On discovery of novel hub genes for ER+ and TN breast cancer types through RNA seq data analyses and classification models.

Breast cancer (BC) is a malignant neoplasm which is classified into various types defined by underlying molecular factors such as estrogen receptor positive (ER+), progesterone receptor positive (PR+), human epidermal growth factor positive (HER2+) and triple negative (TNBC). Early detection of ER+ and TNBC is crucial in the choice of diagnosis and appropriate treatment strategy. Here we report the key genes associated to ER+ and TNBC using RNA-Seq analysis and machine learning models. Three ER+ and TNBC RNA seq datasets comprising 164 patients in-toto were selected for standard NGS hierarchical data processing and data analyses protocols. Enrichment pathway analysis and network analysis was done and finally top hub genes were identified. To come with a reliable classifier which could distinguish the distinct transcriptome patterns associated to ER+ and TNBC, ML models were built employing Naïve Bayes, SVM and kNN. 1730 common DEG's exhibiting significant logFC values with 0.05 p-value threshold were identified. A list of top ten hub genes were screened on the basis of maximal clique centrality (MCC) which included CDC20, CDK1, BUB1, AURKA, CDCA8, RRM2, TTK, CENPF, CEP55 and NDC80.These genes were found to be involved in crucial cell cycle pathways. k-Nearest Neighbor (kNN) model was observed to be best classifier with accuracy 84%, specificity 66% and sensitivity 95% to differentiate between ER+ and TNBC RNA-Seq transcriptomes. Our screened list of 10 hub genes can thus help unearth novel molecular signatures implicated in ER+ and TNBC onset, prognosis and design of novel protocols for breast cancer diagnostics and therapeutics.

Imaging Features and World Health Organization Classification of Rare Breast Tumors.

Breast radiologists encounter unusual lesions, which may not be well described in the literature. Previously based on histologic and molecular classifications, the World Health Organization (WHO) classification of tumors has become increasingly multidisciplinary. Familiarity with imaging features and basic pathology of infrequent breast lesions, as well as their current classification according to the WHO, may help the radiologist evaluate biopsy results for concordance and help direct the management of uncommon breast lesions. This review article provides a case-based review of imaging features and WHO histologic classification of rare breast tumors.

[BIRADS 0 patient reclassification in a first-level of care unit]. / Reclasificación de pacientes BIRADS 0 en una unidad de primer nivel de atención.

Background: In Mexico and the world, breast cancer is the cancer type with the highest incidence and mortality for women. Its incidence has increased due to a higher life expectancy and a higher exposure to risk factors. Screening is done by mammography using the BIRADS (Breast Imaging Reporting and Data System) system, the standard for mammography screening report which classifies lesions assigning recommendations for patient follow-up. The system goes from 0 (not conclusive) to 6 (demonstrated malignancy), being of interest for this study the BIRADS 0 category. Objective: To describe patients classified as BIRADS 0 by mammography and their reclassification in a first-level hospital during 2021. Material and methods: Retrospective, descriptive, cross-sectional, observational study. Women over 40 years with a BIRADS 0 result were studied. The following databases were used: Institutional Cancer Registry, Family Medicine Information System, Electronic Clinical File, and the mammography and patient list from preventive medicine. Results: Reclassification by ultrasound (US) was achieved in 100% of patients, in all of the BIRADS US categories. In 3.8% of BIRADS 0 patients, ductal adenocarcinoma was found and confirmed by histological testing. Conclusion: All of the reassessed lesions with US were adequately reclassified.

