Breast Cancer Classification in Ultrasound Images Using Convolutional Neural Network (CNN) with Watershed Transform Method

Optimization and normalization strategies for long term untargeted HILIC-LC-qTOF-MS based metabolomics analysis: Early diagnosis of breast cancer

Although breast cancer, with easy recurrence and high mortality, has become one of the leading causes of cancer death in women, early and accurate diagnosis of breast cancer can effectively increase the likelihood of a cure. Therefore, it is particularly important to improve the accuracy of early diagnosis of breast cancer. However, conventional early diagnosis relies on human experience and has a low accuracy rate. Therefore, many researchers have proposed various machine learning methods to improve the accuracy and efficiency of prediction. Most of the existing studies around breast cancer classification adopt a single algorithm to fit breast cancer data but ignore the applicability of different breast cancer data features to the model. In this paper, we adopt machine algorithms to strip the features of machine learning methods from the rest of the features and attempt to enhance the model effect by designing deep learning model structures to find the hidden patterns in the rest of the features. In addition, due to strict medical data privacy requirements and high collection difficulty and cost, the model designed in this paper will be trained on a small number of samples. As a result, we attempt to find a minimization model for a breast cancer classification algorithm that features both low cost and high efficiency. At the same time, the deep learning model is further designed to complement the original model when it is possible to introduce complex data indicators. Experimental values show that the design model in this paper performs best not only under limited data and limited indicators but also under limited data complex indicators, demonstrating the effectiveness of the approach of mixed comparison and feature selection of multiple classification algorithms. In summary, the fusion model designed and implemented in this paper performs well in the experiments, and the accuracy of the model test reaches 98.3%.

Breast cancer is the primary malignant tumor that endangers women's health. The incidence of breast cancer is increasing rapidly in recent years. Accurate disease evaluation before treatment is the key to the selection of treatment options. Biomedical imaging technology plays an irreplaceable role in the diagnosis and staging of tumors. Various imaging methods can provide excellent temporal and spatial resolution from multiple levels and perspectives and have become one of the most commonly used means of breast cancer early detection. With the development of radiomics, it has been found that early imaging diagnosis of breast cancer plays an important guiding role in clinical decision-making. The purpose of this study is to explore the characteristics of various breast cancer imaging technologies, promote the development of individualized accurate diagnosis and treatment of imaging, and improve the clinical application value of radiomics in the early diagnosis of breast cancer.

A time for creative collaboration

BackgroundBreast cancer is the second leading cause of cancer related deaths in women worldwide. Reports about the early diagnosis of breast cancer are suggestive of an improved clinical outcome and overall survival rate in cancer patients. Therefore, cancer screening biomarker for early detection and diagnosis is urgently required for timely treatment and better cancer management. In this context, we investigated an association of cancer testis antigen, A-Kinase anchor protein 4 (AKAP4) with breast carcinoma.Methodology/FindingsWe first compared the AKAP4 gene and protein expression in four breast cancer cells (MCF7, MDA-MB-231, SK-BR3 and BT474) and normal human mammary epithelial cells. In addition, 91 clinical specimens of breast cancer patients of various histotypes including ductal carcinoma in situ, infiltrating ductal carcinoma and infiltrating lobular carcinoma and 83 available matched adjacent non-cancerous tissues were examined for AKAP4 gene and protein expression by employing in situ RNA hybridization and immunohistochemistry respectively. Humoral response against AKAP4 was also investigated in breast cancer patients employing ELISA. Our in vitro studies in all breast cancer cells revealed AKAP4 gene and protein expression whereas, normal human mammary epithelial cells failed to show any expression. Using in situ RNA hybridization and immunohistochemistry, 85% (77/91) tissue specimens irrespective of histotypes, stages and grades of breast cancer clinical specimens revealed AKAP4 gene and protein expression. However, matched adjacent non-cancerous tissues failed to display any AKAP4 gene and protein expression. Furthermore, humoral response was observed in 79% (72/91) of total breast cancer patients. Interestingly, we observed that 94% (72/77) of breast cancer patients found positive for AKAP4 protein expression generated humoral response against AKAP4 protein.ConclusionsCollectively, our data suggests that AKAP4 may be used as serum based diagnostic test for an early detection and diagnosis of breast cancer and may be a potential target for immunotherapeutic use.

