Explore the vast range of titles available.

Computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still, lack of interpretability remains a significant barrier to clinical integration. We present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5700 samples to train deep learning models for cell and tissue classification that can exhaustively map whole-slide images at two and four micron-resolution. Cell- and tissue-type model outputs are combined into 607 HIFs that quantify specific and biologically-relevant characteristics across five cancer types. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment and can predict diverse molecular signatures (AUROC 0.601–0.864), including expression of four immune checkpoint proteins and homologous recombination deficiency, with performance comparable to ‘black-box’ methods. Our HIF-based approach provides a comprehensive, quantitative, and interpretable window into the composition and spatial architecture of the tumor microenvironment. Computational methods have made progress in improving classification accuracy and throughput of pathology workflows, but lack of interpretability remains a barrier to clinical integration. Here, the authors present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features.

The term ‘field effect' (also known as field defect, field cancerization, or field carcinogenesis) has been used to describe a field of cellular and molecular alteration, which predisposes to the development of neoplasms within that territory. We explore an expanded, integrative concept, ‘etiologic field effect', which asserts that various etiologic factors (the exposome including dietary, lifestyle, environmental, microbial, hormonal, and genetic factors) and their interactions (the interactome) contribute to a tissue microenvironmental milieu that constitutes a ‘field of susceptibility' to neoplasia initiation, evolution, and progression. Importantly, etiological fields predate the acquisition of molecular aberrations commonly considered to indicate presence of filed effect. Inspired by molecular pathological epidemiology (MPE) research, which examines the influence of etiologic factors on cellular and molecular alterations during disease course, an etiologically focused approach to field effect can: (1) broaden the horizons of our inquiry into cancer susceptibility and progression at molecular, cellular, and environmental levels, during all stages of tumor evolution; (2) embrace host–environment–tumor interactions (including gene-environment interactions) occurring in the tumor microenvironment; and, (3) help explain intriguing observations, such as shared molecular features between bilateral primary breast carcinomas, and between synchronous colorectal cancers, where similar molecular changes are absent from intervening normal colon. MPE research has identified a number of endogenous and environmental exposures which can influence not only molecular signatures in the genome, epigenome, transcriptome, proteome, metabolome and interactome, but also host immunity and tumor behavior. We anticipate that future technological advances will allow the development of in vivo biosensors capable of detecting and quantifying ‘etiologic field effect' as abnormal network pathology patterns of cellular and microenvironmental responses to endogenous and exogenous exposures. Through an ‘etiologic field effect' paradigm, and holistic systems pathology (systems biology) approaches to cancer biology, we can improve personalized prevention and treatment strategies for precision medicine.

The breast stromal microenvironment is a pivotal factor in breast cancer development, growth and metastases. Although pathologists often detect morphologic changes in stroma by light microscopy, visual classification of such changes is subjective and non-quantitative, limiting its diagnostic utility. To gain insights into stromal changes associated with breast cancer, we applied automated machine learning techniques to digital images of 2387 hematoxylin and eosin stained tissue sections of benign and malignant image-guided breast biopsies performed to investigate mammographic abnormalities among 882 patients, ages 40–65 years, that were enrolled in the Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project. Using deep convolutional neural networks, we trained an algorithm to discriminate between stroma surrounding invasive cancer and stroma from benign biopsies. In test sets (928 whole-slide images from 330 patients), this algorithm could distinguish biopsies diagnosed as invasive cancer from benign biopsies solely based on the stromal characteristics (area under the receiver operator characteristics curve = 0.962). Furthermore, without being trained specifically using ductal carcinoma in situ as an outcome, the algorithm detected tumor-associated stroma in greater amounts and at larger distances from grade 3 versus grade 1 ductal carcinoma in situ. Collectively, these results suggest that algorithms based on deep convolutional neural networks that evaluate only stroma may prove useful to classify breast biopsies and aid in understanding and evaluating the biology of breast lesions.

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.

