Omitting Radiotherapy after Breast-Conserving Surgery in Luminal A Breast Cancer.

BACKGROUND: Adjuvant radiotherapy is prescribed after breast-conserving surgery to reduce the risk of local recurrence. However, radiotherapy is inconvenient, costly, and associated with both short-term and long-term side effects. Clinicopathologic factors alone are of limited use in the identification of women at low risk for local recurrence in whom radiotherapy can be omitted. Molecularly defined intrinsic subtypes of breast cancer can provide additional prognostic information. METHODS: We performed a prospective cohort study involving women who were at least 55 years of age, had undergone breast-conserving surgery for T1N0 (tumor size <2 cm and node negative), grade 1 or 2, luminal A-subtype breast cancer (defined as estrogen receptor positivity of ≥1%, progesterone receptor positivity of >20%, negative human epidermal growth factor receptor 2, and Ki67 index of ≤13.25%), and had received adjuvant endocrine therapy. Patients who met the clinical eligibility criteria were registered, and Ki67 immunohistochemical analysis was performed centrally. Patients with a Ki67 index of 13.25% or less were enrolled and did not receive radiotherapy. The primary outcome was local recurrence in the ipsilateral breast. In consultation with radiation oncologists and patients with breast cancer, we determined that if the upper boundary of the two-sided 90% confidence interval for the cumulative incidence at 5 years was less than 5%, this would represent an acceptable risk of local recurrence at 5 years. RESULTS: Of 740 registered patients, 500 eligible patients were enrolled. At 5 years after enrollment, recurrence was reported in 2.3% of the patients (90% confidence interval [CI], 1.3 to 3.8; 95% CI, 1.2 to 4.1), a result that met the prespecified boundary. Breast cancer occurred in the contralateral breast in 1.9% of the patients (90% CI, 1.1 to 3.2), and recurrence of any type was observed in 2.7% (90% CI, 1.6 to 4.1). CONCLUSIONS: Among women who were at least 55 years of age and had T1N0, grade 1 or 2, luminal A breast cancer that were treated with breast-conserving surgery and endocrine therapy alone, the incidence of local recurrence at 5 years was low with the omission of radiotherapy. (Funded by the Canadian Cancer Society and the Canadian Breast Cancer Foundation; LUMINA ClinicalTrials.gov number, NCT01791829.).

A study of clinical and molecular characteristics in bilateral primary breast cancer.

BACKGROUND: Bilateral primary breast cancer (BPBC) is a rare type of breast cancer. Studies on the clinicopathologic and molecular characteristics of BPBC in a metastatic context are very limited. METHODS: A total of 574 unselected metastatic breast cancer patients with clinical information were enrolled in our next-generation sequencing (NGS) database. Patients with BPBC from our NGS database were regarded as the study cohort. In addition, 1467 patients with BPBC and 2874 patients with unilateral breast cancer (UBC) from the Surveillance, Epidemiology, and End Results (SEER) public database were also analyzed to determine the characteristics of BPBC. RESULTS: Among the 574 patients enrolled in our NGS database, 20 (3.5%) patients had bilateral disease, comprising 15 (75%) patients with synchronous bilateral disease and 5 (25%) patients with metachronous bilateral disease. Eight patients had bilateral hormone receptor-positive (HR+)/human epidermal growth factor receptor-negative (HER2-) tumors, and three had unilateral HR+/HER2- tumors. More HR+/HER2- tumors and lobular components were found in BPBC patients than in UBC patients. The molecular subtype of the metastatic lesions in three patients was inconsistent with either side of the primary lesions, which suggested the importance of rebiopsy. Strong correlations in clinicopathologic features between the left and right tumors in BPBC were exhibited in the SEER database. In our NGS database, only one BPBC patient was found with a pathogenic germline mutation in BRCA2. The top mutated somatic genes in BPBC patients were similar to those in UBC patients, including TP53 (58.8% in BPBC and 60.6% in UBC) and PI3KCA (47.1% in BPBC and 35.9% in UBC). CONCLUSIONS: Our study suggested that BPBC may tend to be lobular carcinoma and have the HR+/HER2- subtype. Although our study did not find specific germline and somatic mutations in BPBC, more research is needed for verification.

