Breast Cancer Pathology Research Articles

Boric Acid Alters the Expression ofDNA Double Break Repair Genes in MCF-7-Derived Breast Cancer Stem Cells.

Breast cancer pathology ranks second in mortality among women worldwide due to the resistance of cancer stem cells in tumor tissue to radiotherapy and chemotherapy and their effective DNA damage response system (DDR). Targeting the expression of DNA double-strand break (DSB) repair genes in breast cancer stem cells (BC-SCs) is essential for facilitating their elimination with conventional therapies. This study aims to investigate the effects of boric acid (BA) on the expression of DNA DSB repair genes in BC-SCs, which has not been studied in the literature before. BS-SCs were isolated by the MACS method and characterized by flow cytometry. The effects of BA on BC-SCs' DNA DSB repair genes were deciphered by cell viability assay, inverted microscopy, and RT-qPCR. While the expression of the BRCA1 and BRCA2 was upregulated, the expression of the ATM (p < 0.001), RAD51 (p < 0.001), and KU70 (p < 0.001) was downregulated in dose-treated BC-SCs (p < 0.001) to the qPCR results. Consequently, BA affects some of the DNA DSB repair genes of breast cancer stem cells. Findings from this study could provide new insights into the potential therapeutic application of BA in BC-SC elimination and cancer intervention.

Semi-supervised breast cancer pathology image segmentation based on fine-grained classification guidance.

Breast cancer pathological image segmentation (BCPIS) holds significant value in assisting physicians with quantifying tumor regions and providing treatment guidance. However, achieving fine-grained semantic segmentation remains a major challenge for this technology. The complex and diverse morphologies of breast cancer tissue structures result in high costs for manual annotation, thereby limiting the sample size and annotation quality of the dataset. These practical issues have a significant impact on the segmentation performance. To overcome these challenges, this study proposes a semi-supervised learning model based on classification-guided segmentation. The model first utilizes a multi-scale convolutional network to extract rich semantic information and then employs a multi-expert cross-layer joint learning strategy, integrating a small number of labeled samples to iteratively provide the model with class-generated multi-cue pseudo-labels and real labels. Given the complexity of the breast cancer samples and the limited sample quantity, an innovative approach of augmenting additional unlabeled data was adopted to overcome this limitation. Experimental results demonstrate that, although the proposed model falls slightly behind supervised segmentation models, it still exhibits significant progress and innovation. The semi-supervised model in this study achieves outstanding performance, with an IoU (Intersection over Union) value of 71.53%. Compared to other semi-supervised methods, the model developed in this study demonstrates a performance advantage of approximately 3%. Furthermore, the research findings indicate a significant correlation between the classification and segmentation tasks in breast cancer pathological images, and the guidance of a multi-expert system can significantly enhance the fine-grained effects of semi-supervised semantic segmentation.

Comprehensive analysis of mitophagy-related subtypes of breast cancer and the association with immune related characteristics

Breast cancer (BRCA) is a common neoplasm characterized by high levels of molecular heterogeneity. Previous studies have noted the importance of mitophagy for the progression and prognosis of BRCA. However, little was found in the similarity and difference of mitophagy-related gene expression patterns of BRCA. This study intended to investigate the differences in functional activation, somatic mutation, and immune-related characteristics among different subtypes of BRCA associated with mitophagy. Based on bioinformatics analysis, we systematically examined the heterogeneity of breast cancer concerning mitophagy and observed two distinct subtypes with different tumor microenvironments and prognoses. BRCA samples from TCGA database were divided into two subtypes based on the expression of 29 mitophagy-related genes by ConsensusClusterPlus algorithm. Two mitophagy-related subtypes with marked prognostic discrepancies were significantly correlated with race, intrinsic subtype grouped based on PAM50 subtype purity and BRCA Pathology. The results of GSVA and immune microenvironment analysis showed significant differences in cancer-related and immune-related features between the two subtypes. METABRIC datasets were extracted to validate the immune characteristics scoring and the expression of immune checkpoints between different subtypes based on the medium value of TCGA-Mitophagy score. It is noteworthy that the present study is the first to demonstrate a new classification based on the mitophagy of breast cancer, which comes up with a new perspective for the assessment and prognoses of BRCA.

