Deep Learning for Grading Endometrial Cancer.

Endometrial cancer is the fourth most common cancer in women in the United States; the lifetime risk for developing this disease is approximately 2.8%. Precise histologic evaluation and molecular classification of endometrial cancer are important for effective patient management and determining the best treatment modalities. This study introduces EndoNet, which uses convolutional neural networks for extracting histologic features and a vision transformer for aggregating these features and classifying slides based on their visual characteristics into high- and low-grade cases. The model was trained on 929 digitized hematoxylin and eosin-stained whole-slide images of endometrial cancer from hysterectomy cases at Dartmouth-Health. It classifies these slides into low-grade (endometrioid grades 1 and 2) and high-grade (endometrioid carcinoma International Federation of Gynecology and Obstetrics grade 3, uterine serous carcinoma, or carcinosarcoma) categories. EndoNet was evaluated on an internal test set of 110 patients and an external test set of 100 patients from The Cancer Genome Atlas public database. The model achieved a weighted average F1 score of 0.91 (95% CI, 0.86 to 0.95) and an area under the curve of 0.95 (95% CI, 0.89 to 0.99) on the internal test, and 0.86 (95% CI, 0.80 to 0.94) for F1 score and 0.86 (95% CI, 0.75 to 0.93) for area under the curve on the external test. Pending further validation, EndoNet has the potential to support pathologists without the need of manual annotations in classifying the grades of gynecologic pathology tumors.

Pharmacological induction of chromatin remodeling drives chemosensitization in triple-negative breast cancer.

Targeted therapies have improved outcomes for certain cancer subtypes, but cytotoxic chemotherapy remains a mainstay for triple-negative breast cancer (TNBC). The epithelial-to-mesenchymal transition (EMT) is a developmental program co-opted by cancer cells that promotes metastasis and chemoresistance. There are no therapeutic strategies specifically targeting mesenchymal-like cancer cells. We report that the US Food and Drug Administration (FDA)-approved chemotherapeutic eribulin induces ZEB1-SWI/SNF-directed chromatin remodeling to reverse EMT that curtails the metastatic propensity of TNBC preclinical models. Eribulin induces mesenchymal-to-epithelial transition (MET) in primary TNBC in patients, but conventional chemotherapy does not. In the treatment-naive setting, but not after acquired resistance to other agents, eribulin sensitizes TNBC cells to subsequent treatment with other chemotherapeutics. These findings provide an epigenetic mechanism of action of eribulin, supporting its use early in the disease process for MET induction to prevent metastatic progression and chemoresistance. These findings warrant prospective clinical evaluation of the chemosensitizing effects of eribulin in the treatment-naive setting.

Alteration of DNA methyltransferases by eribulin elicits broad DNA methylation changes with potential therapeutic implications for triple-negative breast cancer.

Background: Triple-negative breast cancer (TNBC) is an aggressive disease with limited treatment options. Eribulin, a chemotherapeutic drug, induces epigenetic changes in cancer cells, suggesting a unique mechanism of action. Materials & methods: MDA-MB 231 cells were treated with eribulin and paclitaxel, and the samples from 53 patients treated with neoadjuvant eribulin were compared with those from 14 patients who received the standard-of-care treatment using immunohistochemistry. Results: Eribulin treatment caused significant DNA methylation changes in drug-tolerant persister TNBC cells, and it also elicited changes in the expression levels of epigenetic modifiers (DNMT1, TET1, DNMT3A/B) in vitro and in primary TNBC tumors. Conclusion: These findings provide new insights into eribulin's mechanism of action and potential biomarkers for predicting TNBC treatment response.

Nonmetastatic Axillary Lymph Nodes Have Distinct Morphology and Immunophenotype in Obese Patients with Breast Cancer at Risk for Metastasis.

