Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer.

BACKGROUND: Pathological complete response (pCR) is associated with favorable prognosis in patients with triple-negative breast cancer (TNBC). However, only 30-40% of TNBC patients treated with neoadjuvant chemotherapy (NAC) show pCR, while the remaining 60-70% show residual disease (RD). The role of the tumor microenvironment in NAC response in patients with TNBC remains unclear. In this study, we developed a machine learning-based two-step pipeline to distinguish between various histological components in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of TNBC tissue biopsies and to identify histological features that can predict NAC response. METHODS: H&E-stained WSIs of treatment-naïve biopsies from 85 patients (51 with pCR and 34 with RD) of the model development cohort and 79 patients (41 with pCR and 38 with RD) of the validation cohort were separated through a stratified eightfold cross-validation strategy for the first step and leave-one-out cross-validation strategy for the second step. A tile-level histology label prediction pipeline and four machine-learning classifiers were used to analyze 468,043 tiles of WSIs. The best-trained classifier used 55 texture features from each tile to produce a probability profile during testing. The predicted histology classes were used to generate a histology classification map of the spatial distributions of different tissue regions. A patient-level NAC response prediction pipeline was trained with features derived from paired histology classification maps. The top graph-based features capturing the relevant spatial information across the different histological classes were provided to the radial basis function kernel support vector machine (rbfSVM) classifier for NAC treatment response prediction. RESULTS: The tile-level prediction pipeline achieved 86.72% accuracy for histology class classification, while the patient-level pipeline achieved 83.53% NAC response (pCR vs. RD) prediction accuracy of the model development cohort. The model was validated with an independent cohort with tile histology validation accuracy of 83.59% and NAC prediction accuracy of 81.01%. The histological class pairs with the strongest NAC response predictive ability were tumor and tumor tumor-infiltrating lymphocytes for pCR and microvessel density and polyploid giant cancer cells for RD. CONCLUSION: Our machine learning pipeline can robustly identify clinically relevant histological classes that predict NAC response in TNBC patients and may help guide patient selection for NAC treatment.

A spatial attention guided deep learning system for prediction of pathological complete response using breast cancer histopathology images.

MOTIVATION: Predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) patients accurately is direly needed for clinical decision making. pCR is also regarded as a strong predictor of overall survival. In this work, we propose a deep learning system to predict pCR to NAC based on serial pathology images stained with hematoxylin and eosin and two immunohistochemical biomarkers (Ki67 and PHH3). To support human prior domain knowledge-based guidance and enhance interpretability of the deep learning system, we introduce a human knowledge-derived spatial attention mechanism to inform deep learning models of informative tissue areas of interest. For each patient, three serial breast tumor tissue sections from biopsy blocks were sectioned, stained in three different stains and integrated. The resulting comprehensive attention information from the image triplets is used to guide our prediction system for prognostic tissue regions. RESULTS: The experimental dataset consists of 26 419 pathology image patches of 1000×1000 pixels from 73 TNBC patients treated with NAC. Image patches from randomly selected 43 patients are used as a training dataset and images patches from the rest 30 are used as a testing dataset. By the maximum voting from patch-level results, our proposed model achieves a 93% patient-level accuracy, outperforming baselines and other state-of-the-art systems, suggesting its high potential for clinical decision making. AVAILABILITY AND IMPLEMENTATION: The codes, the documentation and example data are available on an open source at: https://github.com/jkonglab/PCR_Prediction_Serial_WSIs_biomarkers. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Barriers to breast cancer screening in Atlanta, GA: results from the Pink Panel survey at faith-based institutions.