Introducción: en México y el mundo, el cáncer de mama causa la mayor mortalidad por cáncer en mujeres. Su incidencia ha incrementado por una mayor esperanza de vida y exposición a factores de riesgo. El tamizaje de esta enfermedad se hace mediante mastografía, y para la estratificación de las lesiones se utiliza el sistema BIRADS (Breast Imaging Reporting and Data System), que estandariza el informe, categoriza las lesiones según el grado de sospecha y asigna recomendaciones a seguir. Dicho sistema va desde 0 (no concluyente) hasta 6 (lesión con malignidad demostrada) y es de interés para este estudio la categoría 0. Objetivo: describir la reclasificación de pacientes con reporte BIRADS 0 por mastografía durante 2021 en una unidad de primer nivel de atención. Material y métodos: estudio retrospectivo, descriptivo, transversal, observacional. Se estudiaron mujeres mayores de 40 años con resultado BIRADS 0. Se utilizaron las siguientes bases de datos: Registro Institucional de Cáncer, Sistema de Información de Medicina Familiar, Expediente Clínico Electrónico y lista nominal de mastografías y censo de pacientes sospechosos de medicina preventiva. Resultados: la reclasificación con ultrasonido (US) se logró en el 100% de pacientes, en todas las categorías de BIRADS US. En el 3.8% se confirmó carcinoma ductal por histología en las pacientes inicialmente categorizadas como BIRADS 0. Conclusiones: la totalidad de lesiones reevaluadas con US fueron reclasificadas satisfactoriamente.

Comparative profiling of whole-cell and exosome samples reveals protein signatures that stratify breast cancer subtypes.

Identifying novel breast cancer biomarkers will improve patient stratification, enhance therapeutic outcomes, and help develop non-invasive diagnostics. We compared the proteomic profiles of whole-cell and exosomal samples of representative breast cancer cell subtypes to evaluate the potential of extracellular vesicles as non-invasive disease biomarkers in liquid biopsies. Overall, differentially-expressed proteins in whole-cell and exosome samples (which included markers for invasion, metastasis, angiogenesis, and drug resistance) effectively discriminated subtypes; furthermore, our results confirmed that the proteomic profile of exosomes reflects breast cancer cell-of-origin, which underscores their potential as disease biomarkers. Our study will contribute to identifying biomarkers that support breast cancer patient stratification and developing novel therapeutic strategies. We include an open, interactive web tool to explore the data as a molecular resource that can explain the role of these protein signatures in breast cancer classification.

The "Forgotten" Subtypes of Breast Carcinoma: A Systematic Review of Selected Histological Variants Not Included or Not Recognized as Distinct Entities in the Current World Health Organization Classification of Breast Tumors.

Breast carcinoma is the most common cancer in women. Nineteen different subtypes of breast carcinomas are recognized in the current WHO classification of breast tumors. Except for these subtypes, there are a number of carcinomas with special morphologic and immunohistochemical features that are not included in the 5th WHO classification, while others are considered special morphologic patterns of invasive breast carcinoma of no special type. In this manuscript, we systematically review the literature on four different subtypes of invasive breast carcinoma, namely lymphoepithelioma-like breast carcinoma, breast carcinoma with osteoclast-like giant cells, signet-ring breast carcinoma, and metaplastic breast carcinoma with melanocytic differentiation. We describe their clinicopathological characteristics, focusing on the differential diagnosis, treatment, and prognosis.

Proteomic Profiling of HDL in Newly Diagnosed Breast Cancer Based on Tumor Molecular Classification and Clinical Stage of Disease.

The association between high-density lipoprotein (HDL) cholesterol and breast cancer (BC) remains controversial due to the high complexity of the HDL particle and its functionality. The HDL proteome was determined in newly diagnosed BC classified according to the molecular type [luminal A or B (LA or LB), HER2, and triple-negative (TN)] and clinical stage of the disease. Women (n = 141) aged between 18 and 80 years with BC, treatment-naïve, and healthy women [n = 103; control group (CT)], matched by age and body mass index, were included. Data-independent acquisition (DIA) proteomics was performed in isolated HDL (D = 1.063-1.21 g/mL). Results: Paraoxonase1, carnosine dipeptidase1, immunoglobulin mMu heavy chain constant region (IGHM), apoA-4, and transthyretin were reduced, and serum amyloid A2 and tetranectin were higher in BC compared to CT. In TNBC, apoA-1, apoA-2, apoC-2, and apoC-4 were reduced compared to LA, LB, and HER2, and apoA-4 compared to LA and HER2. ComplementC3, lambda immunoglobulin2/3, serpin3, IGHM, complement9, alpha2 lysine rich-glycoprotein1, and complement4B were higher in TNBC in comparison to all other types; complement factor B and vitamin D-binding protein were in contrast to LA and HER2, and plasminogen compared to LA and LB. In grouped stages III + IV, tetranectin and alpha2-macroglobulin were reduced, and haptoglobin-related protein; lecithin cholesterol acyltransferase, serum amyloid A1, and IGHM were increased compared to stages I + II. Conclusions: A differential proteomic profile of HDL in BC based on tumor molecular classification and the clinical stage of the disease may contribute to a better understanding of the association of HDL with BC pathophysiology, treatment, and outcomes.