Obese patients with breast cancer have worse outcomes than their normal weight counterparts, with a 50% to 80% increased rate of axillary nodal metastasis. Recent studies suggest a link between increased lymph node adipose tissue and breast cancer nodal metastasis. Further investigation into potential mechanisms underlying this link may reveal potential prognostic utility of fat-enlarged lymph nodes in patients with breast cancer. This study used a deep learning model to identify morphologic differences in nonmetastatic axillary nodes between obese, node-positive, and node-negative patients with breast cancer. The model was developed using nested cross-validation on 180 cases and achieved an area under the receiver operator characteristic curve of 0.67 in differentiating patients using hematoxylin and eosin-stained whole slide images. The morphologic analysis of the predictive regions showed an increased average adipocyte size (P = 0.004), increased white space between lymphocytes (P < 0.0001), and increased red blood cells (P < 0.001) in nonmetastatic lymph nodes of node-positive patients. Preliminary immunohistochemistry analysis on a subset of 30 patients showed a trend of decreased CD3 expression and increased leptin expression in fat-replaced axillary lymph nodes of obese, node-positive patients. These findings suggest a novel direction to further investigate the interaction between lymph node adiposity, lymphatic dysfunction, and breast cancer nodal metastases, highlighting a possible prognostic tool for obese patients with breast cancer.

Sixteen-Year Institutional Review of Magnetic Resonance Imaging-Guided Breast Biopsies: Trends in Histologic Diagnoses With Radiologic Correlation.

Background: Breast magnetic resonance imaging (MRI) is an important imaging tool for the management of breast cancer patients and for screening women at high risk for breast cancer. Objectives: To examine long-term trends in the distribution of histologic diagnoses obtained from MRI-guided breast biopsies. Design: Retrospective analysis. Methods: We retrospectively reviewed the distribution of histologic diagnoses of MRI-guided breast biopsies from 2004 to 2019. All cases underwent central pathology review and lesions were classified based on the most prominent histologic finding present. Magnetic resonance imaging features were extracted from radiology reports when available and correlated with pathology diagnoses. Results: Four hundred ninety-four MRI-guided biopsies were performed on 440 patients; overall, 73% of biopsies were benign and 27% were malignant. The annual percentages of benign and malignant diagnoses remained similar throughout the 16-year period. Of the benign entities commonly identified, the percentage of benign papillary and sclerosing lesions detected in the benign biopsies increased significantly (13% in 2004-2011 vs 31% in 2012-2019, P = .03). The mean size of malignant lesions was larger than benign lesions (30.1 mm compared with 14.2 mm, P = .045); otherwise, there were no distinguishing radiologic features between benign and malignant lesions. Conclusion: The specificity of breast MRI remained constant over a 16-year period; however, there was a shift in the distribution of benign diagnoses with increased detection and biopsy of benign papillary and sclerosing lesions. Monitoring the distribution of breast MRI biopsy diagnoses over time with radiology-pathology correlation might improve the suboptimal specificity of breast MRI.

Near-Infrared Spectral Tomography for Predicting Residual Cancer Burden during Early-Stage Neoadjuvant Chemotherapy for Breast Cancer.

PURPOSE: The aim of this study is to investigate whether near-infrared spectral tomography (NIRST) might serve as a reliable prognostic tool to predict residual cancer burden (RCB) in patients with breast cancer undergoing neoadjuvant chemotherapy (NAC) based upon early treatment response measurements. EXPERIMENTAL DESIGN: A total of thirty-five patients with breast cancer receiving NAC were included in this study. NIRST imaging was performed at multiple time points, including: before treatment, at end of the first cycle, at the mid-point, and post-NAC treatments. From reconstructed NIRST images, average values of total hemoglobin (HbT) were obtained for both the tumor region and contralateral breast at each time point. RCB scores/classes were assessed by a pathologist using histologic slides of the surgical specimen obtained after completing NAC. Logistic regression of the normalized early percentage change of HbT in the tumor region (ΔHbT%) was used to predict RCB and determine its significance as an indicator for differentiating cases within each RCB class. RESULTS: The ΔHbT% at the end of the first cycle, as compared with pretreatment levels, showed excellent prognostic capability in differentiating RCB-0 from RCB-I/II/III or RCB-II from RCB-0/I/III (P < 0.001). Corresponding area under the curve (AUC) values for these comparisons were 0.97 and 0.94, and accuracy values were 0.90 and 0.83, respectively. CONCLUSIONS: NIRST holds promise as a potential clinical tool that can be seamlessly integrated into existing clinical workflow within the infusion suite. By providing early assessment of RCB, NIRST has potential to improve breast cancer patient management strategies.

Machine Learning-Based Prediction of Distant Recurrence in Invasive Breast Carcinoma Using Clinicopathological Data: A Cross-Institutional Study.