Cáncer de mama: nueva clasificación molecular / Breast cancer: New molecular classification

A pesar de utilizar criterios histológicos e inmunohistoquímicos, no somos capaces de reflejar la heterogeneidad del cáncer de mama. En 2012 se realiza el estudio Molecular Taxonomy of Breast Cancer International Consortium (METABRIC), el cual analiza la arquitectura genómica y de transcripción en 2000 cánceres de mama. Aparecieron subtipos moleculares con gran implicación. Tal es la importancia de la biología molecular que, en el AJCC-TNM8 (2017), se incorporaron grupos pronósticos con base en la expresión de biomarcadores (RE, RP, HER2, Ki67). Estos grupos complementan a la clasificación tradicional y añade un enfoque biológico al puramente anatómico existente. Hemos analizado el estudio METABRIC, haciendo hincapié en la nueva línea de investigación que aportó. Realizamos una exhaustiva búsqueda bibliográfica en las principales bases de datos, obteniendo los artículos que exponen los resultados del METABRIC. Desglosamos los 10 grupos integradores descubiertos recientemente, sus variaciones genéticas y su implicación para nuestra práctica clínica. Comprobamos que la clasificación actual del cáncer de mama no es lo suficientemente precisa, cuyas incongruencias se explican por los grupos integradores. Sientan los cimientos para una nueva clasificación o para refinar los subtipos existentes. (AU)

Despite using histological and immunohistochemical criteria, we are unable to reflect the heterogeneity of breast cancer. In 2012 METABRIC analyzed the genomic and transcriptional architecture of 2000 breast cancers. Molecular subtypes were found to be highly implicated. Such is the importance of molecular biology that, in AJCC-TNM8 (2017), prognostic groups based on biomarker expression (ER, PR, HER2, and Ki67) were incorporated. These groups complement the traditional classification and add a biological approach to the existing purely anatomical one. We have analyzed the METABRIC study, emphasizing the new line of research it contributed. We did an exhaustive literature search in the main databases, obtaining the articles presenting the METABRIC results. We broke down the 10 recently discovered integrative clusters, their genetic variations and their implication for our clinical practice. We found that the current classification of breast cancer is not enough accurate, the inconsistencies of which are explained by the integrative clusters. They lay the foundation for a new classification or for refining existing subtypes. (AU)

Perfil imuno-histoquímico dos casos de carcinomas mamários da microrregião de catanduva-sp / Immunohistochemical profile of breast carcinoma cases from the microregion of catanduva-sp / Perfil inmunohistoquímico de los casos de carcinomas de mama en la microrregión de catanduva-sp

Introdução: O câncer de mama compreende a principal neoplasia maligna que acomete as mulheres brasileiras, com destaque nos índices de mortalidade. O diagnóstico precoce é preconizado através da mamografia, a qual, quando alterada, sugere realizar biópsia para estudo histopatológico e, caso confirmado um carcinoma mamário, acrescenta-se o estudo imuno-histoquímico para determinação de fatores prognósticos e preditivos para o tumor. Objetivos: Levantar os resultados de análise imuno-histoquímica dos carcinomas mamários diagnosticados pelo Serviço de Patologia do Hospital Emílio Carlos (Catanduva-SP) e estabelecer os principais subtipos moleculares do câncer de mama encontrados nessa população. Material e Método: O estudo foi transversal e retrospectivo, a partir dos relatórios de imunohistoquímica dos carcinomas. Foram relatados idade, sexo, subtipo histológico do tumor e positividade imunohistoquímica para receptor de estrogênio, receptor de progesterona, fator de crescimento epidérmico humano 2, índice de proliferação celular e E-caderina. Os casos foram classificados conforme os critérios estabelecidos pelo Consenso de St. Gallen e os dados apresentados por meio de gráficos e tabelas. Resultados: A amostra foi constituída por n=210 casos de carcinomas mamários, com idade média de 58 anos e predominantemente do sexo feminino. O tipo histológico predominante foi o carcinoma mamário invasivo do tipo não especial. A expressão de receptor de estrogênio ocorreu em 92,86%, progesterona 80,48%, HER2 32,38% e Ki67 alto em 70%. O principal subtipo molecular foi o luminal B. Conclusão: Os casos de carcinomas mamários da microrregião de Catanduva apresentam diferenças quando comparados com estudos nacionais, porém similares a outros de caráter regional