Raman spectroscopy combined with convolutional neural network for the sub-types classification of breast cancer and critical feature visualization.

PROBLEMS: Raman spectroscopy has emerged as an effective technique that can be used for noninvasive breast cancer analysis. However, the current Raman prediction models fail to cover all the molecular sub-types of breast cancer, and lack the visualization of the model. AIMS: Using Raman spectroscopy combined with convolutional neural network (CNN) to construct a prediction model for the existing known molecular sub-types of breast cancer, and selected critical peaks through visualization strategies, so as to achieve the purpose of mining specific biomarker information. METHODS: Optimizing network parameters with the help of sparrow search algorithm (SSA) for the multiple parameters in the CNN to improve the prediction performance of the model. To avoid the contingency of the results, multiple sets of data were generated through Monte Carlo sampling and used to train the model, thereby improving the credibility of the results. Based on the accurate prediction of the model, the spectral regions that contributed to the classification were visualized using Gradient-weighted Class Activation Mapping (Grad-CAM), achieving the goal of visualizing characteristic peaks. RESULTS: Compared with other algorithms, optimized CNN could obtain the highest accuracy and lowest standard error. And there was no significant difference between using full spectra and fingerprint regions (within 2 %), indicating that the fingerprint region provided the most contribution in classifying sub-types. Based on the classification results from the fingerprint region, the model performances about various sub-types were as follows: CNN (95.34 %±2.18 %)>SVM(94.90 %±1.88 %)>PLS-DA(94.52 %±2.22 %)> KNN (80.00 %±5.27 %). The critical features visualized by Grad-CAM could match well with IHC information, allowing for a more distinct differentiation of sub-types in their spatial positions. CONCLUSION: Raman spectroscopy combined with CNN could achieve accurate and rapid identification of breast cancer molecular sub-types. Proposed visualization strategy could be proved from biochemistry information and spatial location, demonstrated that the strategy might be used for the mining of biomarkers in future.

Comparative analysis of features and classification techniques in breast cancer detection for Biglycan biomarker images.

BACKGROUND: Breast cancer (BC) is considered the world's most prevalent cancer. Early diagnosis of BC enables patients to receive better care and treatment, hence lowering patient mortality rates. Breast lesion identification and classification are challenging even for experienced radiologists due to the complexity of breast tissue and variations in lesion presentations. OBJECTIVE: This work aims to investigate appropriate features and classification techniques for accurate breast cancer detection in 336 Biglycan biomarker images. METHODS: The Biglycan biomarker images were retrieved from the Mendeley Data website (Repository name: Biglycan breast cancer dataset). Five features were extracted and compared based on shape characteristics (i.e., Harris Points and Minimum Eigenvalue (MinEigen) Points), frequency domain characteristics (i.e., The Two-dimensional Fourier Transform and the Wavelet Transform), and statistical characteristics (i.e., histogram). Six different commonly used classification algorithms were used; i.e., K-nearest neighbours (k-NN), Naïve Bayes (NB), Pseudo-Linear Discriminate Analysis (pl-DA), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). RESULTS: The histogram of greyscale images showed the best performance for the k-NN (97.6%), SVM (95.8%), and RF (95.3%) classifiers. Additionally, among the five features, the greyscale histogram feature achieved the best accuracy in all classifiers with a maximum accuracy of 97.6%, while the wavelet feature provided a promising accuracy in most classifiers (up to 94.6%). CONCLUSION: Machine learning demonstrates high accuracy in estimating cancer and such technology can assist doctors in the analysis of routine medical images and biopsy samples to improve early diagnosis and risk stratification.