Breast cancer remains the leading cause of death in the female population. Screening studies are conducted in order to detect the disease at an early stage. At the same time, domestic authors emphasize the lack of alternatives to preventive mammography in breast cancer screening and the prospects of using mobile mammographs for early diagnosis of breast cancer and precancerous breast diseases.Aim. To evaluat the results of the use of mobile mammography units for active and early detection of breast cancer.Materials and methods. The research uses methods of content analysis, information and analytical materials of Russian and foreign researchers, and forms of federal statistical observation. Statistical research methods were used to analyze the data obtained.Results. Regression analysis with a very low probability of error (p = 0.001) showed that the larger the total volume of mammographic studies with preventive purposes in the subjects of the Russian Federation, the higher the proportion of cases of active detection of breast cancer, although this relationship is rather weak. Taking into account the obtained value of R2 (0.192), only 19.2% of the increase in the proportion of breast cancer cases detected actively can be explained by an increase in the volume of preventive mammograms. The correlation analysis showed that the volumes of preventive mammograms performed using mobile devices in the subjects of the Russian Federation were not associated with either the proportion of breast cancer cases detected actively or with the proportion of breast cancer cases detected in the early stages. At the same time, it is worth noting that the obtained value of p ≥ 0.5 indicates a statistically insignificant result of evaluating the relationship between variables, the interpretation of which should be performed with caution.Conclusion. Despite the high cost of mobile mammography units, the increase in their number in the subjects of the Russian Federation and the growth in their activities, the contribution of these diagnostic devices to solving the problem of early and active diagnosis of breast cancer remains uncertain. More promising are personalized approaches to the timely detection of cancers, including breast cancer, based on an assessment of the individual risk of their occurrence.

BackgroundEarly diagnosis is a key determinant of breast cancer prognosis and survival. More than half of breast cancer cases are diagnosed at an advanced stage in Ethiopia, and the barriers to early diagnosis in this country are not well understood. We aimed to identify the perceived barriers to early diagnosis of breast cancer from the perspective of patients and health care providers in south and southwestern Ethiopia.MethodsA qualitative study was conducted from March to April 2018 using in-depth interviews of breast cancer patients and breast cancer health care providers from six public hospitals located in urban and rural areas of south and southwestern Ethiopia. All participants provided verbal consent before participating. A thematic analysis was performed using Open Code 4.02.ResultsTwelve breast cancer patients and thirteen health care providers were included in the study. Patient and health-system related barriers to early diagnosis of breast cancer were identified. Patient-related barriers were lack of knowledge and awareness of breast cancer, belief in traditional medicine and religious practices for treatment, and lack of social and financial support to seek care at a medical facility. Health-system related barriers were misdiagnosis of breast cancer, long distance to referral facilities, high cost of diagnostic services, long waiting time for diagnostic tests, and lack of screening and diagnostic tests in local facilities.ConclusionsEarly diagnosis of breast cancer is affected by multiple barriers in south and southwestern Ethiopia. Awareness campaigns and education about the disease, prevention, and early detection are needed to increase early diagnosis of breast cancer. Opportunities exist to improve early diagnosis and timely treatment in rural areas.

The early and precise diagnosis of breast cancer is one of the most important factors in enhancing survival rates. Despite considerable improvements in screening methods, medical imaging, and treatment approaches, the issue of reliable early detection remains a significant problem due to instability in clinical interpretation and the complexity of diagnostic information. Conventional methods of diagnosis emphasize the analysis of clinical and histopathological information, which are prone to inter-observer error and do not necessarily reveal subtle patterns related to disease progression. Artificial Intelligence has demonstrated enormous potential in alleviating these weaknesses. Ensemble methods, as well as support vector machines and gradient boosting-based algorithms such as XGBoost and LightGBM, have shown excellent results in the analysis of structured clinical data. Simultaneously, deep learning (DL) systems, specifically convolutional neural networks (CNNs), have been demonstrated to be exceptionally successful in medical image analysis such as mammography and histopathology. However, the interpretability of such models remains a major obstacle to their usage in clinical practice. To address this problem, Explainable Artificial Intelligence (XAI) methods, including SHAP, LIME, and Grad-CAM, have been proposed to improve model transparency and contribute significantly to understanding how decisions are made. This paper reviews recent developments in ML, DL, and XAI in relation to breast cancer diagnosis. It examines commonly used datasets, evaluation metrics, and trends, and also reports the most significant issues, including data constraints, lack of interpretability, and challenges in multimodal integration. Moreover, this paper identifies knowledge gaps in existing research and highlights the necessity of developing robust, explainable, and actionable AI-based diagnostic systems.

