Tissue-resident FOLR2+ macrophages associate with CD8+ T cell infiltration in human breast cancer.

Macrophage infiltration is a hallmark of solid cancers, and overall macrophage infiltration correlates with lower patient survival and resistance to therapy. Tumor-associated macrophages, however, are phenotypically and functionally heterogeneous. Specific subsets of tumor-associated macrophage might be endowed with distinct roles on cancer progression and antitumor immunity. Here, we identify a discrete population of FOLR2+ tissue-resident macrophages in healthy mammary gland and breast cancer primary tumors. FOLR2+ macrophages localize in perivascular areas in the tumor stroma, where they interact with CD8+ T cells. FOLR2+ macrophages efficiently prime effector CD8+ T cells ex vivo. The density of FOLR2+ macrophages in tumors positively correlates with better patient survival. This study highlights specific roles for tumor-associated macrophage subsets and paves the way for subset-targeted therapeutic interventions in macrophages-based cancer therapies.

A spatially resolved single-cell genomic atlas of the adult human breast.

The adult human breast is comprised of an intricate network of epithelial ducts and lobules that are embedded in connective and adipose tissue1-3. Although most previous studies have focused on the breast epithelial system4-6, many of the non-epithelial cell types remain understudied. Here we constructed the comprehensive Human Breast Cell Atlas (HBCA) at single-cell and spatial resolution. Our single-cell transcriptomics study profiled 714,331 cells from 126 women, and 117,346 nuclei from 20 women, identifying 12 major cell types and 58 biological cell states. These data reveal abundant perivascular, endothelial and immune cell populations, and highly diverse luminal epithelial cell states. Spatial mapping using four different technologies revealed an unexpectedly rich ecosystem of tissue-resident immune cells, as well as distinct molecular differences between ductal and lobular regions. Collectively, these data provide a reference of the adult normal breast tissue for studying mammary biology and diseases such as breast cancer.

The epithelial polarity axis controls the resting membrane potential and Cl- co-transport in breast glandular structures.

The membrane potential (MP) controls cell homeostasis by directing molecule transport and gene expression. How the MP is set upon epithelial differentiation is unknown. Given that tissue architecture also controls homeostasis, we investigated the relationship between basoapical polarity and resting MP in three-dimensional culture of the HMT-3522 breast cancer progression. A microelectrode technique to measure MP and input resistance reveals that the MP is raised by gap junction intercellular communication (GJIC), which directs tight-junction mediated apical polarity, and is decreased by the Na+/K+/2Cl- (NKCC, encoded by SLC12A1 and SLC12A2) co-transporter, active in multicellular structures displaying basal polarity. In the tumor counterpart, the MP is reduced. Cancer cells display diminished GJIC and do not respond to furosemide, implying loss of NKCC activity. Induced differentiation of cancer cells into basally polarized multicellular structures restores widespread GJIC and NKCC responses, but these structures display the lowest MP. The absence of apical polarity, necessary for cancer onset, in the non-neoplastic epithelium is also associated with the lowest MP under active Cl- transport. We propose that the loss of apical polarity in the breast epithelium destabilizes cellular homeostasis in part by lowering the MP.

Breast-Conserving Surgery with or without Irradiation in Early Breast Cancer.