CNN-based deep learning approach for classification of invasive ductal and metastasis types of breast carcinoma.

OBJECTIVE: Breast cancer is one of the leading cancer causes among women worldwide. It can be classified as invasive ductal carcinoma (IDC) or metastatic cancer. Early detection of breast cancer is challenging due to the lack of early warning signs. Generally, a mammogram is recommended by specialists for screening. Existing approaches are not accurate enough for real-time diagnostic applications and thus require better and smarter cancer diagnostic approaches. This study aims to develop a customized machine-learning framework that will give more accurate predictions for IDC and metastasis cancer classification. METHODS: This work proposes a convolutional neural network (CNN) model for classifying IDC and metastatic breast cancer. The study utilized a large-scale dataset of microscopic histopathological images to automatically perceive a hierarchical manner of learning and understanding. RESULTS: It is evident that using machine learning techniques significantly (15%-25%) boost the effectiveness of determining cancer vulnerability, malignancy, and demise. The results demonstrate an excellent performance ensuring an average of 95% accuracy in classifying metastatic cells against benign ones and 89% accuracy was obtained in terms of detecting IDC. CONCLUSIONS: The results suggest that the proposed model improves classification accuracy. Therefore, it could be applied effectively in classifying IDC and metastatic cancer in comparison to other state-of-the-art models.

Mapping the cited evidence of ductal carcinoma in situ from the 5th edition of the World Health Organisation classification of tumours of the breast.

AIMS: Ductal carcinoma in situ (DCIS) is recognised by the World Health Organisation (WHO) Classification of Tumours (WCT) as a non-invasive neoplastic epithelial proliferation confined to the mammary ducts and lobules. This report categorises the references cited in the DCIS chapter of the 5th edition of the WCT (Breast Tumours) according to prevailing evidence levels for evidence-based medicine and the Hierarchy of Evidence for Tumour Pathology (HETP), identifying potential gaps that can inform subsequent editions of the WCT for this tumour. METHODS AND RESULTS: We included all citations from the DCIS chapter of the WCT (Breast Tumours, 5th edition). Each citation was appraised according to its study design and evidence level. We developed our map of cited evidence, which is a graphical matrix of tumour type (column) and tumour descriptors (rows). Spheres were used to represent the evidence, with size and colour corresponding to their number and evidence level respectively. Thirty-six publications were retrieved. The cited literature in the DCIS chapter comprised mainly case series and were regarded as low-level. We found an unequal distribution of citations among tumour descriptors. 'Pathogenesis' and 'prognosis and prediction' contained the most references, while 'clinical features', 'aetiology' and 'diagnostic molecular pathology' had only a single citation each. 'Prognosis and prediction' had the greatest proportion of moderate- and high-levels of evidence. CONCLUSION: Our findings align with the disposition for observational studies inherent in the field of pathology. Our map is a springboard for future efforts in mapping all available evidence on DCIS, potentially augmenting the editorial process and future editions of WCTs.

Spatial molecular profiling of mixed invasive ductal and lobular breast cancers reveals heterogeneity in intrinsic molecular subtypes, oncogenic signatures, and mutations.

Mixed invasive ductal and lobular carcinoma (MDLC) is a rare histologic subtype of breast cancer displaying both E-cadherin positive ductal and E-cadherin negative lobular morphologies within the same tumor, posing challenges with regard to anticipated clinical management. It remains unclear whether these distinct morphologies also have distinct biology and risk of recurrence. Our spatially resolved transcriptomic, genomic, and single-cell profiling revealed clinically significant differences between ductal and lobular tumor regions including distinct intrinsic subtype heterogeneity - e.g., MDLC with triple-negative breast cancer (TNBC) or basal ductal and estrogen receptor positive (ER+) luminal lobular regions, distinct enrichment of cell cycle arrest/senescence and oncogenic (ER and MYC) signatures, genetic and epigenetic CDH1 inactivation in lobular but not ductal regions, and single-cell ductal and lobular subpopulations with unique oncogenic signatures further highlighting intraregional heterogeneity. Altogether, we demonstrated that the intratumoral morphological/histological heterogeneity within MDLC is underpinned by intrinsic subtype and oncogenic heterogeneity which may result in prognostic uncertainty and therapeutic dilemma.