Antibodies against CD47, which block tumor cell CD47 interactions with macrophage signal regulatory protein-α, have been shown to decrease tumor size in hematological and epithelial tumor models by interfering with the protection from phagocytosis by macrophages that intact CD47 bestows upon tumor cells. Leiomyosarcoma (LMS) is a tumor of smooth muscle that can express varying levels of colony-stimulating factor-1 (CSF1), the expression of which correlates with the numbers of tumor-associated macrophages (TAMs) that are found in these tumors. We have previously shown that the presence of TAMs in LMS is associated with poor clinical outcome and the overall effect of TAMs in LMS therefore appears to be protumorigenic. However, the use of inhibitory antibodies against CD47 offers an opportunity to turn TAMs against LMS cells by allowing the phagocytic behavior of resident macrophages to predominate. Here we show that interference with CD47 increases phagocytosis of two human LMS cell lines, LMS04 and LMS05, in vitro. In addition, treatment of mice bearing subcutaneous LMS04 and LMS05 tumors with a novel, humanized anti-CD47 antibody resulted in significant reductions in tumor size. Mice bearing LMS04 tumors develop large numbers of lymph node and lung metastases. In a unique model for neoadjuvant treatment, mice were treated with anti-CD47 antibody starting 1 wk before resection of established primary tumors and subsequently showed a striking decrease in the size and number of metastases. These data suggest that treatment with anti-CD47 antibodies not only reduces primary tumor size but can also be used to inhibit the development of, or to eliminate, metastatic disease.

In a Perspective, Francisco Beca and Andrew Beck discuss Charles Swanton and colleagues' accompanying Research Article on somatic mutations in patients with inflammatory breast cancer treated in a Phase II clinical trial.

In this guest editorial, Andrew Beck discusses the importance of open access to big data for translating knowledge of cancer heterogeneity into better outcomes for cancer patients.In this guest editorial, Andrew Beck discusses the importance of open access to big data for translating knowledge of cancer heterogeneity into better outcomes for cancer patients.

Current clinical judgment in bladder cancer (BC) relies primarily on pathological stage and grade. We investigated whether a molecular classification of tumor cell differentiation, based on a developmental biology approach, can provide additional prognostic information. Exploiting large preexisting gene-expression databases, we developed a biologically supervised computational model to predict markers that correspond with BC differentiation. To provide mechanistic insight, we assessed relative tumorigenicity and differentiation potential via xenotransplantation. We then correlated the prognostic utility of the identified markers to outcomes within gene expression and formalin-fixed paraffin-embedded (FFPE) tissue datasets. Our data indicate that BC can be subclassified into three subtypes, on the basis of their differentiation states: basal, intermediate, and differentiated, where only the most primitive tumor cell subpopulation within each subtype is capable of generating xenograft tumors and recapitulating downstream populations. We found that keratin 14 (KRT14) marks the most primitive differentiation state that precedes KRT5 and KRT20 expression. Furthermore, KRT14 expression is consistently associated with worse prognosis in both univariate and multivariate analyses. We identify here three distinct BC subtypes on the basis of their differentiation states, each harboring a unique tumor-initiating population.

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.

Though patient sex influences response to cancer treatments, little is known of the molecular causes and cancer therapies are generally given irrespective of patient sex. We assessed transcriptomic differences in tumors from men and women spanning 17 cancer types and we assessed differential expression between tumor and normal samples stratified by sex across 7 cancers. We used the LincsCloud platform to perform Connectivity Map analyses to link transcriptomic signatures identified in male and female tumors with chemical and genetic perturbagens and we performed permutation testing to identify perturbagens that showed significantly differential connectivity with male and female tumors. Our analyses predicted that females are sensitive and males are resistant to tamoxifen treatment of lung adenocarcinoma, a finding which is consistent with known male-female differences in lung cancer. We made several novel predictions, including that CDK1 and PTPN1 knockdown would be more effective in males with hepatocellular carcinoma and SMAD3 and HSPA4 knockdown would be more effective in females with head and neck squamous cell carcinoma. Our results provide a new resource for researchers studying male-female biological and treatment response differences in human cancer. The complete results of our analyses are provided at the website accompanying this manuscript ( http://becklab.github.io/SexLinked ).