BACKGROUND: Limited level 1 evidence is available on the omission of radiotherapy after breast-conserving surgery in older women with hormone receptor-positive early breast cancer receiving adjuvant endocrine therapy. METHODS: We performed a phase 3 randomized trial of the omission of irradiation; the trial population included women 65 years of age or older who had hormone receptor-positive, node-negative, T1 or T2 primary breast cancer (with tumors ≤3 cm in the largest dimension) treated with breast-conserving surgery with clear excision margins and adjuvant endocrine therapy. Patients were randomly assigned to receive whole-breast irradiation (40 to 50 Gy) or no irradiation. The primary end point was local breast cancer recurrence. Regional recurrence, breast cancer-specific survival, distant recurrence as the first event, and overall survival were also assessed. RESULTS: A total of 1326 women were enrolled; 658 were randomly assigned to receive whole-breast irradiation and 668 to receive no irradiation. The median follow-up was 9.1 years. The cumulative incidence of local breast cancer recurrence within 10 years was 9.5% (95% confidence interval [CI], 6.8 to 12.3) in the no-radiotherapy group and 0.9% (95% CI, 0.1 to 1.7) in the radiotherapy group (hazard ratio, 10.4; 95% CI, 4.1 to 26.1; P<0.001). Although local recurrence was more common in the group that did not receive radiotherapy, the 10-year incidence of distant recurrence as the first event was not higher in the no-radiotherapy group than in the radiotherapy group, at 1.6% (95% CI, 0.4 to 2.8) and 3.0% (95% CI, 1.4 to 4.5), respectively. Overall survival at 10 years was almost identical in the two groups, at 80.8% (95% CI, 77.2 to 84.3) with no radiotherapy and 80.7% (95% CI, 76.9 to 84.3) with radiotherapy. The incidence of regional recurrence and breast cancer-specific survival also did not differ substantially between the two groups. CONCLUSIONS: Omission of radiotherapy was associated with an increased incidence of local recurrence but had no detrimental effect on distant recurrence as the first event or overall survival among women 65 years of age or older with low-risk, hormone receptor-positive early breast cancer. (Funded by the Chief Scientist Office of the Scottish Government and the Breast Cancer Institute, Western General Hospital, Edinburgh; ISRCTN number, ISRCTN95889329.).

Paracrine and autocrine signals induce and maintain mesenchymal and stem cell states in the breast.

The epithelial-mesenchymal transition (EMT) has been associated with the acquisition of motility, invasiveness, and self-renewal traits. During both normal development and tumor pathogenesis, this change in cell phenotype is induced by contextual signals that epithelial cells receive from their microenvironment. The signals that are responsible for inducing an EMT and maintaining the resulting cellular state have been unclear. We describe three signaling pathways, involving transforming growth factor (TGF)-ß and canonical and noncanonical Wnt signaling, that collaborate to induce activation of the EMT program and thereafter function in an autocrine fashion to maintain the resulting mesenchymal state. Downregulation of endogenously synthesized inhibitors of autocrine signals in epithelial cells enables the induction of the EMT program. Conversely, disruption of autocrine signaling by added inhibitors of these pathways inhibits migration and self-renewal in primary mammary epithelial cells and reduces tumorigenicity and metastasis by their transformed derivatives.

HyperTMO: a trusted multi-omics integration framework based on hypergraph convolutional network for patient classification.

MOTIVATION: The rapid development of high-throughput biomedical technologies can provide researchers with detailed multi-omics data. The multi-omics integrated analysis approach based on machine learning contributes a more comprehensive perspective to human disease research. However, there are still significant challenges in representing single-omics data and integrating multi-omics information. RESULTS: This article presents HyperTMO, a Trusted Multi-Omics integration framework based on Hypergraph convolutional network for patient classification. HyperTMO constructs hypergraph structures to represent the association between samples in single-omics data, then evidence extraction is performed by hypergraph convolutional network, and multi-omics information is integrated at an evidence level. Last, we experimentally demonstrate that HyperTMO outperforms other state-of-the-art methods in breast cancer subtype classification and Alzheimer's disease classification tasks using multi-omics data from TCGA (BRCA) and ROSMAP datasets. Importantly, HyperTMO is the first attempt to integrate hypergraph structure, evidence theory, and multi-omics integration for patient classification. Its accurate and robust properties bring great potential for applications in clinical diagnosis. AVAILABILITY AND IMPLEMENTATION: HyperTMO and datasets are publicly available at https://github.com/ippousyuga/HyperTMO.

Risk of male breast cancer after Hodgkin lymphoma.