Deep learning empowered breast cancer diagnosis: Advancements in detection and classification.

Recent advancements in AI, driven by big data technologies, have reshaped various industries, with a strong focus on data-driven approaches. This has resulted in remarkable progress in fields like computer vision, e-commerce, cybersecurity, and healthcare, primarily fueled by the integration of machine learning and deep learning models. Notably, the intersection of oncology and computer science has given rise to Computer-Aided Diagnosis (CAD) systems, offering vital tools to aid medical professionals in tumor detection, classification, recurrence tracking, and prognosis prediction. Breast cancer, a significant global health concern, is particularly prevalent in Asia due to diverse factors like lifestyle, genetics, environmental exposures, and healthcare accessibility. Early detection through mammography screening is critical, but the accuracy of mammograms can vary due to factors like breast composition and tumor characteristics, leading to potential misdiagnoses. To address this, an innovative CAD system leveraging deep learning and computer vision techniques was introduced. This system enhances breast cancer diagnosis by independently identifying and categorizing breast lesions, segmenting mass lesions, and classifying them based on pathology. Thorough validation using the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) demonstrated the CAD system's exceptional performance, with a 99% success rate in detecting and classifying breast masses. While the accuracy of detection is 98.5%, when segmenting breast masses into separate groups for examination, the method's performance was approximately 95.39%. Upon completing all the analysis, the system's classification phase yielded an overall accuracy of 99.16% for classification. The potential for this integrated framework to outperform current deep learning techniques is proposed, despite potential challenges related to the high number of trainable parameters. Ultimately, this recommended framework offers valuable support to researchers and physicians in breast cancer diagnosis by harnessing cutting-edge AI and image processing technologies, extending recent advances in deep learning to the medical domain.

Segmentation-based BI-RADS ensemble classification of breast tumours in ultrasound images.

BACKGROUND: The development of computer-aided diagnosis systems in breast cancer imaging is exponential. Since 2016, 81 papers have described the automated segmentation of breast lesions in ultrasound images using artificial intelligence. However, only two papers have dealt with complex BI-RADS classifications. PURPOSE: This study addresses the automatic classification of breast lesions into binary classes (benign vs. malignant) and multiple BI-RADS classes based on a single ultrasonographic image. Achieving this task should reduce the subjectivity of an individual operator's assessment. MATERIALS AND METHODS: Automatic image segmentation methods (PraNet, CaraNet and FCBFormer) adapted to the specific segmentation task were investigated using the U-Net model as a reference. A new classification method was developed using an ensemble of selected segmentation approaches. All experiments were performed on publicly available BUS B, OASBUD, BUSI and private datasets. RESULTS: FCBFormer achieved the best outcomes for the segmentation task with intersection over union metric values of 0.81, 0.80 and 0.73 and Dice values of 0.89, 0.87 and 0.82, respectively, for the BUS B, BUSI and OASBUD datasets. Through a series of experiments, we determined that adding an extra 30-pixel margin to the segmentation mask counteracts the potential errors introduced by the segmentation algorithm. An assembly of the full image classifier, bounding box classifier and masked image classifier was the most accurate for binary classification and had the best accuracy (ACC; 0.908), F1 (0.846) and area under the receiver operating characteristics curve (AUROC; 0.871) in the BUS B and ACC (0.982), F1 (0.984) and AUROC (0.998) in the UCC BUS datasets, outperforming each classifier used separately. It was also the most effective for BI-RADS classification, with ACC of 0.953, F1 of 0.920 and AUROC of 0.986 in UCC BUS. Hard voting was the most effective method for dichotomous classification. For the multi-class BI-RADS classification, the soft voting approach was employed. CONCLUSIONS: The proposed new classification approach with an ensemble of segmentation and classification approaches proved more accurate than most published results for binary and multi-class BI-RADS classifications.

Themis: advancing precision oncology through comprehensive molecular subtyping and optimization.