Retracted: Diagnosis of Breast Cancer Pathology on the Wisconsin Dataset with the Help of Data Mining Classification and Clustering Techniques

Retracted: Diagnosis of Breast Cancer Pathology on the Wisconsin Dataset with the Help of Data Mining Classification and Clustering Techniques

Multi-threshold Image Segmentation based on an improved Salp Swarm Algorithm: Case study of breast cancer pathology images

Breast cancer poses a significant risk to women’s health, and it is essential to provide proper diagnostic support. Medical image processing technology is a key component of all supporting diagnostic techniques, with Image Segmentation (IS) being one of its primary steps. Among various methods, Multilevel Image Segmentation (MIS) is considered one of the most effective and straightforward approaches. Many researchers have attempted to improve the quality of image segmentation by combining different metaheuristic algorithms with MIS. However, these methods often suffer from issues such as low convergence accuracy and a proclivity for converging towards Local Optima (LO). To overcome these challenges, this study introduces an integrated approach that combines the Salp Swarm Algorithm (SSA), Slime Mould Algorithm (SMA) and Differential Evolution (DE) algorithm. In this manuscript, we introduce an innovative hybrid MIS model termed SDSSA, which leverages elements from the SSA, SMA and DE algorithms. The SDSSA model fundamentally relies on non-local means 2D histogram and 2D Kapur’s entropy. To evaluate the proposed method effectively, we compare it initially with similar algorithms using the IEEE CEC2014 benchmark functions. The SDSSA showcases enhanced convergence velocity and precision relative to similar algorithms. Furthermore, this paper proposes an excellent MIS method. Subsequently, IS experiments were conducted separately at both low and high threshold levels. The test results demonstrate that the segmentation outcomes of MIS, at both low and high threshold levels, outperform other methods. This validates SDSSA as a superior segmentation technique that provides practical assistance for future research in breast cancer pathology image processing.

Yolov5 AI Deep Learning model driven Nuclear Pleomorphism Grading on Breast Cancer Pathology WSI for Nottingham Cancer Grading

Breast cancer is the second largest cancer caused in the world due to the uncontrollable growth in breast cells. Nottingham Grading is the internationally acceptable system to grade breast cancer. Nuclear pleomorphism is one of the breast cancer biomarkers for computing Nottingham grading. Pathologists grade nuclear pleomorphism on breast cancer glass tissue slides using a conventional microscope which is time consuming and has considerable inter-observer variability between pathologists. The paper proposed an Artificial Intelligence (AI) deep learning model to grade grade1, grade2, grade3 nuclear pleomorphism on breast cancer whole slide images (WSI). The proposed Yolov5 model is trained and tested on 1,30,000 WSI tiles having around two lakh annotations. The accuracy of the model is mAP 0.89. The proposed model saves the time and reduces the workload of the pathologist and also helps them to produce accurate results.

Application of Biosensors in Detecting Breast Cancer Metastasis.

Breast cancer has garnered global attention due to its high incidence worldwide, and even more noteworthy is that approximately 90% deaths due to breast cancer are attributed to cancer metastasis. Therefore, the early diagnosis of breast cancer metastasis holds significant importance for reducing mortality outcomes. Biosensors play a crucial role in the early detection of metastatic breast cancer due to their advantages, such as ease of use, portability, and real-time analysis capabilities. This review primarily described various types of sensors for detecting breast cancer metastasis based on biomarkers and cell characteristics, including electrochemical, optical, and microfluidic chips. We offered detailed descriptions of the performance of these various biosensors and made comparisons between them. Furthermore, we described the pathology of breast cancer and summarized commonly used biomarkers for metastatic breast cancer. Finally, we discussed the advantages of current-stage biosensors and the challenges that need to be addressed, as well as prospects for their future development.

Developing prompts from large language model for extracting clinical information from pathology and ultrasound reports in breast cancer.

We aimed to evaluate the time and cost of developing prompts using large language model (LLM), tailored to extract clinical factors in breast cancer patients and their accuracy. We collected data from reports of surgical pathology and ultrasound from breast cancer patients who underwent radiotherapy from 2020 to 2022. We extracted the information using the Generative Pre-trained Transformer (GPT) for Sheets and Docs extension plugin and termed this the "LLM" method. The time and cost of developing the prompts with LLM methods were assessed and compared with those spent on collecting information with "full manual" and "LLM-assisted manual" methods. To assess accuracy, 340 patients were randomly selected, and the extracted information by LLM method were compared with those collected by "full manual" method. Data from 2,931 patients were collected. We developed 12 prompts for Extract function and 12 for Format function to extract and standardize the information. The overall accuracy was 87.7%. For lymphovascular invasion, it was 98.2%. Developing and processing the prompts took 3.5 hours and 15 minutes, respectively. Utilizing the ChatGPT application programming interface cost US $65.8 and when factoring in the estimated wage, the total cost was US $95.4. In an estimated comparison, "LLM-assisted manual" and "LLM" methods were time- and cost-efficient compared to the "full manual" method. Developing and facilitating prompts for LLM to derive clinical factors was efficient to extract crucial information from huge medical records. This study demonstrated the potential of the application of natural language processing using LLM model in breast cancer patients. Prompts from the current study can be re-used for other research to collect clinical information.