Female survivors of Hodgkin lymphoma (HL) treated with chest radiotherapy have a strongly increased risk of breast cancer (BC), but the treatment-specific BC risk in male survivors of HL has not been evaluated. We assessed BC risk in a cohort of 3077 male survivors of 5-year HL treated at age ≤51 years in 20 Dutch hospitals between 1965 and 2013. We estimated standardized incidence ratios (SIRs), absolute excess risks per 10 000 person-years, and cumulative BC incidences. After a 20-year median follow-up, we observed 8 cases of male with BC. Male survivors of HL experienced a 23-fold (95% confidence interval [CI], 10.1-46.0) increased BC risk compared with the general population, representing 1.6 (95% CI, 0.7-3.3) excess BC incidences per 10 000 person-years. The 20- and 40-year cumulative BC incidences after HL treatment were 0.1% (95% CI, 0.02-0.3) and 0.7% (95% CI, 0.3-1.4), respectively. Treatment with chest radiotherapy without alkylating chemotherapy yielded a strongly increased SIR (20.7; 95% CI, 2.5-74.8), which was not significantly different for chest radiotherapy and alkylating chemotherapy (41.1; 95% CI, 13.4-96.0). Males treated with chest radiotherapy and anthracyclines had an SIR of 48.1 (95% CI, 13.1-123.1). Two patients died from BC (median follow-up, 4.7 years). To ensure early diagnosis and treatment, clinicians should be alert to BC symptoms in male survivors of HL.

Effect of the p-Estrogen Receptor at Serine on Its Function and Breast Growth.

BACKGROUND: Estrogen receptor (ER) signaling plays an important role in the development and functional differentiation of the breast and participates in the process of breast cancer. Activated ER can affect various aspects of the cell's behavior, including proliferation, via modulating the expression of many downstream target genes. Phosphorylation is one of the activation pathways of ER. However, the relationship between estrogen receptor phosphorylation sites and breast development and carcinogenesis is not clear. METHODS: Using Crisper-Cas9 gene editing technology, we constructed ER S309A mutant mice. Using carmine staining of the mammary gland of mice at different developmental stages, we examined the breast development of ER S309A mice. Using hematoxylin-eosin (HE) staining of vaginal smears of mice at the same time for 5 consecutive days, we measured the vaginal epithelial keratinocytes. RESULTS: We established ER S309A mutant mice and observed breast defects in ER S309A mice. In addition, we observed decreased reproductive ability, and estrous cycle disorder in ER S309A mice. The number of vaginal epithelial keratino-cytes in the estrous cycle of ER S309A mice was decreased. CONCLUSION: These results suggest that the phosphorylation site of ER at Serine 309 is important for ER function and breast development.

Detailed DNA methylation characterisation of phyllodes tumours identifies a signature of malignancy and distinguishes phyllodes from metaplastic breast carcinoma.

Phyllodes tumours (PTs) are rare fibroepithelial lesions of the breast that are classified as benign, borderline, or malignant. As little is known about the molecular underpinnings of PTs, current diagnosis relies on histological examination. However, accurate classification is often difficult, particularly for distinguishing borderline from malignant PTs. Furthermore, PTs can be misdiagnosed as other tumour types with shared histological features, such as fibroadenoma and metaplastic breast cancers. As DNA methylation is a recognised hallmark of many cancers, we hypothesised that DNA methylation could provide novel biomarkers for diagnosis and tumour stratification in PTs, whilst also allowing insight into the molecular aetiology of this otherwise understudied tumour. We generated whole-genome methylation data using the Illumina EPIC microarray in a novel PT cohort (n = 33) and curated methylation microarray data from published datasets including PTs and other potentially histopathologically similar tumours (total n = 817 samples). Analyses revealed that PTs have a unique methylome compared to normal breast tissue and to potentially histopathologically similar tumours (metaplastic breast cancer, fibroadenoma and sarcomas), with PT-specific methylation changes enriched in gene sets involved in KRAS signalling and epithelial-mesenchymal transition. Next, we identified 53 differentially methylated regions (DMRs) (false discovery rate < 0.05) that specifically delineated malignant from non-malignant PTs. The top DMR in both discovery and validation cohorts was hypermethylation at the HSD17B8 CpG island promoter. Matched PT single-cell expression data showed that HSD17B8 had minimal expression in fibroblast (putative tumour) cells. Finally, we created a methylation classifier to distinguish PTs from metaplastic breast cancer samples, where we revealed a likely misdiagnosis for two TCGA metaplastic breast cancer samples. In conclusion, DNA methylation alterations are associated with PT histopathology and hold the potential to improve our understanding of PT molecular aetiology, diagnostics, and risk stratification. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

