Mazo Claudia, Orue-Etxebarria Estibaliz, Zabalza Ignacio, Vivanco Maria D M, Kypta Robert M, Beristain Andoni
Vicomtech, eHealth and Biomedical Applications, 20009 San Sebastian-Donostia, Spain.
School of Computer Science, University College Dublin, D14 YH57 Dublin, Ireland.
Cancers (Basel). 2018 Dec 15;10(12):517. doi: 10.3390/cancers10120517.
Breast cancer is the most frequently diagnosed cancer in women and the second most common cancer overall, with nearly 1.7 million new cases worldwide every year. Breast cancer patients need accurate tools for early diagnosis and to improve treatment. Biomarkers are increasingly used to describe and evaluate tumours for prognosis, to facilitate and predict response to therapy and to evaluate residual tumor, post-treatment. Here, we evaluate different methods to separate Diaminobenzidine (DAB) from Hematoxylin and Eosin (H&E) staining for , a potential cytoplasmic breast cancer biomarker. A method comprising clustering and Color deconvolution allowed us to recognize and quantify levels accurately at pixel levels. Experimental validation was conducted using a set of 12,288 blocks of m × n pixels without overlap, extracted from a Tissue Microarray (TMA) composed of 192 tissue cores. Intraclass Correlations (ICC) among evaluators of the data of 0.634 , 0.791 , 0.551 and 0.63 for each Allred class and an average ICC of 0.752 among evaluators and automatic classification were obtained. Furthermore, this method received an average rating of 4.26 out of 5 in the segmentation process from the evaluators.
乳腺癌是女性中最常被诊断出的癌症，也是总体上第二常见的癌症，全球每年有近170万新病例。乳腺癌患者需要准确的工具用于早期诊断和改善治疗。生物标志物越来越多地用于描述和评估肿瘤的预后，促进和预测对治疗的反应以及评估治疗后的残留肿瘤。在此，我们评估了从苏木精和伊红（H&E）染色中分离二氨基联苯胺（DAB）的不同方法，以用于一种潜在的细胞质乳腺癌生物标志物。一种包括聚类和颜色反卷积的方法使我们能够在像素水平上准确识别和量化 水平。使用从由192个组织芯组成的组织微阵列（TMA）中提取的一组12288个m×n像素的无重叠块进行了实验验证。对于每个艾尔雷德等级，评估者之间的数据类内相关性（ICC）分别为0.634、0.791、0.551和0.63，评估者与自动分类之间的平均ICC为0.752。此外，在评估者的 分割过程中，该方法在5分制中平均获得了4.26分的评分。
