Person:

Schnitt, Stuart

The categorization of intraductal proliferative lesions of the breast based on routine light microscopic examination of histopathologic sections is in many cases challenging, even for experienced pathologists. The development of computational tools to aid pathologists in the characterization of these lesions would have great diagnostic and clinical value. As a first step to address this issue, we evaluated the ability of computational image analysis to accurately classify DCIS and UDH and to stratify nuclear grade within DCIS. Using 116 breast biopsies diagnosed as DCIS or UDH from the Massachusetts General Hospital (MGH), we developed a computational method to extract 392 features corresponding to the mean and standard deviation in nuclear size and shape, intensity, and texture across 8 color channels. We used L1-regularized logistic regression to build classification models to discriminate DCIS from UDH. The top-performing model contained 22 active features and achieved an AUC of 0.95 in cross-validation on the MGH data-set. We applied this model to an external validation set of 51 breast biopsies diagnosed as DCIS or UDH from the Beth Israel Deaconess Medical Center, and the model achieved an AUC of 0.86. The top-performing model contained active features from all color-spaces and from the three classes of features (morphology, intensity, and texture), suggesting the value of each for prediction. We built models to stratify grade within DCIS and obtained strong performance for stratifying low nuclear grade vs. high nuclear grade DCIS (AUC = 0.98 in cross-validation) with only moderate performance for discriminating low nuclear grade vs. intermediate nuclear grade and intermediate nuclear grade vs. high nuclear grade DCIS (AUC = 0.83 and 0.69, respectively). These data show that computational pathology models can robustly discriminate benign from malignant intraductal proliferative lesions of the breast and may aid pathologists in the diagnosis and classification of these lesions.

Background: Enhancer of zeste homolog 2 (EZH2) is a polycomb-group protein that is involved in stem cell renewal and carcinogenesis. In breast cancer, increased EZH2 expression is associated with aggressiveness and has been suggested to identify normal breast epithelium at increased risk of breast cancer development. However, the association between EZH2 expression in benign breast tissue and breast cancer risk has not previously been evaluated in a large prospective cohort. Methods: We examined the association between EZH2 protein expression and subsequent breast cancer risk using logistic regression in a nested case-control study of benign breast disease (BBD) and breast cancer within the Nurses’ Health Studies. EZH2 immunohistochemical expression in normal breast epithelium and stroma was evaluated by computational image analysis and its association with breast cancer risk was analyzed after adjusting for matching factors between cases and controls, the concomitant BBD diagnosis, and the Ki67 proliferation index. Results: Women with a breast biopsy in which more than 20% of normal epithelial cells expressed EZH2 had a significantly increased risk of developing breast cancer (odds ratio (OR) 2.95, 95% confidence interval (CI) 1.11–7.84) compared to women with less than 10% EZH2 epithelial expression. The risk of developing breast cancer increased for each 5% increase in EZH2 expression (OR 1.22, 95% CI 1.02–1.46, p value 0.026). Additionally, women with high EZH2 expression and low estrogen receptor (ER) expression had a 4-fold higher risk of breast cancer compared to women with low EZH2 and low ER expression (OR 4.02, 95% CI 1.29–12.59). Conclusions: These results provide further evidence that EZH2 expression in the normal breast epithelium is independently associated with breast cancer risk and might be used to assist in risk stratification for women with benign breast biopsies. Electronic supplementary material The online version of this article (doi:10.1186/s13058-017-0817-6) contains supplementary material, which is available to authorized users.