PURPOSE: Our research sought to describe barriers to mammography screening among a sample of predominantly Black women in metropolitan Atlanta, Georgia. METHODS: The Pink Panel project convened community leaders from faith-based institutions to administer an offline survey to women via convenience sampling at fourteen churches in Atlanta in late 2019 and early 2020. With the COVID-19 pandemic, the research team switched to an online survey. The survey included seven questions about breast cancer awareness, barriers to breast cancer screening, and screening status. We used residence information to attain the 9-digit zip code to link to the Area Deprivation Index at the Census Block Group neighborhood level. We report results as descriptive statistics of the barriers to mammography screening. RESULTS: The 643 women represented 21 counties in Georgia, predominantly from metropolitan Atlanta, and 86% identified as Black. Among women aged 40 and older, 90% have ever had a mammogram. Among all women, 79% have ever had a mammogram, and 86% indicated that they would get a mammogram if offered in their neighborhood. The top barriers to mammography screening were lack of health insurance and high cost. Barriers to mammography screening did not differ substantially by Area Deprivation Index. CONCLUSION: Among metropolitan Atlanta women aged 40+ , nearly all reported ever having a mammogram. However, addressing the barriers, including lack of health insurance and high cost, that women reported may further improve mammography screening rates.

Exosomal Metabolic Signatures Are Associated with Differential Response to Neoadjuvant Chemotherapy in Patients with Breast Cancer.

Neoadjuvant chemotherapy (NAC) is commonly used in breast cancer (BC) patients to increase eligibility for breast-conserving surgery. Only 30% of patients with BC show pathologic complete response (pCR) after NAC, and residual disease (RD) is associated with poor long-term prognosis. A critical barrier to improving NAC outcomes in patients with BC is the limited understanding of the mechanisms underlying differential treatment outcomes. In this study, we evaluated the ability of exosomal metabolic profiles to predict NAC response in patients with BC. Exosomes isolated from the plasma of patients after NAC were used for metabolomic analyses to identify exosomal metabolic signatures associated with the NAC response. Among the 16 BC patients who received NAC, eight had a pCR, and eight had RD. Patients with RD had 2.52-fold higher exosome concentration in their plasma than those with pCR and showed significant enrichment of various metabolic pathways, including citrate cycle, urea cycle, porphyrin metabolism, glycolysis, and gluconeogenesis. Additionally, the relative exosomal levels of succinate and lactate were significantly higher in patients with RD than in those with pCR. These data suggest that plasma exosomal metabolic signatures could be associated with differential NAC outcomes in BC patients and provide insight into the metabolic determinants of NAC response in patients with BC.

A Case Series Exploration of Multi-Regional Expression Heterogeneity in Triple-Negative Breast Cancer Patients.

Extensive intratumoral heterogeneity (ITH) is believed to contribute to therapeutic failure and tumor recurrence, as treatment-resistant cell clones can survive and expand. However, little is known about ITH in triple-negative breast cancer (TNBC) because of the limited number of single-cell sequencing studies on TNBC. In this study, we explored ITH in TNBC by evaluating gene expression-derived and imaging-derived multi-region differences within the same tumor. We obtained tissue specimens from 10 TNBC patients and conducted RNA sequencing analysis of 2-4 regions per tumor. We developed a novel analysis framework to dissect and characterize different types of variability: between-patients (inter-tumoral heterogeneity), between-patients across regions (inter-tumoral and region heterogeneity), and within-patient, between-regions (regional intratumoral heterogeneity). We performed a Bayesian changepoint analysis to assess and classify regional variability as low (convergent) versus high (divergent) within each patient feature (TNBC and PAM50 subtypes, immune, stroma, tumor counts and tumor infiltrating lymphocytes). Gene expression signatures were categorized into three types of variability: between-patients (108 genes), between-patients across regions (183 genes), and within-patients, between-regions (778 genes). Based on the between-patient gene signature, we identified two distinct patient clusters that differed in menopausal status. Significant intratumoral divergence was observed for PAM50 classification, tumor cell counts, and tumor-infiltrating T cell abundance. Other features examined showed a representation of both divergent and convergent results. Lymph node stage was significantly associated with divergent tumors. Our results show extensive intertumoral heterogeneity and regional ITH in gene expression and image-derived features in TNBC. Our findings also raise concerns regarding gene expression based TNBC subtyping. Future studies are warranted to elucidate the role of regional heterogeneity in TNBC as a driver of treatment resistance.