Introduction: Breast cancer is the main malignant neoplasm that affects Brazilian women, especially in mortality rates. Early diagnosis is recommended through mammography, which, when altered, suggests biopsy for histopathological study and, if a breast carcinoma is confirmed, the immunohistochemical study is added for determination of prognostic and predictive factors for the tumor. Objectives: To survey the results of immunohistochemical analysis of breast carcinomas diagnosed by the Pathology Service of Hospital Emílio Carlos (Catanduva-SP) and to establish the main molecular subtypes of breast cancer found in this population. Material and Method: The study was cross-sectional and retrospective, from the reports of immunohistochemistry of carcinomas (CEP/UNIFIPA number 4737142). Age, sex, histological subtype of the tumor and immunohistochemical positivity for estrogen receptor, progesterone receptor, human epidermal growth factor 2, cell proliferation index and E-cadherin were reported. The cases were classified according to the criteria established by the St. Gallen Consensus and the data presented by means of graphs and tables. Results: The sample consisted of n=210 cases of breast carcinomas, with a mean age of 58 years and predominantly female. The predominant histological type was invasive breast carcinoma of the non-special type. Estrogen receptor expression occurred in 92.86%, progesterone 80.48%, HER2 32.38% and high Ki67 in 70%. The main molecular subtype was luminal B. Conclusion: The cases of breast carcinomas in the microregion of Catanduva present differences when compared to national studies, but similar to other regional studies

Introduction: Breast cancer comprises the main malignant neoplasm that affects Brazilian women, especially in mortality rates. Early diagnosis is recommended through mammography, which, when altered, suggests biopsy for histopathological study and, if confirmed a breast carcinoma, the immuno-study is addedto determine prognostic and predictive factors for the tumor. Objectives: To collect the results of immunohistochemical analysis of breast carcinomas diagnosed by the Pathology Service of the Emílio Carlos Hospital (Catanduva-SP) and to establish the main molecular subtypes of breast cancer found in this population. Methods: The study was cross-sectional and retrospective, from the reports of immunohistochemistry of carcinomas. Age, sex, tumor histological subtype and immunohistochemical positivity for estrogen receptor, progesterone receptor, human epidermal growth factor 2, cell proliferation index and E-cadherin were reported. The cases were classified according to the criteria established by the St. Gallen Consensus and the data presented through graphs and tables. Results: The sample consisted of n = 210 cases of breast carcinomas, with a mean age of 58 years and predominantly female. The predominant histological type was nonspecial invasive breast carcinoma. The expression of estrogen receptor occurred in 92.86%, progesterone 80.48%, HER2 32.38% and Ki67 high in 70%. The main molecular subtype was luminal B. Conclusion: The cases of breast carcinomas in the Catanduva microregion show differences when compared to national studies, but similar to others of regional character

The Value of 320-Slice Spiral Computed Tomography Perfusion Imaging in Staging and Long-Term Dynamic Evaluation of Breast Cancer.