PALB2-mutated human mammary cells display a broad spectrum of morphological and functional abnormalities induced by increased TGFß signaling.

Heterozygous mutations in any of three major genes, BRCA1, BRCA2 and PALB2, are associated with high-risk hereditary breast cancer susceptibility frequently seen as familial disease clustering. PALB2 is a key interaction partner and regulator of several vital cellular activities of BRCA1 and BRCA2, and is thus required for DNA damage repair and alleviation of replicative and oxidative stress. Little is however known about how PALB2-deficiency affects cell function beyond that, especially in the three-dimensional setting, and also about its role during early steps of malignancy development. To answer these questions, we have generated biologically relevant MCF10A mammary epithelial cell lines with mutations that are comparable to certain clinically important PALB2 defects. We show in a non-cancerous background how both mono- and biallelically PALB2-mutated cells exhibit gross spontaneous DNA damage and mitotic aberrations. Furthermore, PALB2-deficiency disturbs three-dimensional spheroid morphology, increases the migrational capacity and invasiveness of the cells, and broadly alters their transcriptome profiles. TGFß signaling and KRT14 expression are enhanced in PALB2-mutated cells and their inhibition and knock down, respectively, lead to partial restoration of cell functions. KRT14-positive cells are also more abundant with DNA damage than KRT14-negative cells. The obtained results indicate comprehensive cellular changes upon PALB2 mutations, even in the presence of half dosage of wild type PALB2 and demonstrate how PALB2 mutations may predispose their carriers to malignancy.

Redefining normal breast cell populations using long noncoding RNAs.

Single-cell RNAseq has allowed unprecedented insight into gene expression across different cell populations in normal tissue and disease states. However, almost all studies rely on annotated gene sets to capture gene expression levels and sequencing reads that do not align to known genes are discarded. Here, we discover thousands of long noncoding RNAs (lncRNAs) expressed in human mammary epithelial cells and analyze their expression in individual cells of the normal breast. We show that lncRNA expression alone can discriminate between luminal and basal cell types and define subpopulations of both compartments. Clustering cells based on lncRNA expression identified additional basal subpopulations, compared to clustering based on annotated gene expression, suggesting that lncRNAs can provide an additional layer of information to better distinguish breast cell subpopulations. In contrast, these breast-specific lncRNAs poorly distinguish brain cell populations, highlighting the need to annotate tissue-specific lncRNAs prior to expression analyses. We also identified a panel of 100 breast lncRNAs that could discern breast cancer subtypes better than protein-coding markers. Overall, our results suggest that lncRNAs are an unexplored resource for new biomarker and therapeutic target discovery in the normal breast and breast cancer subtypes.

A brain-enriched lncRNA shields cancer cells from immune-mediated killing for metastatic colonization in the brain.

Brain metastases, including prevalent breast-to-brain metastasis (B2BM), represent an urgent unmet medical need in the care of cancer due to a lack of effective therapies. Immune evasion is essential for cancer cells to metastasize to the brain tissue for brain metastasis. However, the intrinsic genetic circuits that enable cancer cells to avoid immune-mediated killing in the brain microenvironment remain poorly understood. Here, we report that a brain-enriched long noncoding RNA (BMOR) expressed in B2BM cells is required for brain metastasis development and is both necessary and sufficient to drive cancer cells to colonize the brain tissue. Mechanistically, BMOR enables cancer cells to evade immune-mediated killing in the brain microenvironment for the development of brain metastasis by binding and inactivating IRF3. In preclinical brain metastasis murine models, locked nucleic acid-BMOR, a designed silencer targeting BMOR, is effective in suppressing the metastatic colonization of cancer cells in the brain for brain metastasis. Taken together, our study reveals a mechanism underlying B2BM immune evasion during cancer cell metastatic colonization of brain tissue for brain metastasis, where B2BM cells evade immune-mediated killing in the brain microenvironment by acquiring a brain-enriched long noncoding RNA genetic feature.