QNBC Is Associated with High Genomic Instability Characterized by Copy Number Alterations and miRNA Deregulation.

Triple-negative breast cancer (TNBC) can be further classified into androgen receptor (AR)-positive TNBC and AR-negative TNBC or quadruple-negative breast cancer (QNBC). Here, we investigated genomic instability in 53 clinical cases by array-CGH and miRNA expression profiling. Immunohistochemical analysis revealed that 64% of TNBC samples lacked AR expression. This group of tumors exhibited a higher level of copy number alterations (CNAs) and a higher frequency of cases affected by CNAs than TNBCs. CNAs in genes of the chromosome instability 25 (CIN25) and centrosome amplification (CA) signatures were more frequent in the QNBCs and were similar between the groups, respectively. However, expression levels of CIN25 and CA20 genes were higher in QNBCs. miRNA profiling revealed 184 differentially expressed miRNAs between the groups. Fifteen of these miRNAs were mapped at cytobands with CNAs, of which eight (miR-1204, miR-1265, miR-1267, miR-23c, miR-548ai, miR-567, miR-613, and miR-943), and presented concordance of expression and copy number levels. Pathway enrichment analysis of these miRNAs/mRNAs pairings showed association with genomic instability, cell cycle, and DNA damage response. Furthermore, the combined expression of these eight miRNAs robustly discriminated TNBCs from QNBCs (AUC = 0.946). Altogether, our results suggest a significant loss of AR in TNBC and a profound impact in genomic instability characterized by CNAs and deregulation of miRNA expression.

Quadruple-negative breast cancer: novel implications for a new disease.

Based on the androgen receptor (AR) expression, triple-negative breast cancer (TNBC) can be subdivided into AR-positive TNBC and AR-negative TNBC, also known as quadruple-negative breast cancer (QNBC). QNBC characterization and treatment is fraught with many challenges. In QNBC, there is a greater paucity of prognostic biomarkers and therapeutic targets than AR-positive TNBC. Although the prognostic role of AR in TNBC remains controversial, many studies revealed that a lack of AR expression confers a more aggressive disease course. Literature characterizing QNBC tumor biology and uncovering novel biomarkers for improved management of the disease remains scarce. In this comprehensive review, we summarize the current QNBC landscape and propose avenues for future research, suggesting potential biomarkers and therapeutic strategies that warrant investigation.

A novel prognostic two-gene signature for triple negative breast cancer.

The absence of a robust risk stratification tool for triple negative breast cancer (TNBC) underlies imprecise and nonselective treatment of these patients with cytotoxic chemotherapy. This study aimed to interrogate transcriptomes of TNBC resected samples using next generation sequencing to identify novel biomarkers associated with disease outcomes. A subset of cases (n = 112) from a large, well-characterized cohort of primary TNBC (n = 333) were subjected to RNA-sequencing. Reads were aligned to the human reference genome (GRCH38.83) using the STAR aligner and gene expression quantified using HTSEQ. We identified genes associated with distant metastasis-free survival and breast cancer-specific survival by applying supervised artificial neural network analysis with gene selection to the RNA-sequencing data. The prognostic ability of these genes was validated using the Breast Cancer Gene-Expression Miner v4. 0 and Genotype 2 outcome datasets. Multivariate Cox regression analysis identified a prognostic gene signature that was independently associated with poor prognosis. Finally, we corroborated our results from the two-gene prognostic signature by their protein expression using immunohistochemistry. Artificial neural network identified two gene panels that strongly predicted distant metastasis-free survival and breast cancer-specific survival. Univariate Cox regression analysis of 21 genes common to both panels revealed that the expression level of eight genes was independently associated with poor prognosis (p < 0.05). Adjusting for clinicopathological factors including patient's age, grade, nodal stage, tumor size, and lymphovascular invasion using multivariate Cox regression analysis yielded a two-gene prognostic signature (ACSM4 and SPDYC), which was associated with poor prognosis (p < 0.05) independent of other prognostic variables. We validated the protein expression of these two genes, and it was significantly associated with patient outcome in both independent and combined manner (p < 0.05). Our study identifies a prognostic gene signature that can predict prognosis in TNBC patients and could potentially be used to guide the clinical management of TNBC patients.