Improved Breast Cancer Classification through Combining Transfer Learning and Attention Mechanism.

Breast cancer, a leading cause of female mortality worldwide, poses a significant health challenge. Recent advancements in deep learning techniques have revolutionized breast cancer pathology by enabling accurate image classification. Various imaging methods, such as mammography, CT, MRI, ultrasound, and biopsies, aid in breast cancer detection. Computer-assisted pathological image classification is of paramount importance for breast cancer diagnosis. This study introduces a novel approach to breast cancer histopathological image classification. It leverages modified pre-trained CNN models and attention mechanisms to enhance model interpretability and robustness, emphasizing localized features and enabling accurate discrimination of complex cases. Our method involves transfer learning with deep CNN models-Xception, VGG16, ResNet50, MobileNet, and DenseNet121-augmented with the convolutional block attention module (CBAM). The pre-trained models are finetuned, and the two CBAM models are incorporated at the end of the pre-trained models. The models are compared to state-of-the-art breast cancer diagnosis approaches and tested for accuracy, precision, recall, and F1 score. The confusion matrices are used to evaluate and visualize the results of the compared models. They help in assessing the models' performance. The test accuracy rates for the attention mechanism (AM) using the Xception model on the "BreakHis" breast cancer dataset are encouraging at 99.2% and 99.5%. The test accuracy for DenseNet121 with AMs is 99.6%. The proposed approaches also performed better than previous approaches examined in the related studies.

Familial genetic cancer risk assessment in a male patient with pancreatic and breast cancer with a silent BRCA2 mutation

Male breast cancer (MBC) is relatively rare, accounting for &lt;1% of cancers in men. Hereditary MBC is mainly attributed to BRCA1/2 germline mutations. Accordingly, National Comprehensive Cancer Network guidelines advise genetic counseling and testing for all cases of MBCs and their unaffected family members. In this report, we present an uncommon case of a male patient in his late 50s primarily diagnosed with pancreatic cancer who later developed asynchronous bilateral hormone-positive breast cancer. Genetic testing revealed a “pathogenic/likely pathogenic” BRCA2 variant (c.8754G &gt;A, pE2918E) in the proband. Cascade testing of 34 family members identified 5 of the family members as carriers of this BRCA2 variant. Among them, two members were breast cancer affected and three were unaffected healthy carriers. Our study demonstrates the clinical relevance of this silent BRCA2 mutation and emphasizes the need for further experimental studies to elucidate its functional role in breast cancer pathology.

Adversarial Attack and Defense in Breast Cancer Deep Learning Systems.

Deep-learning-assisted medical diagnosis has brought revolutionary innovations to medicine. Breast cancer is a great threat to women's health, and deep-learning-assisted diagnosis of breast cancer pathology images can save manpower and improve diagnostic accuracy. However, researchers have found that deep learning systems based on natural images are vulnerable to attacks that can lead to errors in recognition and classification, raising security concerns about deep systems based on medical images. We used the adversarial attack algorithm FGSM to reveal that breast cancer deep learning systems are vulnerable to attacks and thus misclassify breast cancer pathology images. To address this problem, we built a deep learning system for breast cancer pathology image recognition with better defense performance. Accurate diagnosis of medical images is related to the health status of patients. Therefore, it is very important and meaningful to improve the security and reliability of medical deep learning systems before they are actually deployed.

Examining the Completeness of Breast Cancer Pathology Reports Registered in the Population-based Cancer Registration System and Spatial Analysis of the Incidence of this Cancer in Iran in 2016