Breast cancer is the most common type of cancer worldwide. Alarmingly, approximately 30% of breast cancer cases result in disease recurrence at distant organs after treatment. Distant recurrence is more common in some subtypes such as invasive breast carcinoma (IBC). While clinicians have utilized several clinicopathological measurements to predict distant recurrences in IBC, no studies have predicted distant recurrences by combining clinicopathological evaluations of IBC tumors pre- and post-therapy with machine learning (ML) models. The goal of our study was to determine whether classification-based ML techniques could predict distant recurrences in IBC patients using key clinicopathological measurements, including pathological staging of the tumor and surrounding lymph nodes assessed both pre- and post-neoadjuvant therapy, response to therapy via standard-of-care imaging, and binary status of adjuvant therapy administered to patients. We trained and tested four clinicopathological ML models using a dataset (144 and 17 patients for training and testing, respectively) from Duke University and validated the best-performing model using an external dataset (8 patients) from Dartmouth Hitchcock Medical Center. The random forest model performed better than the C-support vector classifier, multilayer perceptron, and logistic regression models, yielding AUC values of 1.0 in the testing set and 0.75 in the validation set (p < 0.002) across both institutions, thereby demonstrating the cross-institutional portability and validity of ML models in the field of clinical research in cancer. The top-ranking clinicopathological measurement impacting the prediction of distant recurrences in IBC were identified to be tumor response to neoadjuvant therapy as evaluated via SOC imaging and pathology, which included tumor as well as node staging.

Alteration of DNMT1/DNMT3A by eribulin elicits global DNA methylation changes with potential therapeutic implications for triple-negative breast cancer.

Triple-negative breast cancer (TNBC) is an aggressive disease subtype with limited treatment options. Eribulin is a chemotherapeutic approved for the treatment of advanced breast cancer that has been shown to elicit epigenetic changes. We investigated the effect of eribulin treatment on genome-scale DNA methylation patterns in TNBC cells. Following repeated treatment, The results showed that eribulin-induced changes in DNA methylation patterns evident in persister cells. Eribulin also affected the binding of transcription factors to genomic ZEB1 binding sites and regulated several cellular pathways, including ERBB and VEGF signaling and cell adhesion. Eribulin also altered the expression of epigenetic modifiers including DNMT1, TET1, and DNMT3A/B in persister cells. Data from primary human TNBC tumors supported these findings: DNMT1 and DNMT3A levels were altered by eribulin treatment in human primary TNBC tumors. Our results suggest that eribulin modulates DNA methylation patterns in TNBC cells by altering the expression of epigenetic modifiers. These findings have clinical implications for using eribulin as a therapeutic agent.

Non-Metastatic Axillary Lymph Nodes Have Distinct Morphology and Immunophenotype in Obese Breast Cancer patients at Risk for Metastasis.

Obese patients have worse breast cancer outcomes than normal weight women including a 50% to 80% increased rate of axillary nodal metastasis. Recent studies have shown a potential link between increased lymph node adipose tissue and breast cancer nodal metastasis. Further investigation into potential mechanisms underlying this link may reveal potential prognostic utility of fat-enlarged lymph nodes in breast cancer patients. In this study, a deep learning framework was developed to identify morphological differences of non-metastatic axillary nodes between node-positive and node-negative obese breast cancer patients. Pathology review of the model-selected patches found an increase in the average size of adipocytes (p-value=0.004), an increased amount of white space between lymphocytes (p-value<0.0001), and an increased amount of red blood cells (p-value<0.001) in non-metastatic lymph nodes of node-positive breast cancer patients. Our downstream immunohistology (IHC) analysis showed a decrease of CD3 expression and increase of leptin expression in fat-replaced axillary lymph nodes in obese node-positive patients. In summary, our findings suggest a novel direction to further investigate the crosstalk between lymph node adiposity, lymphatic dysfunction, and breast cancer nodal metastases.

Pharmacological Induction of mesenchymal-epithelial transition chemosensitizes breast cancer cells and prevents metastatic progression.