Machine learning-based prediction of breast cancer growth rate in vivo.

BACKGROUND: Determining the rate of breast cancer (BC) growth in vivo, which can predict prognosis, has remained elusive despite its relevance for treatment, screening recommendations and medicolegal practice. We developed a model that predicts the rate of in vivo tumour growth using a unique study cohort of BC patients who had two serial mammograms wherein the tumour, visible in the diagnostic mammogram, was missed in the first screen. METHODS: A serial mammography-derived in vivo growth rate (SM-INVIGOR) index was developed using tumour volumes from two serial mammograms and time interval between measurements. We then developed a machine learning-based surrogate model called Surr-INVIGOR using routinely assessed biomarkers to predict in vivo rate of tumour growth and extend the utility of this approach to a larger patient population. Surr-INVIGOR was validated using an independent cohort. RESULTS: SM-INVIGOR stratified discovery cohort patients into fast-growing versus slow-growing tumour subgroups, wherein patients with fast-growing tumours experienced poorer BC-specific survival. Our clinically relevant Surr-INVIGOR stratified tumours in the discovery cohort and was concordant with SM-INVIGOR. In the validation cohort, Surr-INVIGOR uncovered significant survival differences between patients with fast-growing and slow-growing tumours. CONCLUSION: Our Surr-INVIGOR model predicts in vivo BC growth rate during the pre-diagnostic stage and offers several useful applications.

Extremely Elevated Prostate-Specific Antigen in Acute Prostatitis: A Case Report.

Elevated prostate-specific antigen (PSA) levels are mostly suggestive of prostate cancer, but they are elevated in non-cancerous prostatic conditions as well. However, extreme levels of PSA as reported here have not been observed in cases other than prostatic cancer so far. Our patient had a significantly elevated PSA of 1,398 ng/mL in acute prostatitis. The purpose of this case report is to review the patient's atypical and rare presentation of extremely high PSA in acute prostatitis in the background of benign prostatic hyperplasia (BPH) and chronic prostatitis.

Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer.

Background: Pathological complete response (pCR) is associated with favorable prognosis in patients with triple-negative breast cancer (TNBC). However, only 30-40% of TNBC patients treated with neoadjuvant chemotherapy (NAC) show pCR, while the remaining 60-70% show residual disease (RD). The role of the tumor microenvironment (TME) in NAC response in patients with TNBC remains unclear. In this study, we developed a machine learning-based two-step pipeline to distinguish between various histological components in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of TNBC tissue biopsies and to identify histological features that can predict NAC response. Methods: H&E-stained WSIs of treatment-naïve biopsies from 85 patients (51 with pCR and 34 with RD) were separated through a stratified 8-fold cross validation strategy for the first step and leave one out cross validation strategy for the second step. A tile-level histology label prediction pipeline and four machine learning classifiers were used to analyze 468,043 tiles of WSIs. The best-trained classifier used 55 texture features from each tile to produce a probability profile during testing. The predicted histology classes were used to generate a histology classification map of the spatial distributions of different tissue regions. A patient-level NAC response prediction pipeline was trained with features derived from paired histology classification maps. The top graph-based features capturing the relevant spatial information across the different histological classes were provided to the radial basis function kernel support vector machine (rbfSVM) classifier for NAC treatment response prediction. Results: The tile-level prediction pipeline achieved 86.72% accuracy for histology class classification, while the patient-level pipeline achieved 83.53% NAC response (pCR vs. RD) prediction accuracy. The histological class pairs with the strongest NAC response predictive ability were tumor and tumor tumor-infiltrating lymphocytes for pCR and microvessel density and polyploid giant cancer cells for RD. Conclusion: Our machine learning pipeline can robustly identify clinically relevant histological classes that predict NAC response in TNBC patients and may help guide patient selection for NAC treatment.