Background: Breast cancer (BC) is a leading cause of cancer-related deaths among women worldwide, and its incidence has increased in Iran over recent years. Objectives: In this study, we aimed at assessing the completeness of BC pathology reports in the population-based cancer registration system and perform a spatial analysis of the incidence of this cancer in Iran in 2016 to help policymakers develop targeted interventions. Methods: We conducted a retrospective descriptive analysis, using secondary data from the Integrated Cancer Information Management System, and obtained 13789 BC pathology reports from all provinces in Iran in 2016. Pathology data, including tumor type, tumor site, tumor size, pathologic T stage, pathologic N stage, and tumor grade were examined for completeness by age group. Results: Pathology reports from 4000 women with BC in 2016 from across all provinces of Iran were selected for this study. The completeness of tumor type, tumor site, tumor size, pathologic T stage, pathologic N stage, and tumor grade increased with aging. In addition, the completeness of pathology reports varied across different variables. Accordingly, the tumor grade and pathologic T stage had the highest and lowest completeness rates (100 % versus 27.4%), respectively. Spatial analysis revealed significant high-risk areas for BC incidence, including Isfahan, Markazi, Chaharmahal and Bakhtiari, and Kohgiluyeh and Boyer-Ahmad provinces in central Iran. In contrast, North Khorasan was identified as a low-risk area. Conclusions: Considering the incompleteness of the pathology report in most of the tumor variables in the BC registry, we recognize the gaps to improve pathology data. To ensure effective interventions for BC control, tailored preventive measures are needed, particularly for high-risk areas. Continuous evaluation and data completion, including standard cellular pathology reports, are necessary for accurate BC control in Iran.

High Atlastin 2-2 (ATL2-2) Expression Associates with Worse Prognosis in Estrogen-Receptor-Positive Breast Cancer.

The disruption of endoplasmic reticulum (ER) homeostasis occurs in many human diseases. Atlastins (ATLs) maintain the branched network of the ER. The dysregulation of ATL2, located at ER network junctions, has been associated with cancer. ATL2 is necessary for lipid droplet formation in murine breast tissue. Thus, we analyzed whether ATL2 has a role in human breast cancer (BC) pathology. The expression of ATL2 variant ATL2-2 was analyzed in breast tumors from the BC cohorts of the TCGA, METABRIC, and two independent Icelandic cohorts, Cohort 1 and 2; its association with clinical, pathological, survival, and cellular pathways was explored. ATL2-2 mRNA and protein expression were higher in breast tumors than in normal tissue. ATL2-2 mRNA associated with tumor characteristics that indicate a worse prognosis. In METABRIC, high ATL2-2 mRNA levels were associated with shorter BC-specific survival (BCSS) in patients with estrogen-receptor-positive luminal breast tumors, which remained significant after correction for grade and tumor size (HR 1.334, CI 1.063-1.673). Tumors with high ATL2 mRNA showed an upregulation of hallmark pathways MYC targets v1, E2F targets, and G2M checkpoint genes. Taken together, the results suggest that high levels of ATL2-2 may support BC progression through key cancer driver pathways.

Advances in the application of computational pathology in diagnosis, immunomicroenvironment recognition, and immunotherapy evaluation of breast cancer: a narrative review.

Breast cancer (BC) is a prevalent and highly lethal malignancy affecting women worldwide. Immunotherapy has emerged as a promising therapeutic strategy for BC, offering potential improvements in patient survival. Neoadjuvant therapy (NAT) has also gained significant clinical traction. With the advancement of computer technology, Artificial Intelligence (AI) has been increasingly applied in pathology research, expanding and redefining the scope of the field. This narrative review aims to provide a comprehensive overview of the current literature on the application of computational pathology in BC, specifically focusing on diagnosis, immune microenvironment recognition, and the evaluation of immunotherapy and NAT response. A thorough examination of relevant literature was conducted, focusing on studies investigating the role of computational pathology in BC diagnosis, immune microenvironment recognition, and immunotherapy and NAT assessment. The application of computational pathology has shown significant potential in BC management. AI-based techniques enable improved diagnosis and classification of BC subtypes, enhance the identification and characterization of the immune microenvironment, and facilitate the evaluation of immunotherapy and NAT response. However, challenges related to data quality, standardization, and algorithm development still need to be addressed. The integration of computational pathology and AI has transformative implications for BC patient care. By leveraging AI-based technologies, clinicians can make more informed decisions in diagnosis, treatment planning, and therapeutic response assessment. Future research should focus on refining AI algorithms, addressing technical challenges, and conducting large-scale clinical validation studies to facilitate the translation of computational pathology into routine clinical practice for BC patients.

Urolithin A: A promising selective estrogen receptor modulator and 27-hydroxycholesterol attenuator in breast cancer.