The value of 320-slice spiral computed tomography (CT) perfusion imaging in staging and long-term dynamic evaluation of breast cancer was explored. 120 breast cancer patients who underwent preoperative CT examination and were confirmed by surgery and pathology were selected. All patients underwent preoperative TNM staging of breast cancer, with 120 cases in each stage. According to the results of 320-slice spiral CT, the postoperative pathology and surgical methods were compared and analyzed. CT diagnosis of breast cancer showed that T1 sensitivity was 71% and accuracy was 61%, T2 sensitivity was 74% and accuracy was 64%, T3 sensitivity was 94% and the accuracy was 84%, and the T4 sensitivity was 100% and the accuracy was 91%. The sensitivity of N1 stage was 71%, and the accuracy was 61%; and the sensitivity of N2 ~ N3 stage was 81%, and the accuracy was 76%. There were 7 cases of M1 with distant metastasis, the sensitivity was 71%, and the accuracy was 71%. At T1 stage, blood flow (BF) was 39.2 ± 16.7 mL/min/100 g, blood volume (BV) was 2.66 ± 1.4 mL/100 g, mean transit time (MTT) was 8.16 ± 2.7 s, and permeability surface (PS) was 16.6 ± 9.7 mL/min/100 g. 320-slice spiral CT perfusion imaging technology provided a new diagnostic mode for everyone, which can quantitatively identify breast cancer with multiple parameters, which was of great significance for clinical auxiliary diagnosis.

Breast Tumor Classification Using Intratumoral Quantitative Ultrasound Descriptors.

Breast cancer is a global epidemic, responsible for one of the highest mortality rates among women. Ultrasound imaging is becoming a popular tool for breast cancer screening, and quantitative ultrasound (QUS) techniques are being increasingly applied by researchers in an attempt to characterize breast tissue. Several different quantitative descriptors for breast cancer have been explored by researchers. This study proposes a breast tumor classification system using the three major types of intratumoral QUS descriptors which can be extracted from ultrasound radiofrequency (RF) data: spectral features, envelope statistics features, and texture features. A total of 16 features were extracted from ultrasound RF data across two different datasets, of which one is balanced and the other is severely imbalanced. The balanced dataset contains RF data of 100 patients with breast tumors, of which 48 are benign and 52 are malignant. The imbalanced dataset contains RF data of 130 patients with breast tumors, of which 104 are benign and 26 are malignant. Holdout validation was used to split the balanced dataset into 60% training and 40% testing sets. Feature selection was applied on the training set to identify the most relevant subset for the classification of benign and malignant breast tumors, and the performance of the features was evaluated on the test set. A maximum classification accuracy of 95% and an area under the receiver operating characteristic curve (AUC) of 0.968 was obtained on the test set. The performance of the identified relevant features was further validated on the imbalanced dataset, where a hybrid resampling strategy was firstly utilized to create an optimal balance between benign and malignant samples. A maximum classification accuracy of 93.01%, sensitivity of 94.62%, specificity of 91.4%, and AUC of 0.966 were obtained. The results indicate that the identified features are able to distinguish between benign and malignant breast lesions very effectively, and the combination of the features identified in this research has the potential to be a significant tool in the noninvasive rapid and accurate diagnosis of breast cancer.

Ultrasonic Omics Based on Intelligent Classification Algorithm in Hormone Receptor Expression and Efficacy Evaluation of Breast Cancer.

The changes of hormone expression and efficacy of breast cancer (BC) were investigated under the VGG19FCN algorithm and ultrasound omics. 120 patients with BC were selected, of which 90 were positive for hormone receptor and 30 were negative. The VGG19FCN model algorithm and classifier were selected to classify the features of ultrasound breast map, and reliable ultrasound feature data were obtained. The evaluation and analysis of BC hormone receptor expression and clinical efficacy in patients with BC were realized by using ultrasonic omics. The evaluation of the results of the VGG19FCN algorithm was DSC (Dice similarity coefficient) = 0.9626, MPA (mean pixel accuracy) = 0.9676, and IOU (intersection over union) = 0.9155. When the classifier was used to classify the lesion features of BC image, the sensitivity of classification was improved to a certain extent. Compared with the classification of radiologists, when classifying whether patients had BC lesions, the sensitivity increased by 22.7%, the accuracy increased from 71.9% to 79.7%, and the specific evaluation index increased by 0.8%. No substantial difference was indicated between RT (arrive time), WIS (wash in slope), and TTP (time to peak) before and after chemotherapy, P > 0.05. After chemotherapy, the AUC (area under curve) and PI (peak intensity) of ultrasonographic examination were substantially lower than those before chemotherapy, and there were substantial differences in statistics (P < 0.05). In summary, the VGG19FCN algorithm effectively reduces the subjectivity of traditional ultrasound images and can effectively improve the value of ultrasound image features in the accurate diagnosis of BC. It provides a theoretical basis for the subsequent treatment of BC and the prediction of biological behavior. The VGG19FCN algorithm had a good performance in ultrasound image processing of BC patients, and hormone receptor expression changed substantially after chemotherapy treatment.