The impact of tyrosine metabolism on the early diagnosis and treatment of breast cancer remains unclear. This underlines importance of exploring its mechanisms. This study conducted an integrated analysis of breast cancer transcriptome data from the TCGA and GEO databases, utilizing differential expression analysis, enrichment analysis, immune infiltration analysis, single-cell RNA sequencing analysis, hdWGCNA analysis, and molecular docking to investigate the role of tyrosine metabolism in breast cancer and its relationship with chemotherapy response. The co-expression prognosis model of tyrosine metabolism developed in this study demonstrated superior performance in the prognostic assessment of breast cancer, achieving an AUC value of 0.735, surpassing traditional clinical indicators. The identified two key genes(MAOA, MAOB) and their interaction network showed significant value in the diagnosis and prognosis of breast cancer. Moreover, the early diagnosis model "Extra Trees (BO)" developed using machine learning algorithms exhibited excellent stability and generalization capability. These findings not only highlight the critical role of tyrosine metabolism in regulating the tumor immune microenvironment but also mark Monoamine oxidase A (MAOA) and Monoamine oxidase B (MAOB) as important potential biomarkers linking immunotherapy and chemotherapy. This research provides an effective model for the prognostic assessment and early diagnosis of breast cancer, opening new avenues for research into the precision treatment of breast cancer and the management of chemotherapy side effects.

BackgroundThe incidence of malignancies in kidney transplant recipients is increasing. Breast cancer is a common malignancy after kidney transplantation and can be more aggressive in kidney transplant recipients than in the general population. In this study, we evaluated the incidence and prognosis of breast cancer in kidney transplant recipients.FindingsBetween 1993 and 2013, 750 kidney transplant patients were followed-up at our center. Since 1999, annual physical examination, mammography, and breast ultrasonography have been performed for such patients. Diagnostic studies, including core needle or mammotome biopsy, were performed for suspected malignancies. Patients with malignant neoplasm were administered the appropriate treatment and followed-up to assess tumor response and symptoms.Nine patients were diagnosed with breast cancer during the follow-up period. The mean age at the initial detection of the breast cancer was 47.7 ± 8.4 years. The mean interval from transplantation to diagnosis was 148.7 ± 37.1 months. Of the 9 patients, 8 were detected through the screening test; 7 were treated with breast conservative surgery and 1 was treated with modified radical mastectomy. The cancer stages were 0 (n = 2), I (n = 6), and II (n = 1). The incidence of breast cancer tended to be unchanged with time between transplantation and diagnosis, inconsistent with the increase in the duration of immunosuppression.ConclusionAnnual screening tests are crucial in the early diagnosis of breast cancer. Early treatment of breast cancer can result in an excellent prognosis in kidney transplant recipients.

Breast cancer is one of the common malignancies among females in Saudi Arabia and has also been ranked as the one most prevalent and the number two killer disease in the country. However, the clinical diagnosis process of any disease such as breast cancer, coronary artery diseases, diabetes, COVID-19, among others, is often associated with uncertainty due to the complexity and fuzziness of the process. In this work, a fuzzy neural network expert system with an improved gini index random forest-based feature importance measure algorithm for early diagnosis of breast cancer in Saudi Arabia was proposed to address the uncertainty and ambiguity associated with the diagnosis of breast cancer and also the heavier burden on the overlay of the network nodes of the fuzzy neural network system that often happens due to insignificant features that are used to predict or diagnose the disease. An Improved Gini Index Random Forest-Based Feature Importance Measure Algorithm was used to select the five fittest features of the diagnostic wisconsin breast cancer database out of the 32 features of the dataset. The logistic regression, support vector machine, k-nearest neighbor, random forest, and gaussian naïve bayes learning algorithms were used to develop two sets of classification models. Hence, the classification models with full features (32) and models with the 5 fittest features. The two sets of classification models were evaluated, and the results of the evaluation were compared. The result of the comparison shows that the models with the selected fittest features outperformed their counterparts with full features in terms of accuracy, sensitivity, and sensitivity. Therefore, a fuzzy neural network based expert system was developed with the five selected fittest features and the system achieved 99.33% accuracy, 99.41% sensitivity, and 99.24% specificity. Moreover, based on the comparison of the system developed in this work against the previous works that used fuzzy neural network or other applied artificial intelligence techniques on the same dataset for diagnosis of breast cancer using the same dataset, the system stands to be the best in terms of accuracy, sensitivity, and specificity, respectively. The z test was also conducted, and the test result shows that there is significant accuracy achieved by the system for early diagnosis of breast cancer.