Associations between health insurance status, neighborhood deprivation, and treatment delays in women with breast cancer living in Georgia.

BACKGROUND: Little is known regarding the association between insurance status and treatment delays in women with breast cancer and whether this association varies by neighborhood socioeconomic deprivation status. METHODS: In this cohort study, we used medical record data of women diagnosed with breast cancer between 2004 and 2022 at two Georgia-based healthcare systems. Treatment delay was defined as >90 days to surgery or >120 days to systemic treatment. Insurance coverage was categorized as private, Medicaid, Medicare, other public, or uninsured. Area deprivation index (ADI) was used as a proxy for neighborhood-level socioeconomic status. Associations between delayed treatment and insurance status were analyzed using logistic regression, with an interaction term assessing effect modification by ADI. RESULTS: Of the 14,195 women with breast cancer, 54% were non-Hispanic Black and 52% were privately insured. Compared with privately insured patients, those who were uninsured, Medicaid enrollees, and Medicare enrollees had 79%, 75%, and 27% higher odds of delayed treatment, respectively (odds ratio [OR]: 1.79, 95% confidence interval [CI]: 1.32-2.43; OR: 1.75, 95% CI: 1.43-2.13; OR: 1.27, 95% CI: 1.06-1.51). Among patients living in low-deprivation areas, those who were uninsured, Medicaid enrollees, and Medicare enrollees had 100%, 84%, and 26% higher odds of delayed treatment than privately insured patients (OR: 2.00, 95% CI: 1.44-2.78; OR: 1.84, 95% CI: 1.48-2.30; OR: 1.26, 95% CI: 1.05-1.53). No differences in the odds of delayed treatment by insurance status were observed in patients living in high-deprivation areas. DISCUSSION/CONCLUSION: Insurance status was associated with treatment delays for women living in low-deprivation neighborhoods. However, for women living in neighborhoods with high deprivation, treatment delays were observed regardless of insurance status.

PLK1 and AURKB phosphorylate survivin differentially to affect proliferation in racially distinct triple-negative breast cancer.

Protein diversity due to alternative mRNA splicing or post-translational modifications (PTMs) plays a vital role in various cellular functions. The mitotic kinases polo-like kinase 1 (PLK1) and Aurora B (AURKB) phosphorylate survivin, an inhibitor of apoptosis (IAP) family member, thereby regulating cell proliferation. PLK1, AURKB, and survivin are overexpressed in triple-negative breast cancer (TNBC), an aggressive breast cancer subtype. TNBC is associated with high proliferative capacity, high rates of distant metastasis, and treatment resistance. The proliferation-promoting protein survivin and its activating kinases, PLK1 and AURKB, are overexpressed in TNBC. In this study, we investigated the role of survivin phosphorylation in racial disparities in TNBC cell proliferation. Analysis of TCGA TNBC data revealed higher expression levels of PLK1 (P = 0.026) and AURKB (P = 0.045) in African Americans (AAs; n = 41) than in European Americans (EAs; n = 86). In contrast, no significant racial differences in survivin mRNA or protein levels were observed. AA TNBC cells exhibited higher p-survivin levels than EA TNBC cells. Survivin silencing using small interfering RNAs significantly attenuated cell proliferation and cell cycle progression in AA TNBC cells, but not in EA TNBC cells. In addition, PLK1 and AURKB inhibition with volasertib and barasertib significantly inhibited the growth of AA TNBC xenografts, but not of EA TNBC tumors. These data suggest that inhibition of PLK1 and AURKB suppresses cell proliferation and tumor growth, specifically in AA TNBC. These findings suggest that targeting survivin phosphorylation may be a viable therapeutic option for AA patients with TNBC.

Predicting neoadjuvant treatment response in triple-negative breast cancer using machine learning.