Investigation of genes and pathways involved in breast cancer subtypes through gene expression meta-analysis.

BACKGROUND: Molecular-based studies have revealed heterogeneity in Breast cancer BC while also improving classification and treatment. However, efforts are underway to distinguish between distinct subtypes of breast cancer. In this study, the results of several microarray studies were combined to identify genes and pathways specific to each BC subtype. METHODS: Meta-analysis of multiple gene expression profile datasets was screened to find differentially expressed genes (DEGs) across subtypes of BC and normal breast tissue samples. Protein-protein interaction network and gene set enrichment analysis were used to identify critical genes and pathways associated with BC subtypes. The differentially expressed genes from meta-analysis was validated using an independent comprehensive breast cancer RNA-sequencing dataset obtained from the Cancer Genome Atlas (TCGA). RESULTS: We identified 110 DEGs (13 DEGs in all and 97 DEGs in each subtype) across subtypes of BC. All subtypes had a small set of shared DEGs enriched in the Chemokine receptor bind chemokine pathway. Luminal A specific were enriched in the translational elongation process in mitochondria, and the enhanced process in luminal B subtypes was interferon-alpha/beta signaling. Cell cycle and mitotic DEGs were enriched in the basal-like group. All subtype-specific DEG genes (100%) were successfully validated for Luminal A, Luminal B, ERBB2, and Normal-like. However, the validation percentage for Basal-like group was 77.8%. CONCLUSION: Integrating researches such as a meta-analysis of gene expression might be more effective in uncovering subtype-specific DEGs and pathways than a single-study analysis. It would be more beneficial to increase the number of studies that use matched BC subtypes along with GEO profiling approaches to reach a better result regarding DEGs and reduce probable biases. However, achieving 77.8% overlap in basal-specific genes and complete concordance in specific genes related to other subtypes can implicate the strength of our analysis for discovering the subtype-specific genes.

Gini's mean difference and the long-term prognostic value of nodal quanta classes after pre-operative chemotherapy in advanced breast cancer.

Gini's mean difference (GMD, mean absolute difference between any two distinct quantities) of the restricted mean survival times (RMSTs, expectation of life at a given time limit) has been proposed as a new metric where higher GMD indicates better prognostic value. GMD is applied to the RMSTs at 25 years time-horizon to evaluate the long-term overall survival of women with breast cancer who received neoadjuvant chemotherapy, comparing a classification based on the number (pN) versus a classification based on the ratio (LNRc) of positive nodes found at axillary surgery. A total of 233 patients treated in 1980-2009 with documented number of positive nodes (npos) and number of nodes examined (ntot) were identified. The numbers were categorized into pN0, npos = 0; pN1, npos = [1,3]; pN2, npos = [4,9]; pN3, npos ≥ 10. The ratios npnx = npos/ntot were categorized into Lnr0, npnx = 0; Lnr1, npnx = (0,0.20]; Lnr2, npnx = (0.20,0.65]; Lnr3, npnx > 0.65. The GMD for pN-classification was 5.5 (standard error: ± 0.9) years, not much improved over a simple node-negative vs. node-positive that showed a GMD of 5.0 (± 1.4) years. The GMD for LNRc-classification was larger, 6.7 (± 0.8) years. Among other conventional metrics, Cox-model LNRc's c-index was 0.668 vs. pN's c = 0.641, indicating commensurate superiority of LNRc-classification. The usability of GMD-RMSTs warrants further investigation.

Assessment of Ki-67 proliferation index with deep learning in DCIS (ductal carcinoma in situ).