Single-Cell Transcription Mapping of Murine and Human Mammary Organoids Responses to Female Hormones.

During female adolescence and pregnancy, rising levels of hormones result in a cyclic source of signals that control the development of mammary tissue. While such alterations are well understood from a whole-gland perspective, the alterations that such hormones bring to organoid cultures derived from mammary glands have yet to be fully mapped. This is of special importance given that organoids are considered suitable systems to understand cross species breast development. Here we utilized single-cell transcriptional profiling to delineate responses of murine and human normal breast organoid systems to female hormones across evolutionary distinct species. Collectively, our study represents a molecular atlas of epithelial dynamics in response to estrogen and pregnancy hormones.

A novel preclinical model of the normal human breast.

Improved screening and treatment have decreased breast cancer mortality, although incidence continues to rise. Women at increased risk of breast cancer can be offered risk reducing treatments, such as tamoxifen, but this has not been shown to reduce breast cancer mortality. New, more efficacious, risk-reducing agents are needed. The identification of novel candidates for prevention is hampered by a lack of good preclinical models. Current patient derived in vitro and in vivo models cannot fully recapitulate the complexities of the human tissue, lacking human extracellular matrix, stroma, and immune cells, all of which are known to influence therapy response. Here we describe a normal breast explant model utilising a tuneable hydrogel which maintains epithelial proliferation, hormone receptor expression, and residency of T cells and macrophages over 7 days. Unlike other organotypic tissue cultures which are often limited by hyper-proliferation, loss of hormone signalling, and short treatment windows (< 48h), our model shows that tissue remains viable over 7 days with none of these early changes. This offers a powerful and unique opportunity to model the normal breast and study changes in response to various risk factors, such as breast density and hormone exposure. Further validation of the model, using samples from patients undergoing preventive therapies, will hopefully confirm this to be a valuable tool, allowing us to test novel agents for breast cancer risk reduction preclinically.

Recent advancements in artificial intelligence for breast cancer: Image augmentation, segmentation, diagnosis, and prognosis approaches.

Breast cancer is a significant global health burden, with increasing morbidity and mortality worldwide. Early screening and accurate diagnosis are crucial for improving prognosis. Radiographic imaging modalities such as digital mammography (DM), digital breast tomosynthesis (DBT), magnetic resonance imaging (MRI), ultrasound (US), and nuclear medicine techniques, are commonly used for breast cancer assessment. And histopathology (HP) serves as the gold standard for confirming malignancy. Artificial intelligence (AI) technologies show great potential for quantitative representation of medical images to effectively assist in segmentation, diagnosis, and prognosis of breast cancer. In this review, we overview the recent advancements of AI technologies for breast cancer, including 1) improving image quality by data augmentation, 2) fast detection and segmentation of breast lesions and diagnosis of malignancy, 3) biological characterization of the cancer such as staging and subtyping by AI-based classification technologies, 4) prediction of clinical outcomes such as metastasis, treatment response, and survival by integrating multi-omics data. Then, we then summarize large-scale databases available to help train robust, generalizable, and reproducible deep learning models. Furthermore, we conclude the challenges faced by AI in real-world applications, including data curating, model interpretability, and practice regulations. Besides, we expect that clinical implementation of AI will provide important guidance for the patient-tailored management.

Chromatograms and Mass Spectra of High-Mannose and Paucimannose N-Glycans for Rapid Isomeric Identifications.