Background: Neoadjuvant chemotherapy (NAC) is the standard treatment for early-stage triple negative breast cancer (TNBC). The primary endpoint of NAC is a pathological complete response (pCR). NAC results in pCR in only 30%â€"40% of TNBC patients. Tumor-infiltrating lymphocytes (TILs), Ki67 and phosphohistone H3 (pH3) are a few known biomarkers to predict NAC response. Currently, systematic evaluation of the combined value of these biomarkers in predicting NAC response is lacking. In this study, the predictive value of markers derived from H&E and IHC stained biopsy tissue was comprehensively evaluated using a supervised machine learning (ML)-based approach. Identifying predictive biomarkers could help guide therapeutic decisions by enabling precise stratification of TNBC patients into responders and partial or non-responders. Methods: Serial sections from core needle biopsies (n=76) were stained with H&E, and immunohistochemically for the Ki67 and pH3 markers, followed by whole slide image (WSI) generation. The resulting WSI triplets were co-registered with H&E WSIs serving as the reference. Separate mask region-based CNN (MRCNN) models were trained with annotated H&E, Ki67 and pH3 images for detecting tumor cells, stromal and intratumoral TILs (sTILs and tTILs), Ki67 + , and pH3 + cells. Top image patches with a high density of cells of interest were identified as hotspots. Best classifiers for NAC response prediction were identified by training multiple ML models, and evaluating their performance by accuracy, area under curve, and confusion matrix analyses. Results: Highest prediction accuracy was achieved when hotspot regions were identified by tTIL counts and each hotspot was represented by measures of tTILs, sTILs, tumor cells, Ki67 + , and pH3 + features. Regardless of the hotspot selection metric, a complementary use of multiple histological features (tTILs, sTILs) and molecular biomarkers (Ki67 and pH3) resulted in top ranked performance at the patient level. Conclusions: Overall, our results emphasize that prediction models for NAC response should be based on biomarkers in combination rather than in isolation. Our study provides compelling evidence to support the use of ML-based models to predict NAC response in patients with TNBC.

Deep learning based registration of serial whole-slide histopathology images in different stains.

For routine pathology diagnosis and imaging-based biomedical research, Whole-slide image (WSI) analyses have been largely limited to a 2D tissue image space. For a more definitive tissue representation to support fine-resolution spatial and integrative analyses, it is critical to extend such tissue-based investigations to a 3D tissue space with spatially aligned serial tissue WSIs in different stains, such as Hematoxylin and Eosin (H&E) and Immunohistochemistry (IHC) biomarkers. However, such WSI registration is technically challenged by the overwhelming image scale, the complex histology structure change, and the significant difference in tissue appearances in different stains. The goal of this study is to register serial sections from multi-stain histopathology whole-slide image blocks. We propose a novel translation-based deep learning registration network CGNReg that spatially aligns serial WSIs stained in H&E and by IHC biomarkers without prior deformation information for the model training. First, synthetic IHC images are produced from H&E slides through a robust image synthesis algorithm. Next, the synthetic and the real IHC images are registered through a Fully Convolutional Network with multi-scaled deformable vector fields and a joint loss optimization. We perform the registration at the full image resolution, retaining the tissue details in the results. Evaluated with a dataset of 76 breast cancer patients with 1 H&E and 2 IHC serial WSIs for each patient, CGNReg presents promising performance as compared with multiple state-of-the-art systems in our evaluation. Our results suggest that CGNReg can produce promising registration results with serial WSIs in different stains, enabling integrative 3D tissue-based biomedical investigations.

Predicting Neoadjuvant Treatment Response in Triple-Negative Breast Cancer Using Machine Learning.