27-hydroxycholesterol (27-HC) is an oxysterol that acts as an endogenous selective estrogen receptor modulator (SERM), and its adverse effects on breast cancer via the estrogen receptor (ER) have provided new insights into the pathology of cholesterol-linked breast cancer. Our earlier in vitro experiments showed that the methanolic extract of pomegranate could exhibit SERM properties and compete with 27-HC. The major constituents of pomegranate are ellagitannins and ellagic acid, which are converted into urolithins by the colonic microbiota. In recent years, urolithins, especially urolithin A (UA) and urolithin B (UB), have been reported to have a plethora of advantageous effects, including antiproliferative and estrogenic activities. In this study, we attempted to determine the potential of urolithins in antagonizing and counteracting the adverse effects of 27-HC in breast cancer cells. Our findings suggested that UA had an antiproliferative capacity and attenuated the proliferative effects of 27-HC, resulting in subsequent loss of membrane potential and apoptosis in breast cancer cells. Further, UA induced estrogen response element (ERE) transcriptional activity and modulated estrogen-responsive genes, exhibiting a SERM-like response concerning receptor binding. Our in vivo hollow fiber assay results showed a loss of cell viability in breast cancer cells upon UA consumption, as well as a reduction in 27-HC-induced proliferative activity. Additionally, it was shown that UA did not induce uterine proliferation or alter blood biochemical parameters. Based on these findings, we can conclude that UA has the potential to act as a potent estrogen receptor alpha (ERα) modulator and 27-HC antagonist. UA is safe to consume and is very well tolerated. This study further opens up the potential of UA as ER modulator and its benefits in estrogen-dependent tissues.

Special issue. De-escalation of loco-regional treatment in breast cancer: Time to find the balance? Partial breast irradiation.

Breast cancer is the most common cancer in women worldwide. Over the past few decades, remarkable progress has been made in understanding the biology and pathology of breast cancer. A personalized conservative approach has been currently adopted addressing the patient's individual risk of relapse. After postoperative whole breast irradiation for early-stage breast cancer, a rate of recurrences outside the initial tumour bed lower than 4% was observed. Thus, the highest benefits of breast irradiation seem to result from the dose delivered to the tissue neighbouring the tumour bed. Nonetheless, reducing treatment morbidity while maintaining radiation therapy's ability to decrease local recurrences is an important challenge in treating patients with radiation therapy. In this regard, strategies such as partial-breast irradiation have been developed to reduce toxicity without compromising oncologic outcomes. According to the national and international published guidelines, clinical oncologists can refer to specific dose/fractionation schedules and eligible criteria. However, there are still some areas of open questions. Breast cancer represents a multidisciplinary paradigm; it should be considered a heterogeneous disease where a "one-treatment-fits-all" approach cannot be considered an appropriate option. This is a wide overview on the main partial breast irradiation advantages, risks, timings, techniques, and available recommendations. We aim to provide practical findings to support clinical decision-making, exploring future perspectives, towards a balance for optimisation of breast cancer.

Clinical Pathology of Breast Cancer: Staging and Biomarkers

Based on recent statistics, one in every eight women will be diagnosed with breast cancer in their life. Breast cancer is classified into a staging system that ranges from zero to four, which is determined by several factors. In the staging system, the clinical pathology taken and tested by the healthcare professional plays a key role in determining the gravity of the patient's case. Biomarkers provide insight into the carcinogenic cells in the person's body, such as the Estrogen receptor (ER), human epidermal growth factor (HER2), and the progesterone receptor which are discussed in this paper. Each of these biomarkers communicates a specific attribute about the tumor cells and signifies the severity and the extent of the breast cancer. Based on this research, it was proven that there is not a direct correlation, but a slight correlation between the biomarkers found in the cells with the relative stage the patient has. Studies have shown a link between cells testing HER2 positive with high-grade tumors, unfavorable prognosis, lymph node collusion, high mortality rates, and higher rates of recurrence in patients which signify a stage three or four cancer. Studies also suggested that patients who test ER positive, PR negative, and HER2 negative are more likely to have early-stage invasive breast cancer, which alludes to stage one or two clinically. A definite conclusion was not able to be obtained as more research must be conducted, however, general trends were discovered between stages and biomarkers.