The proliferation index (PI) is crucial in histopathologic diagnostics, in particular tumors. It is calculated based on Ki-67 protein expression by immunohistochemistry. PI is routinely evaluated by a visual assessment of the sample by a pathologist. However, this approach is far from ideal due to its poor intra- and interobserver variability and time-consuming. These factors force the community to seek out more precise solutions. Virtual pathology as being increasingly popular in diagnostics, armed with artificial intelligence, may potentially address this issue. The proposed solution calculates the Ki-67 proliferation index by utilizing a deep learning model and fuzzy-set interpretations for hot-spots detection. The obtained region-of-interest is then used to segment relevant cells via classical methods of image processing. The index value is approximated by relating the total surface area occupied by immunopositive cells to the total surface area of relevant cells. The achieved results are compared to the manual calculation of the Ki-67 index made by a domain expert. To increase results reliability, we trained several models in a threefold manner and compared the impact of different hyper-parameters. Our best-proposed method estimates PI with 0.024 mean absolute error, which gives a significant advantage over the current state-of-the-art solution.

Nicotine treatment regulates PD-L1 and PD-L2 expression via inhibition of Akt pathway in HER2-type breast cancer cells.

The immune checkpoint molecules such as PD-L1 and PD-L2 have a substantial contribution to cancer immunotherapy including breast cancer. Microarray expression profiling identified several molecular subtypes, namely luminal-type (with a good-prognosis), HER2-type (with an intermediate-prognosis), and triple-negative breast cancer (TNBC)-type (with a poor-prognosis). We found that PD-L1 and PD-L2 mRNA expressions were highly expressed in TNBC-type cell lines (HCC1937, MDA-MB-231), moderately expressed in HER2-type cell line (SK-BR-3), and poorly expressed in luminal-type cell lines (MDA-MB-361, MCF7). The PD-L1 and PD-L2 expression in SK-BR-3 cells, but not those in HCC1937 and MDA-MB-231 cells, decreased by nicotine stimulation in a dose-dependent manner. In addition, nicotine treatment decreased the phosphorylation of Akt in SK-BR-3 cells, but not in other cell lines. These results show that nicotine regulates the expression of immune checkpoint molecules, PD-L1 and PD-L2, via inhibition of Akt phosphorylation. This findings may provide the new therapeutic strategies for the treatment of breast cancer.

Cystic hypersecretory carcinoma with invasion: Case series on a rare variant of carcinoma breast.

BACKGROUND: Cystic Hypersecretory Carcinoma (CHC) is a rare subset of breast carcinoma. It is part of a spectrum of cystic hypersecretory lesions which includes cystic hypersecretory hyperplasia (CHH), CHH with atypia, CHC in situ and CHC with invasion. Approximately 65 cases of cystic hypersecretory lesions have been reported; most of them were CHC in situ and only 19 cases of CHC with invasion have been reported so far. CASE PRESENTATION: We are reporting 2 cases of 47 and 62 year old women with a palpable breast mass for 6 and 1 month duration respectively. Trucut biopsy was carried out for both which showed high grade ductal carcinoma in situ with microinvasion in the first patient and the latter showed a tiny focus of invasive carcinoma. Simple mastectomy and modified radical mastectomy (MRM) were done for the respective cases; both showed dilated cystic spaces filled with eosinophilic secretions (thyroid colloid-like), lining neoplastic cells that showed variable degrees of proliferation, atypia and in situ carcinoma. There were foci of invasion in both cases and hence a morphological diagnosis of CHC with invasion was made. CONCLUSION: Owing to a smaller number of reported cases, little is known about the biological behavior, prognosis and molecular profile of cystic hypersecretory carcinoma.

Primary breast sarcoma: A case series.