The epithelial-mesenchymal transition (EMT) is a developmental program co-opted by tumor cells that aids the initiation of the metastatic cascade. Tumor cells that undergo EMT are relatively chemoresistant, and there are currently no therapeutic avenues specifically targeting cells that have acquired mesenchymal traits. We show that treatment of mesenchymal-like triple-negative breast cancer (TNBC) cells with the microtubule-destabilizing chemotherapeutic eribulin, which is FDA-approved for the treatment of advanced breast cancer, leads to a mesenchymal-epithelial transition (MET). This MET is accompanied by loss of metastatic propensity and sensitization to subsequent treatment with other FDA-approved chemotherapeutics. We uncover a novel epigenetic mechanism of action that supports eribulin pretreatment as a path to MET induction that curtails metastatic progression and the evolution of therapy resistance.

Exploring the Clinical Feasibility of Alternative Word-Understanding Measures for Autistic Children With Minimal Spoken Language.

PURPOSE: The primary aim of this study was to explore the clinical feasibility of using alternate word-understanding assessment modalities for autistic children who have minimal verbal skills. Specifically, assessment duration, occurrence of disruptive behavior, and no-response trials were examined across three word-understanding assessment conditions: a low-tech condition, a touchscreen condition, and a condition that used real-object stimuli. A secondary aim was to examine the relationship between disruptive behavior and assessment outcomes. METHOD: Twenty-seven autistic children between the ages of 3 and 12 years who had minimal verbal skills completed 12 test items on the three assessment conditions. Repeated-measures analyses of variance with post hoc Bonferroni procedures were used to describe and compare assessment duration, occurrence of disruptive behavior, and no-response trials across conditions. A Spearman rank-order correlation coefficient was used to examine the relationship between disruptive behavior and assessment outcomes. RESULTS: The real-object assessment condition took significantly longer than the low-tech and touchscreen conditions. Participants engaged in disruptive behavior most frequently during the low-tech condition; however, differences among conditions were not significant. There were significantly more no-response trials in the low-tech condition than in the touchscreen condition. There was a significant, weak negative correlation between disruptive behavior and experimental assessment outcomes. CONCLUSION: Results show there is promise in using real objects and touchscreen devices to assess word understanding in autistic children who have minimal verbal skills.

Lineage plasticity enables low-ER luminal tumors to evolve and gain basal-like traits.

Stratifying breast cancer into specific molecular or histologic subtypes aids in therapeutic decision-making and predicting outcomes; however, these subtypes may not be as distinct as previously thought. Patients with luminal-like, estrogen receptor (ER)-expressing tumors have better prognosis than patients with more aggressive, triple-negative or basal-like tumors. There is, however, a subset of luminal-like tumors that express lower levels of ER, which exhibit more basal-like features. We have found that breast tumors expressing lower levels of ER, traditionally considered to be luminal-like, represent a distinct subset of breast cancer characterized by the emergence of basal-like features. Lineage tracing of low-ER tumors in the MMTV-PyMT mouse mammary tumor model revealed that basal marker-expressing cells arose from normal luminal epithelial cells, suggesting that luminal-to-basal plasticity is responsible for the evolution and emergence of basal-like characteristics. This plasticity allows tumor cells to gain a new lumino-basal phenotype, thus leading to intratumoral lumino-basal heterogeneity. Single-cell RNA sequencing revealed SOX10 as a potential driver for this plasticity, which is known among breast tumors to be almost exclusively expressed in triple-negative breast cancer (TNBC) and was also found to be highly expressed in low-ER tumors. These findings suggest that basal-like tumors may result from the evolutionary progression of luminal tumors with low ER expression.

Periductal Stromal Tumor of the Breast with a TERT Promoter Mutation: First Case Report with Comprehensive Molecular Analysis.

The molecular pathogenesis of breast fibroepithelial tumors continues to be elucidated. Recently, highly recurrent MED12 mutations arising in exon 2 at codon 44 were discovered in fibroadenomas and phyllodes tumors. In addition, a high prevalence of TERT promoter mutations in two hotspots (124 and 126 bp upstream from the translation start site) was discovered in up to 65% of phyllodes tumors. Breast periductal stromal tumors are a potentially distinct category of fibroepithelial lesions that are exceptionally rare with controversial classification and pathogenesis. Herein, we report the first comprehensive molecular genetic workup of a breast periductal stromal tumor that harbored a TERT promoter -124C > T mutation, supporting a relation to phyllodes tumors.