Features of ovarian steroidogenesis and endometrial hypertrophy during adjuvant therapy with tamoxifen in premenopausal patients with hormone-dependent breast cancer

Background. Difficulties in the prevention and treatment of endometrial pathology in hormone-positive breast cancer are associated with the lack of an unambiguous understanding of the mechanisms of the effect of tamoxifen on target tissues and the development of possible hyperestrogenism.Aim. To study the effect of ovarian steroidogenesis on the endometrium during adjuvant therapy with tamoxifen in pre-menopausal patients with hormone-dependent breast cancer.Materials and methods. All patients at inclusion in the study had intact menstrual function and received adjuvant therapy with tamoxifen. Group 1 included 42 patients without chemotherapy, group 2 included 41 patients with chemotherapy. Depending on the safety of the menstrual function, each group was divided into 2 subgroups. At the control points (3, 6 and 9 months from the start of tamoxifen therapy) patients underwent transvaginal ultrasound with measurement of endometrial thickness, and also determined the content of follicle-stimulating hormone and estradiol in peripheral blood. When menstruation persisted, blood sampling and measurement of endometrial thickness were performed on days 5-8 of the menstrual cycle.Results. In subgroups 1A and 2C, patients with preserved menstrual function showed a trend towards higher values of estradiol levels and endometrial thickness, compared with subgroups 1B and 2D of patients with amenorrhea. Against this background, the absence of statistically significant intergroup differences in the content of follicle-stimulating hormone in patients receiving tamoxifen with a preserved menstrual cycle (1A and 2C) and amenorrhea (1B and 2D) attracts attention. An intragroup analysis of follicle-stimulating hormone dynamics in patients with amenorrhea without chemotherapy in subgroup 1C shows an increase in its content by 162 %, without statistically significant changes in endometrial thickness and estradiol concentration. The statistically significant increase in endometrial thickness by 25 % and the proportion of patients with increasing endometrial wall thickness in 63.3 % in the 2D subgroup in patients receiving tamoxifen, with amenorrhea and previous chemotherapy treatment are cause for concern.Conclusion. The results of the study indicate a possible additive effect of such factors as intact menstrual function before the start of treatment for hormone-positive breast cancer, chemotherapy, and the development of amenorrhea on the progressive increase in endometrial thickness when using tamoxifen in premenopausal patients.

Breast cancer and the molecular mechanism of estrogen signaling

Cancer is a complex pathology that occurs due to the uncontrolled proliferation and growth of cells in any organ or tissue of the body. Breast cancer is the most frequently diagnosed cancer among women worldwide and is the second leading cause of cancer-related deaths. Breast cancer is a pathology that exhibits heterogeneity in which genetic and environmental risk factors play a role. Although many treatment approaches have been developed for breast cancer today, the frequency of the number of patients diagnosed with breast cancer and lost their lives due to this reason is increasing in the world. The most significant limitation to the success of the treatment approaches developing drug resistance in breast cancer cells, and the disease relapses after a certain period and exhibits a more aggressive profile. Therefore, understanding the molecular biology of breast cancer is essential for developing potent therapeutic approaches. It is known that the development of breast cancer is related to changes in direct and indirect signaling mechanisms mediated by estrogen and estrogen receptor. These signaling mechanisms exhibit highly complex interaction patterns. This review summarizes the pathology of breast cancer, estrogenic compounds, estrogen receptors, genomic and non-genomic molecular signaling mechanisms mediated by estrogen and estrogen receptor.

High platelet count as a predicting factor of histopathological grading among invasive breast cancer individuals: a single centre experience from Indonesia.

The interplay between platelet and breast cancer (BC) pathology may have the potential to represent the malignancy status itself, evidently through predicting the histopathological results of each individual. This study aims to elaborate on the diagnostic value of a higher platelet count or thrombocytosis and the histopathological status of invasive BC in our center, explaining its correlation from the diagnostic perspective. A retrospective cohort study was conducted using breast cancer patients' medical records from January to March 2022 at the Haji Adam Malik General Hospital, Medan, Indonesia. The patients' histopathological records and complete blood counts were collected from the hospital's medical records. We analyzed the risk analysis model in receiver operator characteristics analysis and diagnostic parameters, e.g., sensitivity and specificity, which we analyzed further using the correlation test to fulfill our objective. The mean age of the 69 subjects we included, in the final analysis, was 49.0 ± 11.1 years old, of whom 35 (50.7%) individuals were histologically confirmed to be high-grade BC. By applying the cut-off value of 299 × 103 cells/μL, the diagnostic value of a platelet count was 60.0 % in sensitivity, 61.8% in specificity, and an area under the curve (AUC) value of 0.597 (0.462-0.732) in 95% confidence interval (CI) as presented by receiver operating characteristic (ROC). We also found that a higher platelet count may also predict the diagnosis of invasive BC by 2.423 times as shown in the odd ratio (OR) analysis. Platelet counts investigation is an applicable yet potential hematological biomarker to predict invasive BC histopathological grading.