N-Linked glycosylation is one of the most essential post-translational modifications of proteins. However, N-glycan structural determination remains challenging because of the small differences in structures between isomers. In this study, we constructed a database containing collision-induced dissociation MSn mass spectra and chromatograms of high-performance liquid chromatography for the rapid identification of high-mannose and paucimannose N-glycan isomers. These N-glycans include isomers by breaking of arbitrary numbers of glycosidic bonds at arbitrary positions of canonical Man9GlcNAc2 N-glycans. In addition, some GlcMannGlcNAc2 N-glycan isomers were included in the database. This database is particularly useful for the identification of the N-glycans not in conventional N-glycan standards. This study demonstrated the application of the database to structural assignment for high-mannose N-glycans extracted from bovine whey proteins, soybean proteins, human mammary epithelial cells, and human breast carcinoma cells. We found many N-glycans that are not expected to be generated by conventional biosynthetic pathways of multicellular eukaryotes.

Overexpression of malic enzyme is involved in breast cancer growth and is correlated with poor prognosis.

Malic enzyme (ME) genes are key functional metabolic enzymes playing a crucial role in carcinogenesis. However, the detailed effects of ME gene expression on breast cancer progression remain unclear. Here, our results revealed ME1 expression was significantly upregulated in breast cancer, especially in patients with oestrogen receptor/progesterone receptor-negative and human epidermal growth factor receptor 2-positive breast cancer. Furthermore, upregulation of ME1 was significantly associated with more advanced pathological stages (p < 0.001), pT stage (p < 0.001) and tumour grade (p < 0.001). Kaplan-Meier analysis revealed ME1 upregulation was associated with poor disease-specific survival (DSS: p = 0.002) and disease-free survival (DFS: p = 0.003). Multivariate Cox regression analysis revealed ME1 upregulation was significantly correlated with poor DSS (adjusted hazard ratio [AHR] = 1.65; 95% CI: 1.08-2.52; p = 0.021) and DFS (AHR, 1.57; 95% CI: 1.03-2.41; p = 0.038). Stratification analysis indicated ME1 upregulation was significantly associated with poor DSS (p = 0.039) and DFS (p = 0.038) in patients with non-triple-negative breast cancer (TNBC). However, ME1 expression did not affect the DSS of patients with TNBC. Biological function analysis revealed ME1 knockdown could significantly suppress the growth of breast cancer cells and influence its migration ability. Furthermore, the infiltration of immune cells was significantly reduced when they were co-cultured with breast cancer cells with ME1 knockdown. In summary, ME1 plays an oncogenic role in the growth of breast cancer; it may serve as a potential biomarker of progression and constitute a therapeutic target in patients with breast cancer.

Spatial N-glycomics of the normal breast microenvironment reveals fucosylated and high-mannose N-glycan signatures related to BI-RADS density and ancestry.

Higher breast cancer mortality rates continue to disproportionally affect black women (BW) compared to white women (WW). This disparity is largely due to differences in tumor aggressiveness that can be related to distinct ancestry-associated breast tumor microenvironments (TMEs). Yet, characterization of the normal microenvironment (NME) in breast tissue and how they associate with breast cancer risk factors remains unknown. N-glycans, a glucose metabolism-linked post-translational modification, has not been characterized in normal breast tissue. We hypothesized that normal female breast tissue with distinct Breast Imaging and Reporting Data Systems (BI-RADS) categories have unique microenvironments based on N-glycan signatures that varies with genetic ancestries. Profiles of N-glycans were characterized in normal breast tissue from BW (n = 20) and WW (n = 20) at risk for breast cancer using matrix assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI). A total of 176 N-glycans (32 core-fucosylated and 144 noncore-fucosylated) were identified in the NME. We found that certain core-fucosylated, outer-arm fucosylated and high-mannose N-glycan structures had specific intensity patterns and histological distributions in the breast NME dependent on BI-RADS densities and ancestry. Normal breast tissue from BW, and not WW, with heterogeneously dense breast densities followed high-mannose patterns as seen in invasive ductal and lobular carcinomas. Lastly, lifestyles factors (e.g. age, menopausal status, Gail score, BMI, BI-RADS) differentially associated with fucosylated and high-mannose N-glycans based on ancestry. This study aims to decipher the molecular signatures in the breast NME from distinct ancestries towards improving the overall disparities in breast cancer burden.