Phenotypic heterogeneity driven by plasticity of the intermediate EMT state governs disease progression and metastasis in breast cancer.

The epithelial-to-mesenchymal transition (EMT) is frequently co-opted by cancer cells to enhance migratory and invasive cell traits. It is a key contributor to heterogeneity, chemoresistance, and metastasis in many carcinoma types, where the intermediate EMT state plays a critical tumor-initiating role. We isolate multiple distinct single-cell clones from the SUM149PT human breast cell line spanning the EMT spectrum having diverse migratory, tumor-initiating, and metastatic qualities, including three unique intermediates. Using a multiomics approach, we identify CBFß as a key regulator of metastatic ability in the intermediate state. To quantify epithelial-mesenchymal heterogeneity within tumors, we develop an advanced multiplexed immunostaining approach using SUM149-derived orthotopic tumors and find that the EMT state and epithelial-mesenchymal heterogeneity are predictive of overall survival in a cohort of stage III breast cancer. Our model reveals previously unidentified insights into the complex EMT spectrum and its regulatory networks, as well as the contributions of epithelial-mesenchymal plasticity (EMP) in tumor heterogeneity in breast cancer.

What's new in breast pathology 2022: WHO 5th edition and biomarker updates.

The 5th edition WHO Classification of Breast Tumours (2019) has introduced changes to our practices. Highlights are presented below, with a focus on modifications to morphological subtype categorization. In addition, we summarize important updates to ER and PR testing made in the 2020 ASCO/CAP guidelines, and briefly discuss PD-L1 and Ki-67 testing in breast cancer.

Quantifying the Epithelial-to-Mesenchymal Transition (EMT) from Bench to Bedside.

The epithelial-to-mesenchymal transition (EMT) and its reversal, the mesenchymal-to-epithelial transition (MET) are critical components of the metastatic cascade in breast cancer and many other solid tumor types. Recent work has uncovered the presence of a variety of states encompassed within the EMT spectrum, each of which may play unique roles or work collectively to impact tumor progression. However, defining EMT status is not routinely carried out to determine patient prognosis or dictate therapeutic decision-making in the clinic. Identifying and quantifying the presence of various EMT states within a tumor is a critical first step to scoring patient tumors to aid in determining prognosis. Here, we review the major strides taken towards translating our understanding of EMT biology from bench to bedside. We review previously used approaches including basic immunofluorescence staining, flow cytometry, single-cell sequencing, and multiplexed tumor mapping. Future studies will benefit from the consideration of multiple methods and combinations of markers in designing a diagnostic tool for detecting and measuring EMT in patient tumors.

Decrease in the Size of Fat-Enlarged Axillary Lymph Nodes and Serum Lipids after Bariatric Surgery.

BACKGROUND: Ectopic fat deposition in obesity is associated with organ dysfunction; however, little is known about fat deposition within the lymphatic system and associated lymphatic dysfunction. METHODS: One hundred fifty-five women who underwent routine screening mammography before and after a Roux-en-y gastric bypass or a sleeve gastrectomy were retrospectively reviewed and after excluding women without visible nodes both before and after bariatric surgery, 84 patients were included in the final analysis. Axillary lymph node size, patient weight in kilograms, body mass index, and a diagnosis of hypertension, type 2 diabetes, and dyslipidemia were evaluated before and after surgery. Binary linear regression models and Fischer's exact test were used to evaluate the relationship between the size of fat-infiltrated axillary lymph nodes, patient age, change in patient weight, and diagnosis of hypertension, type 2 diabetes, and dyslipidemia. RESULTS: Fat-infiltrated axillary lymph nodes demonstrated a statistically significant decrease in size after bariatric surgery with a mean decrease of 4.23 mm (95% CI: 3.23 to 5.2, p < 0.001). The resolution of dyslipidemia was associated with a decrease in lymph node size independent of weight loss (p = 0.006). CONCLUSIONS: Mammographically visualized fat-infiltrated axillary lymph nodes demonstrated a statistically significant decrease in size after bariatric surgery. The decrease in lymph node size was significantly associated with the resolution of dyslipidemia, independent of weight loss, age, and type of surgery.

Alternative receptive language assessment modalities and stimuli for autistic children who are minimally verbal.