Recent advances in tumor molecular subtyping have revolutionized precision oncology, offering novel avenues for patient-specific treatment strategies. However, a comprehensive and independent comparison of these subtyping methodologies remains unexplored. This study introduces 'Themis' (Tumor HEterogeneity analysis on Molecular subtypIng System), an evaluation platform that encapsulates a few representative tumor molecular subtyping methods, including Stemness, Anoikis, Metabolism, and pathway-based classifications, utilizing 38 test datasets curated from The Cancer Genome Atlas (TCGA) and significant studies. Our self-designed quantitative analysis uncovers the relative strengths, limitations, and applicability of each method in different clinical contexts. Crucially, Themis serves as a vital tool in identifying the most appropriate subtyping methods for specific clinical scenarios. It also guides fine-tuning existing subtyping methods to achieve more accurate phenotype-associated results. To demonstrate the practical utility, we apply Themis to a breast cancer dataset, showcasing its efficacy in selecting the most suitable subtyping methods for personalized medicine in various clinical scenarios. This study bridges a crucial gap in cancer research and lays a foundation for future advancements in individualized cancer therapy and patient management.

An Effective Ultrasound Features-Based Diagnostic Model via Principal Component Analysis Facilitated Differentiating Subtypes of Mucinous Breast Cancer From Fibroadenomas.

BACKGROUND: Mucinous breast carcinoma (MBC) is often misdiagnosed as fibroadenoma (FA),which can lead to inappropriate or delayed treatments. This study aimed to establish an efficient ultrasound (US)-based diagnostic model to distinguish MBC subtypes from FAs. METHODS: Between January 2017 and February 2024, 240 lesions were enrolled, comprising 65 cases of pure mucinous breast carcinoma (PMBC), 47 cases of mixed mucinous breast carcinoma (MMBC), and 128 cases of FAs. Ten US feature variables underwent principal component analysis (PCA). Models were constructed based on components explaining over 75% of the total variation, with varimax rotation applied for interpretability. Comprehensive models were developed to distinguish PMBCs and MMBCs from FAs. RESULTS: Six principal components were selected, achieving a cumulative contribution rate of 77.46% for PMBCs vs. FAs and 78.62% for MMBCs vs. FAs. The principal component of cystic-solid composition and posterior acoustic enhancement demonstrated the highest diagnostic value for distinguishing PMBCs from FAs (AUC: 0.86, ACC: 80.31%). Features including vascularization, irregular shape, ill-defined border, and larger size exhibited the highest diagnostic value for distinguishing MMBCs from FAs (AUC: 0.90, ACC: 87.43%). The comprehensive models showed excellent clinical value in distinguishing PMBCs (AUC = 0.86, SEN = 86.15%, SPE = 73.44%, ACC = 77.72%) and MMBCs (AUC = 0.92, SEN = 80.85%, SPE = 95.31%, ACC = 91.43%) from FAs. CONCLUSION: This diagnostic model holds promise for effectively distinguishing PMBCs and MMBCs from FAs, assisting radiologists in mitigating diagnostic biases and enhancing diagnostic efficiency.

Identifying miRNA as biomarker for breast cancer subtyping using association rule.

- This paper presents a comprehensive study focused on breast cancer subtyping, utilizing a multifaceted approach that integrates feature selection, machine learning classifiers, and miRNA regulatory networks. The feature selection process begins with the CFS algorithm, followed by the Apriori algorithm for association rule generation, resulting in the identification of significant features tailored to Luminal A, Luminal B, HER-2 enriched, and Basal-like subtypes. The subsequent application of Random Forest (RF) and Support Vector Machine (SVM) classifiers yielded promising results, with the SVM model achieving an overall accuracy of 76.60 % and the RF model demonstrating robust performance at 80.85 %. Detailed accuracy metrics revealed strengths and areas for refinement, emphasizing the potential for optimizing subtype-specific recall. To explore the regulatory landscape in depth, an analysis of selected miRNAs was conducted using MIENTURNET, a tool for visualizing miRNA-target interactions. While FDR analysis raised concerns for HER-2 and Basal-like subtypes, Luminal A and Luminal B subtypes showcased significant miRNA-gene interactions. Functional enrichment analysis for Luminal A highlighted the role of Ovarian steroidogenesis, implicating specific miRNAs such as hsa-let-7c-5p and hsa-miR-125b-5p as potential diagnostic biomarkers and regulators of Luminal A breast cancer. Luminal B analysis uncovered associations with the MAPK signaling pathway, with miRNAs like hsa-miR-203a-3p and hsa-miR-19a-3p exhibiting potential diagnostic and therapeutic significance. In conclusion, this integrative approach combines machine learning techniques with miRNA analysis to provide a holistic understanding of breast cancer subtypes. The identified miRNAs and associated pathways offer insights into potential diagnostic biomarkers and therapeutic targets, contributing to the ongoing efforts to improve breast cancer diagnostics and personalized treatment strategies.