BACKGROUND: Neoadjuvant chemotherapy (NAC) is the standard treatment for early-stage triple negative breast cancer (TNBC). The primary endpoint of NAC is a pathological complete response (pCR). NAC results in pCR in only 30-40% of TNBC patients. Tumor-infiltrating lymphocytes (TILs), Ki67 and phosphohistone H3 (pH3) are a few known biomarkers to predict NAC response. Currently, systematic evaluation of the combined value of these biomarkers in predicting NAC response is lacking. In this study, the predictive value of markers derived from H&E and IHC stained biopsy tissue was comprehensively evaluated using a supervised machine learning (ML)-based approach. Identifying predictive biomarkers could help guide therapeutic decisions by enabling precise stratification of TNBC patients into responders and partial or non-responders. METHODS: Serial sections from core needle biopsies (n = 76) were stained with H&E and immunohistochemically for the Ki67 and pH3 markers, followed by whole-slide image (WSI) generation. The serial section stains in H&E stain, Ki67 and pH3 markers formed WSI triplets for each patient. The resulting WSI triplets were co-registered with H&E WSIs serving as the reference. Separate mask region-based CNN (MRCNN) models were trained with annotated H&E, Ki67 and pH3 images for detecting tumor cells, stromal and intratumoral TILs (sTILs and tTILs), Ki67+, and pH3+ cells. Top image patches with a high density of cells of interest were identified as hotspots. Best classifiers for NAC response prediction were identified by training multiple ML models and evaluating their performance by accuracy, area under curve, and confusion matrix analyses. RESULTS: Highest prediction accuracy was achieved when hotspot regions were identified by tTIL counts and each hotspot was represented by measures of tTILs, sTILs, tumor cells, Ki67+, and pH3+ features. Regardless of the hotspot selection metric, a complementary use of multiple histological features (tTILs, sTILs) and molecular biomarkers (Ki67 and pH3) resulted in top ranked performance at the patient level. CONCLUSIONS: Overall, our results emphasize that prediction models for NAC response should be based on biomarkers in combination rather than in isolation. Our study provides compelling evidence to support the use of ML-based models to predict NAC response in patients with TNBC.

Association of Race and Area Deprivation With Breast Cancer Survival Among Black and White Women in the State of Georgia.

Importance: Increasing evidence suggests that low socioeconomic status and geographic residence in disadvantaged neighborhoods contribute to disparities in breast cancer outcomes. However, little epidemiological research has sought to better understand these disparities within the context of location. Objective: To examine the association between neighborhood deprivation and racial disparities in mortality among Black and White patients with breast cancer in the state of Georgia. Design, Setting, and Participants: This population-based cohort study collected demographic and geographic data from patients diagnosed with breast cancer between January 1, 2004, and February 11, 2020, in 3 large health care systems in Georgia. A total of 19 580 patients with breast cancer were included: 12 976 from Piedmont Healthcare, 2285 from Grady Health System, and 4319 from Emory Healthcare. Data were analyzed from October 2, 2020, to August 11, 2022. Exposures: Area deprivation index (ADI) scores were assigned to each patient based on their residential census block group. The ADI was categorized into quartile groups, and associations between ADI and race and ADI × race interaction were examined. Main Outcomes and Measures: Cox proportional hazards regression models were used to compute hazard ratios (HRs) and 95% CIs associating ADI with overall mortality by race. Kaplan-Meier curves were used to visualize mortality stratified across racial and ADI groups. Results: Of the 19 580 patients included in the analysis (mean [SD] age at diagnosis, 58.8 [13.2] years), 3777 (19.3%) died during the course of the study. Area deprivation index contributed differently to breast cancer outcomes for Black and White women. In multivariable-adjusted models, living in a neighborhood with a greater ADI (more deprivation) was associated with increased mortality for White patients with breast cancer; compared with the ADI quartile of less than 25 (least deprived), increased mortality HRs were found in quartiles of 25 to 49 (1.22 [95% CI, 1.07-1.39]), 50 to 74 (1.32 [95% CI, 1.13-1.53]), and 75 or greater (1.33 [95% CI, 1.07-1.65]). However, an increase in the ADI quartile group was not associated with changes in mortality for Black patients with breast cancer (quartile 25 to 49: HR, 0.81 [95% CI, 0.61-1.07]; quartile 50 to 74: HR, 0.91 [95% CI, 0.70-1.18]; and quartile ≥75: HR, 1.05 [95% CI, 0.70-1.36]). In neighborhoods with an ADI of 75 or greater, no racial disparity was observed in mortality (HR, 1.11 [95% CI, 0.92-1.36]). Conclusions and Relevance: Black women with breast cancer had higher mortality than White women in Georgia, but this disparity was not explained by ADI: among Black patients, low ADI was not associated with lower mortality. This lack of association warrants further investigation to inform community-level approaches that may mitigate the existing disparities in breast cancer outcomes in Georgia.

