欢迎来到《四川大学学报(医学版)》
徐春燕, 谢嘉伟, 杨春霞, 等. 基于病理穿刺切片组织形态学分析的乳腺癌新辅助化疗疗效预测[J]. 四川大学学报(医学版), 2021, 52(2): 279-285. DOI: 10.12182/20210360505
引用本文: 徐春燕, 谢嘉伟, 杨春霞, 等. 基于病理穿刺切片组织形态学分析的乳腺癌新辅助化疗疗效预测[J]. 四川大学学报(医学版), 2021, 52(2): 279-285. DOI: 10.12182/20210360505
XU Chun-yan, XIE Jia-wei, YANG Chun-xia, et al. Prediction of Response to Neoadjuvant Chemotherapy for Breast Cancer Based on Histomorphology Analysis of Needle Biopsy Images[J]. Journal of Sichuan University (Medical Sciences), 2021, 52(2): 279-285. DOI: 10.12182/20210360505
Citation: XU Chun-yan, XIE Jia-wei, YANG Chun-xia, et al. Prediction of Response to Neoadjuvant Chemotherapy for Breast Cancer Based on Histomorphology Analysis of Needle Biopsy Images[J]. Journal of Sichuan University (Medical Sciences), 2021, 52(2): 279-285. DOI: 10.12182/20210360505

基于病理穿刺切片组织形态学分析的乳腺癌新辅助化疗疗效预测

Prediction of Response to Neoadjuvant Chemotherapy for Breast Cancer Based on Histomorphology Analysis of Needle Biopsy Images

  • 摘要:
      目的   利用深度学习的方法对乳腺癌患者接受新辅助化疗(NAC)前的穿刺切片进行肿瘤区域和细胞核的自动分割,提取肿瘤区域细胞群特征,从而对乳腺癌NAC病理缓解程度进行预测。
      方法   收集在江苏省人民医院接受NAC治疗前的68位乳腺癌患者的术前穿刺HE染色切片,两位病理医生对其中12张穿刺切片进行了肿瘤区域的标记,其中8张作为训练集,4张作为测试集,剩余的56张由训练好的肿瘤区分割模型进行肿瘤分割。运用UNet++建立分割模型,分别对乳腺癌病理穿刺切片肿瘤区域和细胞核进行自动分割;然后,根据自动分割的肿瘤区域内细胞核,构建肿瘤内细胞层次的特征;最后运用特征选择方法选择有效的特征,通过五折交叉验证训练分类器模型预测NAC的病理缓解程度的高低。
      结果   基于68位患者的病理穿刺切片进行预测,最大相关最小冗余(mRMR)的特征选择方法筛选出的10个维度特征和随机森林(RF)分类器结合训练的模型预测结果的准确率最高,准确率达到82.35%,曲线下面积(AUC)值达到0.9082。
      结论   本模型能够在切片病理图像上自动分割肿瘤区域和细胞核,构建的肿瘤区域细胞核群的特征能够预测患者对NAC的病理缓解程度,方法可靠且可重复性较高,同时发现肿瘤区域细胞核纹理特征在预测中效果较好,进一步证实了肿瘤区域细胞核群对疗效预测具有重要意义。

     

    Abstract:
      Objective   The deep learning method was used to automatically segment the tumor area and the cell nucleus based on needle biopsy images of breast cancer patients prior to receiving neoadjuvant chemotherapy (NAC), and then, the features of the cell clusters in the tumor area were identified to predict the level of pathological remission of breast cancer after NAC.
      Methods   68 breast cancer patients who were to receive NAC at Jiangsu Province Hospital were recruited and the hematoxylin-eosin (HE) stained preoperative biopsy sections of these patients were collected. Unet++ was used to establish a segmentation model and the tumor area and nucleus of the needle biopsy images were automatically segmented accordingly. Then, according to the nuclei in the automatically segmented tumor area, the features of the cells in the tumor were constructed. After that, effective features were selected through the feature selection method and the classifier model was constructed and trained with five-fold cross validation to predict the degree of post-NAC pathological remission.
      Results   Predictions were made based on the needle biopsy images of the 68 patients. The model that combined the 10-dimensional features selected with the minimal redundancy-maximum-relevancy approach (mRMR) and training with the random forest (RF) classifier had the highest prediction accuracy, reaching 82.35%, and an area under curve (AUC) value of 0.9082.
      Conclusion   This model automatically segments tumor areas and cell nucleus on the biopsy images. The features of the cell clusters which are analyzed and identified in the tumor area can be used to predict the pathological response of the patient to NAC. The method is reliable and replicable. In addition, we found that the textural features of cells in the tumor area was a useful predictor of patient response to NAC, which further confirmed that cell cluster in the tumor area is of great significance to the prediction of treatment outcome.

     

/

返回文章
返回