In Asian countries, breast densities and the proportion of younger women with breast cancer are higher than those in Western countries. This study was designed to determine differences in stage at diagnosis of breast cancer among Korean women according to screening history. The study population was derived from the Korea National Cancer Screening Program (KNCSP). The study cohort comprised 17,689 women who were newly diagnosed with breast cancer in 2011 and were invited to undergo breast cancer screening via the KNCSP between 2002 and 2011. Ductal carcinoma in situ (DCIS) and localized breast cancer were most frequent in both ever-screened and never-screened patients. Late stage cancer was significantly more frequent in never-screened patients, compared with ever-screened patients. Compared to never-screened women, the odds ratio (OR) for being diagnosed with early stage breast cancer among screened women was 1.41 (95% Confidence Interval [CI] = 1.28–1.55). The OR for being diagnosed with early stage breast cancer was highest among patients who underwent screening three times or more (aOR = 1.89, 95% CI = 1.57–2.29). Screening by mammography was associated with diagnosis of early stage breast cancer in Korean women. However, significant increases in the diagnosis of DCIS and localized breast cancers among ever-screened patients suggest the possibility of overdiagnosis due to screening.

Breast cancer or ductal carcinoma is prevalent in women and is the leading cause of women's death worldwide. Delaying breast cancer or tumor growth has long-term effects, can also become life-threatening. So the tumor should be identified as early as possible to control the growth and preventing to spread to other tissues. Several types of researches have been done to detect breast cancer early so that the treatment can be started to increase the chance of survival. A mammography procedure for early detection and diagnosis of breast cancer is commonly advised. There are so many techniques that are used for malignancy prediction. Using Artificial Intelligence-powered machine learning is widely recommended. Researches are conducted in machine learning to detect cancerous tumors in the human body. Mainly used algorithms which give high accuracy are SVM, naïve bays, decision trees, KNN. Deep learning, the machine learning sub-branch, can also be used to classify breast cancer. Deep learning is a method that is mostly used to clear, rectify, and detect machine learning errors or disadvantages. Convolutional Neural Networks are the perfect deep learning method for overcoming the drawbacks of machine learning in malignancy detection; however, other strategies such as a recurrent neural network and a deep belief network are being used to overcome the shortcomings of machine learning. As a consequence, using deep learning rather than machine learning yields better results. This review paper's primary motivation is to make budding researchers aware that breast cancer is a serious issue among women and we need to be swift in using different technologies to detect and to improve accuracy as efficiently as possible, it is very important to save our mothers, sisters, loved ones and our society from this dangerous predator. In this review paper, we have discussed all the techniques used by different authors.

Breast cancer is one of the most malignant tumors in women across the globe. Diagnosis of breast cancer at early stages is essential to improve treatment outcomes and decrease mortality rates. There is a pressing need for new non-invasive biomarkers to improve early diagnosis of breast cancer. This study aims to assess plasma miR-27a for the early diagnosis of breast cancer. miR-27a was evaluated in a total of 95 blood samples, 40 newly diagnosed cancer patients, 20 patients with benign breast lesions, 20 females with positive family history for breast cancer and 15 apparently healthy controls, using quantitative real time polymerase chain reaction. Our results exhibited significantly higher expression level of plasma miR-27a in breast cancer patients (median= 8.3 and 19 fold change for early and late stages respectively) compared to controls, high risk group and benign group with (P <0.001) for each. Plasma miR-27a was significantly higher in late breast cancer (median=19 fold change) compared to early breast cancer (median= 8.3) with (P <0.001). There was no statistically significant difference of plasmamiR-27a levels in benign group (median=1.8 fold change) compared to both control group and high risk group. There was no statistically significant difference of plasma miR-27a levels in high risk group (median= 1.2 fold change) compared to control group (median= 1 fold change). We performed Receiver Operating Characteristic (ROC) analysis for discriminating malignant from non-malignant cases. Plasma miR-27a yielded an area under the curve (AUC) of 0.983 with sensitivity 97.5%, specificity 91% and accuracy 94%.We concluded that miR-27a expression level represents sensitive and specific non-invasive molecular biomarkers for diagnosis of breast cancer.

Breast cancer is one of the leading causes of mortality between women, with one in eight women diagnosed with the disease, but early detection can reduce death rates. Therefore, continuous effort is being made to advance more effective methods for the early and effective diagnosis of breast cancer with high accuracy without human intervention. Classical attempts were manual, time- consuming and ineffective in many situations. The purpose of this work is to detect and locate the presence of malignant tissues in the breast using the morphological technique in mammogram images to diagnose breast cancer because morphology is one of the most reliable methods for early detection of breast cancer. The proposed algorithm is developed using watershed segmentation after the preprocessing is completed by the median filter to eliminate any expected noise, and contouring the tumor by morphological techniques to take the best diagnostic for breast cancer in a mammogram image. Good results are obtained for the measurements used like MSE, PSNR, SNR, entropy for the mammogram images.