Spatial Attention-Based Deep Learning System for Breast Cancer Pathological Complete Response Prediction with Serial Histopathology Images in Multiple Stains.

In triple negative breast cancer (TNBC) treatment, early prediction of pathological complete response (PCR) from chemotherapy before surgical operations is crucial for optimal treatment planning. We propose a novel deep learning-based system to predict PCR to neoadjuvant chemotherapy for TNBC patients with multi-stained histopathology images of serial tissue sections. By first performing tumor cell detection and recognition in a cell detection module, we produce a set of feature maps that capture cell type, shape, and location information. Next, a newly designed spatial attention module integrates such feature maps with original pathology images in multiple stains for enhanced PCR prediction in a dedicated prediction module. We compare it with baseline models that either use a single-stained slide or have no spatial attention module in place. Our proposed system yields 78.3% and 87.5% of accuracy for patch-, and patient-level PCR prediction, respectively, outperforming all other baseline models. Additionally, the heatmaps generated from the spatial attention module can help pathologists in targeting tissue regions important for disease assessment. Our system presents high efficiency and effectiveness and improves interpretability, making it highly promising for immediate clinical and translational impact.

Sleep Pattern and Problems in Young Children Visiting Outpatient Department of a Tertiary Level Hospital in Kathmandu, Nepal.

BACKGROUND: Sleep is an important parameter of a child's growth and development. The pattern and duration of sleep varies with age. Sleep problems are a common occurrence during childhood days, and these problems that establish in childhood are presumed to continue later in life. Many times, parental concerns regarding their child's sleep problems like difficulty in putting to sleep, frequent night time awakening, and waking up early are overlooked during their visits to the hospital. OBJECTIVE: The aim of this study was to find out the sleep patterns and problems of children aged six to thirty-six months. Methodology. A cross-sectional study was conducted at the pediatric outpatient department of Kathmandu Medical College Teaching Hospital from October, 2019 till March, 2020. Two hundred and forty-nine respondents were chosen purposively and were given questionnaires to be filled out. Research instrument was a standard, Nepali version of a structured questionnaire called Brief Infant Sleep Questionnaire (BISQ) which contained questions related to sleep parameters and sleep problems existing among young children of 6-36 months. Mean, standard deviation, frequencies, and Kruskal Wallis test were used for statistical analysis. RESULTS: The mean duration of total sleep was 12.12 ± 2.00 hours, while that of night sleep was 9.22 ± 1.19 hours and mean daytime nap was 2.90 ± 1.66 hours. Most of the children (96%) coslept with their parents, and 55% of the children had feeding as a bedtime ritual. Overall, 19.6% of the children had sleep problems as identified by BISQ although only 5.6% of the parents perceived that their children had it. CONCLUSIONS: Sleep problems were present among young Nepalese children included in our study, and sleep assessment should be a part of every health checkup for children.

SARS-CoV-2 Infection in Cancer Patients: Effects on Disease Outcomes and Patient Prognosis.

The severity of coronavirus disease 2019 (COVID-19) symptoms and outcomes vary immensely among patients. Predicting disease progression and managing disease symptoms is even more challenging in cancer patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Cancer therapies, including chemotherapy, radiotherapy, and immunotherapy, often suppress the immune system, rendering cancer patients more susceptible to SARS-CoV-2 infection and the development of severe complications. However, data on the effects of immunosuppression on COVID-19 outcomes in cancer patients remain limited. Further investigations are warranted to better understand the implications of SARS-CoV-2 infection in cancer patients, particularly those that are immunocompromised. In this review, we outline the current knowledge of the effects of SARS-CoV-2 infection in cancer patients.