Prognostic significance and value of further classification of lymphovascular invasion in invasive breast cancer: a retrospective observational study.

PURPOSE: To investigate the prognostic significance of lymphovascular invasion in invasive breast cancer and the value of using specific vascular endothelial markers to further classify lymphovascular invasion. METHODS: We collected 2124 patients with invasive breast cancer who were hospitalized at the First Hospital of Dalian Medical University from 2012 to 2020. Statistical methods were used to investigate the relationship between lymphovascular invasion and clinicopathological characteristics of breast cancer, and the correlation between lymphovascular invasion on overall survival (OS) and disease-free survival (DFS) of various categories of breast cancers. Immunohistochemical staining of breast cancer samples containing lymphovascular invasion using specific vascular endothelial markers D2-40 and CD34 was used to classify lymphovascular invasion and to investigate the relationship between lymphovascular invasion and breast cancer progression. RESULTS: There was a high correlation between lymphovascular invasion and T stage, N stage and nerve invasion. Survival analyses showed that patients with lymphovascular invasion, especially luminal B, triple-negative, and Her-2 overexpression breast cancer patients, had poorer OS and DFS prognosis, and that lymphovascular invasion was an independent prognostic factor affecting OS and DFS in breast cancer. The immunohistochemical staining results showed that positive D2-40 staining of lymphovascular invasion was linked to the N stage and localized recurrence of breast cancer. CONCLUSION: Lymphovascular invasion is associated with aggressive clinicopathological features and is an independent poor prognostic factor in invasive breast cancer. Breast cancer localized recurrence rate and lymph node metastases are influenced by lymphatic vessel invasion. Immunohistochemical techniques should be added to the routine diagnosis of lymphovascular invasion.

Development and validation of a reliable DNA copy-number-based machine learning algorithm (CopyClust) for breast cancer integrative cluster classification.

The Integrative Cluster subtypes (IntClusts) provide a framework for the classification of breast cancer tumors into 10 distinct groups based on copy number and gene expression, each with unique biological drivers of disease and clinical prognoses. Gene expression data is often lacking, and accurate classification of samples into IntClusts with copy number data alone is essential. Current classification methods achieve low accuracy when gene expression data are absent, warranting the development of new approaches to IntClust classification. Copy number data from 1980 breast cancer samples from METABRIC was used to train multiclass XGBoost machine learning algorithms (CopyClust). A piecewise constant fit was applied to the average copy number profile of each IntClust and unique breakpoints across the 10 profiles were identified and converted into ~ 500 genomic regions used as features for CopyClust. These models consisted of two approaches: a 10-class model with the final IntClust label predicted by a single multiclass model and a 6-class model with binary reclassification in which four pairs of IntClusts were combined for initial multiclass classification. Performance was validated on the TCGA dataset, with copy number data generated from both SNP arrays and WES platforms. CopyClust achieved 81% and 79% overall accuracy with the TCGA SNP and WES datasets, respectively, a nine-percentage point or greater improvement in overall IntClust subtype classification accuracy. CopyClust achieves a significant improvement over current methods in classification accuracy of IntClust subtypes for samples without available gene expression data and is an easily implementable algorithm for IntClust classification of breast cancer samples with copy number data.

Breast cancer in northern Peru: molecular subtypes and HER2 low. / Cáncer de mama en el norte del Perú: subtipos moleculares y HER2 low.