BACKGROUND: Primary Breast Sarcomas (PBS) are rare malignancies and seen in less than <1 % of all breast malignancies. PBS are non epithelial, composed of mesenchymal mammary tissue and are difficult to diagnose from other sarcomas arising in breast. MATERIALS AND METHODS: A retrospective study was conducted in the Department of Pathology and slides of breast malignancies over a period of 5 years were reviewed. Out of total 1570 breast malignancies, 5 cases were reported as PBS. Diagnosis was made on the basis of Histopathology and IHC findings. RESULTS: Out of total 1570 cases, 5 cases were diagnosed as PBS (i.e. 0.32% of all cases). 3 out of 5 cases were males comprising of 60% of cases and 2 cases were females accounting for 40% of cases. The age group of presentation was 32-65 years with mean age being 48.5 years. A diagnosis of MPNST was rendered in two cases ( 1=M, 1=F), one each was diagnosed as DFSP ( with fibrosarcoma), Leiomyosarcoma and Fibrosarcoma. CONCLUSION: PBS is an extremely rare entity and locally aggressive. It requires diagnosis as its treatment protocol is different.

Identification of long non-coding RNAs and RNA binding proteins in breast cancer subtypes.

Breast cancer is a heterogeneous disease classified into four main subtypes with different clinical outcomes, such as patient survival, prognosis, and relapse. Current genetic tests for the differential diagnosis of BC subtypes showed a poor reproducibility. Therefore, an early and correct diagnosis of molecular subtypes is one of the challenges in the clinic. In the present study, we identified differentially expressed genes, long non-coding RNAs and RNA binding proteins for each BC subtype from a public dataset applying bioinformatics algorithms. In addition, we investigated their interactions and we proposed interacting biomarkers as potential signature specific for each BC subtype. We found a network of only 2 RBPs (RBM20 and PCDH20) and 2 genes (HOXB3 and RASSF7) for luminal A, a network of 21 RBPs and 53 genes for luminal B, a HER2-specific network of 14 RBPs and 30 genes, and a network of 54 RBPs and 302 genes for basal BC. We validated the signature considering their expression levels on an independent dataset evaluating their ability to classify the different molecular subtypes with a machine learning approach. Overall, we achieved good performances of classification with an accuracy >0.80. In addition, we found some interesting novel prognostic biomarkers such as RASSF7 for luminal A, DCTPP1 for luminal B, DHRS11, KLC3, NAGS, and TMEM98 for HER2, and ABHD14A and ADSSL1 for basal. The findings could provide preliminary evidence to identify putative new prognostic biomarkers and therapeutic targets for individual breast cancer subtypes.

Breast Tumor Detection and Classification in Mammogram Images Using Modified YOLOv5 Network.

Breast cancer incidence has been rising steadily during the past few decades. It is the second leading cause of death in women. If it is diagnosed early, there is a good possibility of recovery. Mammography is proven to be an excellent screening technique for breast tumor diagnosis, but its detection and classification in mammograms remain a significant challenge. Previous studies' major limitation is an increase in false positive ratio (FPR) and false negative ratio (FNR), as well as a drop in Matthews correlation coefficient (MCC) value. A model that can lower FPR and FNR while increasing MCC value is required. To overcome prior research limitations, a modified network of YOLOv5 is used in this study to detect and classify breast tumors. Our research is conducted using publicly available datasets Curated Breast Imaging Subset of DDSM (CBIS-DDSM). The first step is to perform preprocessing, which includes image enhancing techniques and the removal of pectoral muscles and labels. The dataset is then annotated, augmented, and divided into 60% for training, 30% for validation, and 10% for testing. The experiment is then performed using a batch size of 8, a learning rate of 0.01, a momentum of 0.843, and an epoch value of 300. To evaluate the performance of our proposed model, our proposed model is compared with YOLOv3 and faster RCNN. The results show that our proposed model performs better than YOLOv3 and faster RCNN with 96% mAP, 93.50% MCC value, 96.50% accuracy, 0.04 FPR, and 0.03 FNR value. The results show that our suggested model successfully identifies and classifies breast tumors while also overcoming previous research limitations by lowering the FPR and FNR and boosting the MCC value.

Artificial intelligence for histological subtype classification of breast cancer: combining multi-scale feature maps and the recurrent attention model.

