将乳房图像分割成包括肿瘤和周围基质的区域。计算了各种乳腺肿瘤和肿瘤周围区域的统计特征，包括ADC值的平均值，最小值，最大值，方差，四分位数范围，范围，偏度和峰度。另外，还计算了每两个区域之间的特征差异。进行了基于单变量逻辑分类器，以评估用于区分亚型的单个特征的性能。对于多类别分类，对多元逻辑回归模型进行了训练和验证。结果表明，与其他区域相比，肿瘤边界和近端肿瘤周围基质区域衍生的特征在分类方面具有更高的性能。此外，使用统计特征，差异特征和从这些区域组合的所有特征的预测模型分别产生了0.774、0.796和0.811的AUC值。这项研究的结果表明，肿瘤和肿瘤周围基质区域的ADC特征对于评估乳腺癌的分子亚型具有重要价值。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号