This study aimed to understand the immunohistochemical profile of breast cancer and to identify the HER2 low subgroup in the northern macro-region of Peru. A cross-sectional study was conducted in 1176 patients from the Regional Institute of Neoplastic Diseases Northern Peru, from January 2016 to December 2023. We analyzed the data (age, histological type, grade and complementary results), with frequencies and percentages. The profile corresponded to: luminal B (45.6%); luminal A (24.7%); triple negative (18.2%); and HER2 positive non luminal (11.5%). In addition, 215 patients presented HER2 low (25.1% of those previously considered negative). This study provides evidence that the subtyping of breast cancer has changed, being luminal B the most frequent. It is essential to involve health policies to acquire targeted therapies considering HER2 low patients. Motivation for the study. Molecular classification of breast cancer allows the use of targeted treatments. Information on this profile in the northern macroregion of Peru is unknown. In addition, new therapies have appeared for a subgroup of patients. Main findings. In this study, the most frequent molecular subtypes were: luminal B, luminal A, triple negative and non-luminal HER2. Also, 18.3% of patients had low HER2 expression. Implications. Health policies should be aligned with scientific advances, to guarantee targeted therapies and to update the information in health manuals or protocols.

El objetivo del estudio fue conocer el perfil inmunohistoquímico del cáncer de mama e identificar el subgrupo HER2 low en la macrorregión norte del Perú. Se realizó un estudio transversal con una muestra de 1176 pacientes atendidos en el Instituto Regional de Enfermedades Neoplásicas Norte del Perú desde enero de 2016 a diciembre de 2023. Los datos recolectados (edad, tipo histológico, grado y resultados complementarios), se analizaron con frecuencias y porcentajes. El perfil correspondió a: luminal B (45,6%); luminal A (24,7%); triple negativo (18,2%); y HER2 positivo no luminal (11,5%). Además, HER2 low fueron 215 pacientes (25,1% de los considerados previamente negativos). Este estudio proporciona evidencia que la subtipificación de cáncer de mama ha cambiado, siendo luminal B más frecuente, y es esencial involucrar a políticas de salud para adquirir terapias dirigidas considerando a pacientes HER2 low. Motivación para realizar el estudio. La clasificación molecular del cáncer de mama permite utilizar tratamientos dirigidos. La información de este perfil en la macrorregión norte del Perú es desconocida. Además, han aparecido nuevas terapias para un subgrupo de pacientes. Principales hallazgos. En este estudio, los subtipos moleculares por orden de frecuencia fueron: luminal B, luminal A, triple negativo y HER2 no luminal. Asimismo, 18,3% de pacientes tuvieron expresión HER2 low. Implicancias. Las políticas de salud deben corresponderse con los avances científicos, para garantizar terapias dirigidas y actualizar la información de los manuales o protocolos de salud.

Pseudo-class part prototype networks for interpretable breast cancer classification.

Interpretability in machine learning has become increasingly important as machine learning is being used in more and more applications, including those with high-stakes consequences such as healthcare where Interpretability has been regarded as a key to the successful adoption of machine learning models. However, using confounding/irrelevant information in making predictions by deep learning models, even the interpretable ones, poses critical challenges to their clinical acceptance. That has recently drawn researchers' attention to issues beyond the mere interpretation of deep learning models. In this paper, we first investigate application of an inherently interpretable prototype-based architecture, known as ProtoPNet, for breast cancer classification in digital pathology and highlight its shortcomings in this application. Then, we propose a new method that uses more medically relevant information and makes more accurate and interpretable predictions. Our method leverages the clustering concept and implicitly increases the number of classes in the training dataset. The proposed method learns more relevant prototypes without any pixel-level annotated data. To have a more holistic assessment, in addition to classification accuracy, we define a new metric for assessing the degree of interpretability based on the comments of a group of skilled pathologists. Experimental results on the BreakHis dataset show that the proposed method effectively improves the classification accuracy and interpretability by respectively 8 % and 18 % . Therefore, the proposed method can be seen as a step toward implementing interpretable deep learning models for the detection of breast cancer using histopathology images.