LAY ABSTRACT: It is difficult to measure language comprehension abilities in autistic children who have limited expressive language skills. Results from available assessments may underestimate autistic children's receptive language skills. The primary purpose of this study was to compare alternative modalities and stimuli used to measure receptive vocabulary skills in autistic children who are minimally verbal. This study compared participants' outcomes on three different receptive vocabulary assessment conditions: an assessment that used a low-tech stimulus book, a touchscreen assessment, and an assessment that used real-object stimuli. Twenty-seven students between the ages of 3 and 12 who had minimal verbal skills and a diagnosis of autism spectrum disorder participated in this study. Results showed that participants' scores in the real-object assessment condition were significantly higher than in the low-tech condition and marginally higher than scores in the touchscreen condition. These results suggest real-object stimuli may provide a more robust measure of autistic children's receptive vocabulary skills than traditional low-tech picture stimuli. Although many direct standardized assessments use picture stimuli to measure word understanding, when assessing autistic individuals who have limited expressive language, real objects can be used in replacement of, or in addition to, picture stimuli.

Detecting spatially co-expressed gene clusters with functional coherence by graph-regularized convolutional neural network.

MOTIVATION: Clustering spatial-resolved gene expression is an essential analysis to reveal gene activities in the underlying morphological context by their functional roles. However, conventional clustering analysis does not consider gene expression co-localizations in tissue for detecting spatial expression patterns or functional relationships among the genes for biological interpretation in the spatial context. In this article, we present a convolutional neural network (CNN) regularized by the graph of protein-protein interaction (PPI) network to cluster spatially resolved gene expression. This method improves the coherence of spatial patterns and provides biological interpretation of the gene clusters in the spatial context by exploiting the spatial localization by convolution and gene functional relationships by graph-Laplacian regularization. RESULTS: In this study, we tested clustering the spatially variable genes or all expressed genes in the transcriptome in 22 Visium spatial transcriptomics datasets of different tissue sections publicly available from 10× Genomics and spatialLIBD. The results demonstrate that the PPI-regularized CNN constantly detects gene clusters with coherent spatial patterns and significantly enriched by gene functions with the state-of-the-art performance. Additional case studies on mouse kidney tissue and human breast cancer tissue suggest that the PPI-regularized CNN also detects spatially co-expressed genes to define the corresponding morphological context in the tissue with valuable insights. AVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/kuanglab/CNN-PReg. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Fat-enlarged axillary lymph nodes are associated with node-positive breast cancer in obese patients.

PURPOSE: Obesity associated fat infiltration of organ systems is accompanied by organ dysfunction and poor cancer outcomes. Obese women demonstrate variable degrees of fat infiltration of axillary lymph nodes (LNs), and they are at increased risk for node-positive breast cancer. However, the relationship between enlarged axillary nodes and axillary metastases has not been investigated. The purpose of this study is to evaluate the association between axillary metastases and fat-enlarged axillary nodes visualized on mammograms and breast MRI in obese women with a diagnosis of invasive breast cancer. METHODS: This retrospective case-control study included 431 patients with histologically confirmed invasive breast cancer. The primary analysis of this study included 306 patients with pre-treatment and pre-operative breast MRI and body mass index (BMI) > 30 (201 node-positive cases and 105 randomly selected node-negative controls) diagnosed with invasive breast cancer between April 1, 2011, and March 1, 2020. The largest visible LN was measured in the axilla contralateral to the known breast cancer on breast MRI. Multivariate logistic regression models were used to assess the association between node-positive status and LN size adjusting for age, BMI, tumor size, tumor grade, tumor subtype, and lymphovascular invasion. RESULTS: A strong likelihood of node-positive breast cancer was observed among obese women with fat-expanded lymph nodes (adjusted OR for the 4th vs. 1st quartile for contralateral LN size on MRI: 9.70; 95% CI 4.26, 23.50; p < 0.001). The receiver operating characteristic curve for size of fat-enlarged nodes in the contralateral axilla identified on breast MRI had an area under the curve of 0.72 for predicting axillary metastasis, and this increased to 0.77 when combined with patient and tumor characteristics. CONCLUSION: Fat expansion of axillary lymph nodes was associated with a high likelihood of axillary metastases in obese women with invasive breast cancer independent of BMI and tumor characteristics.