AIMS: The aim of this study was to apply a two-stage deep model combining multi-scale feature maps and the recurrent attention model (RAM) to assist with the pathological diagnosis of breast cancer histological subtypes by the use of whole slide images (WSIs). METHODS AND RESULTS: In this article, we propose an integrated framework combining multi-scale feature maps from Inception V3 and the recurrent attention model to classify the six histological subtypes of breast cancer. This model was trained with 194 WSIs, and on 63 validation WSIs the model achieved accuracies of 0.9030 for patch-level classification and 0.8889 for WSI-level classification. In the testing stage, a total of 65 WSIs were used to achieve an accuracy of 0.8462 without any form of data curation. The t-distributed stochastic neighbour embedding showed that features extracted by the feature network of the RAM from WSIs of the same category can cluster together after training, and the visualization of decision steps showed that the decision-making glimpses are focused on the middle tumour area of an example from test WSIs. Finally, the false classification patches indicated that the morphological similarities between tumour tissues of different subtypes or non-tumour tissues and tumour tissues in patches might contribute to misclassification. CONCLUSIONS: This model can imitate the diagnostic process of pathologists, pay attention to a series of local features on the pathology image, and summarize related information, in order to accurately classify breast cancer into its histological subtypes, which is important for treatment and prognosis.

Deep learning-based classification of preclinical breast cancer tumor models using chemical exchange saturation transfer magnetic resonance imaging.

Chemical exchange saturation transfer (CEST) magnetic resonance imaging has shown promise for classifying tumors based on their aggressiveness, but CEST contrast is complicated by multiple signal sources and thus prolonged acquisition times are often required to extract the signal of interest. We investigated whether deep learning could help identify pertinent Z-spectral features for distinguishing tumor aggressiveness as well as the possibility of acquiring only the pertinent spectral regions for more efficient CEST acquisition. Human breast cancer cells, MDA-MB-231 and MCF-7, were used to establish bi-lateral tumor xenografts in mice to represent higher and lower aggressive tumors, respectively. A convolutional neural network (CNN)-based classification model, trained on simulated data, utilized Z-spectral features as input to predict labels of different tissue types, including MDA-MB-231, MCF-7, and muscle tissue. Saliency maps reported the influence of Z-spectral regions on classifying tissue types. The model was robust to noise with an accuracy of more than 91.5% for low and moderate noise levels in simulated testing data (SD of noise less than 2.0%). For in vivo CEST data acquired with a saturation pulse amplitude of 2.0 µT, the model had a superior ability to delineate tissue types compared with Lorentzian difference (LD) and magnetization transfer ratio asymmetry (MTRasym ) analysis, classifying tissues to the correct types with a mean accuracy of 85.7%, sensitivity of 81.1%, and specificity of 94.0%. The model's performance did not improve substantially when using data acquired at multiple saturation pulse amplitudes or when adding LD or MTRasym spectral features, and did not change when using saliency map-based partial or downsampled Z-spectra. This study demonstrates the potential of CNN-based classification to distinguish between different tumor types and muscle tissue, and speed up CEST acquisition protocols.

Survival in metaplastic breast carcinoma: A case series.

BACKGROUND: Metaplastic breast carcinoma (MBC) is a rare type of breast cancer (0.20-1.00% of all cases). With a more aggressive clinical course, MBC frequently presents as a triple-negative subtype. OBJECTIVE: To describe a case series, analyzing patients survival in four MBC cases. METHODS: The cases were obtained from 532 medical records of breast cancer patients (0.7% of the total). RESULTS: All patients were female. Mean patient age was 49 years (range: 38-60 years). Mean tumor size was 8.9 cm (range: 3.0-15.5 cm). Mastectomy was performed in three cases. One patient had axillary nodal metastasis. All underwent chemotherapy and three received radiation therapy after surgery. CONCLUSIONS: With a mean follow-up of 36 months (range: 10-60 months), one case had a tumor recurrence (25%). Three patients (75%) died from metastatic disease and one (25%) is still alive and free of disease.