A genome-wide association study of contralateral breast cancer in the Women's Environmental Cancer and Radiation Epidemiology Study.

BACKGROUND: Contralateral breast cancer (CBC) is the most common second primary cancer diagnosed in breast cancer survivors, yet the understanding of the genetic susceptibility of CBC, particularly with respect to common variants, remains incomplete. This study aimed to investigate the genetic basis of CBC to better understand this malignancy. FINDINGS: We performed a genome-wide association analysis in the Women's Environmental Cancer and Radiation Epidemiology (WECARE) Study of women with first breast cancer diagnosed at age < 55 years including 1161 with CBC who served as cases and 1668 with unilateral breast cancer (UBC) who served as controls. We observed two loci (rs59657211, 9q32, SLC31A2/FAM225A and rs3815096, 6p22.1, TRIM31) with suggestive genome-wide significant associations (P < 1 × 10-6). We also found an increased risk of CBC associated with a breast cancer-specific polygenic risk score (PRS) comprised of 239 known breast cancer susceptibility single nucleotide polymorphisms (SNPs) (rate ratio per 1-SD change: 1.25; 95% confidence interval 1.14-1.36, P < 0.0001). The protective effect of chemotherapy on CBC risk was statistically significant only among patients with an elevated PRS (Pheterogeneity = 0.04). The AUC that included the PRS and known breast cancer risk factors was significantly elevated. CONCLUSIONS: The present GWAS identified two previously unreported loci with suggestive genome-wide significance. We also confirm that an elevated risk of CBC is associated with a comprehensive breast cancer susceptibility PRS that is independent of known breast cancer risk factors. These findings advance our understanding of genetic risk factors involved in CBC etiology.

Improving lesion detection in mammograms by leveraging a Cycle-GAN-based lesion remover.

BACKGROUND: The wide heterogeneity in the appearance of breast lesions and normal breast structures can confuse computerized detection algorithms. Our purpose was therefore to develop a Lesion Highlighter (LH) that can improve the performance of computer-aided detection algorithms for detecting breast cancer on screening mammograms. METHODS: We hypothesized that a Cycle-GAN based Lesion Remover (LR) could act as an LH, which can improve the performance of lesion detection algorithms. We used 10,310 screening mammograms from 4,832 women that included 4,942 recalled lesions (BI-RADS 0) and 5,368 normal results (BI-RADS 1). We divided the dataset into Train:Validate:Test folds with the ratios of 0.64:0.16:0.2. We segmented image patches (400 × 400 pixels) from either lesions marked by MQSA radiologists or normal tissue in mammograms. We trained a Cycle-GAN to develop two GANs, where each GAN transferred the style of one image to another. We refer to the GAN transferring the style of a lesion to normal breast tissue as the LR. We then highlighted the lesion by color-fusing the mammogram after applying the LR to its original. Using ResNet18, DenseNet201, EfficientNetV2, and Vision Transformer as backbone architectures, we trained three deep networks for each architecture, one trained on lesion highlighted mammograms (Highlighted), another trained on the original mammograms (Baseline), and Highlighted and Baseline combined (Combined). We conducted ROC analysis for the three versions of each deep network on the test set. RESULTS: The Combined version of all networks achieved AUCs ranging from 0.963 to 0.974 for identifying the image with a recalled lesion from a normal breast tissue image, which was statistically improved (p-value < 0.001) over their Baseline versions with AUCs that ranged from 0.914 to 0.967. CONCLUSIONS: Our results showed that a Cycle-GAN based LR is effective for enhancing lesion conspicuity and this can improve the performance of a detection algorithm.