Early Detection Of Breast Cancer Research Articles

Orbital metastases from breast cancer: three case reports

Purpose: to describe rare cases of orbital metastases from breast cancer.Material and Methods. Three cases of Luminal A(1) and B(2) breast cancer with orbital metastases were identified and studied during the period from 01.01.2018 to 01.05.2024. Metastasis to the orbit was detected 5, 2 and 1.5 years after radical mastectomy for breast cancer. Patients received chemotherapy and radiation therapy.Results. Cases of orbital metastasis originating from breast cancer were found to have a low frequency, but may be associated with a long period between cancer diagnosis and initiation of treatment. Early detection of breast cancer and its active treatment with chemotherapy and radiation therapy are important factors in preventing orbital metastasis.Conclusion. A routine follow-up surveillance after radical treatment of breast cancer is important because there is an increase risk of developing orbital metastasis. Comprehensive strategies for treating breast cancer metastases can provide long-term disease control.

A New Breast Cancer Discovery Strategy: A Combined Outlier Rejection Technique and an Ensemble Classification Method

Annually, many people worldwide lose their lives due to breast cancer, making it one of the most prevalent cancers in the world. Since the disease is becoming more common, early detection of breast cancer is essential to avoiding serious complications and possibly death as well. This research provides a novel Breast Cancer Discovery (BCD) strategy to aid patients by providing prompt and sensitive detection of breast cancer. The two primary steps that form the BCD are the Breast Cancer Discovery Step (BCDS) and the Pre-processing Step (P2S). In the P2S, the needed data are filtered from any non-informative data using three primary operations: data normalization, feature selection, and outlier rejection. Only then does the diagnostic model in the BCDS for precise diagnosis begin to be trained. The primary contribution of this research is the novel outlier rejection technique known as the Combined Outlier Rejection Technique (CORT). CORT is divided into two primary phases: (i) the Quick Rejection Phase (QRP), which is a quick phase utilizing a statistical method, and (ii) the Accurate Rejection Phase (ARP), which is a precise phase using an optimization method. Outliers are rapidly eliminated during the QRP using the standard deviation, and the remaining outliers are thoroughly eliminated during ARP via Binary Harris Hawk Optimization (BHHO). The P2S in the BCD strategy indicates that data normalization is a pre-processing approach used to find numeric values in the datasets that fall into a predetermined range. Information Gain (IG) is then used to choose the optimal subset of features, and CORT is used to reject incorrect training data. Furthermore, based on the filtered data from the P2S, an Ensemble Classification Method (ECM) is utilized in the BCDS to identify breast cancer patients. This method consists of three classifiers: Naïve Bayes (NB), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The Wisconsin Breast Cancer Database (WBCD) dataset, which contains digital images of fine-needle aspiration samples collected from patients’ breast masses, is used herein to compare the BCD strategy against several contemporary strategies. According to the outcomes of the experiment, the suggested method is very competitive. It achieves 0.987 accuracy, 0.013 error, 0.98 recall, 0.984 precision, and a run time of 3 s, outperforming all other methods from the literature.

Comparative Performance Analysis of Ensemble Models for Breast Cancer Classification

Breast cancer remains a prevalent global health issue, accounting for approximately 2.3 million new cases and 670,000 deaths worldwide in 2022. Early detection and accurate diagnosis are crucial to improving patient outcomes, as delayed identification can lead to severe complications. Advances in machine learning (ML) have facilitated improvements in cancer diagnosis, with various algorithms enhancing predictive accuracy. This study proposes a novel ensemble model for breast cancer classification, utilizing 31 features from the University of Wisconsin Breast Cancer dataset. We applied six algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression, Random Forest, Gradient Boosting, and XGBoost—and combined them with ensemble techniques, specifically Hard Voting, to develop a high-accuracy model. The model was evaluated on classification performance metrics, achieving improvements in accuracy, precision, recall, and F1 score. Results indicate that the proposed ensemble model outperforms individual classifiers and other ensembles, showing potential as a reliable tool for early breast cancer detection.

Factors Associated with Sadari Behavior in Undana FKM Female Students Class of 2023

Introduction: Breast cancer is an abnormal cell growth in the breast that forms a tumor. Starting from the milk ducts or lobules, cancer cells can spread to surrounding tissues of the body and form a lump or thickening. If left untreated, cancer can metastasize and become life-threatening. Breast self-examination (SADARI) is an effective method of early detection, but the rate of implementation is still low among women. Objective: This study aims to determine the relationship between knowledge, attitudes and peer support with SADARI behavior in public health study program students of FKM UNDANA class of 2023. Method: The research method used was quantitative with a cross-sectional approach. The sample consisted of 50 female students of FKM UNDANA class of 2023 who were determined by simple random sampling technique. Data were collected using a questionnaire in the form of a google form and analyzed using the chi-square test. Result: The results showed a significant relationship between knowledge (p=0.001), attitude (p=0.001), and peer support (p=0.000) with SADARI behavior. Most of the respondents had good knowledge (48%), positive attitude (70%), and good peer support (50%). Conclusion: FKM Undana students need to increase their knowledge and positive attitude towards SADARI, making it a monthly routine. They should support each other and create an environment that encourages the practice of early detection of breast cancer.

Automatic Watershed Segmentation of Cancerous Lesions in Unsupervised Breast Histology Images

Segmentation of nuclei in histology images is key in analyzing and quantifying morphology changes of nuclei features and tissue structures. Conventional diagnosis, segmenting, and detection methods have relied heavily on the manual-visual inspection of histology images. These methods are only effective on clearly visible cancerous lesions on histology images thus limited in their performance due to the complexity of tissue structures in histology images. Hence, early detection of breast cancer is key for treatment and profits from Computer-Aided-Diagnostic (CAD) systems introduced to efficiently and automatically segment and detect nuclei cells in pathology. This paper proposes, an automatic watershed segmentation method of cancerous lesions in unsupervised human breast histology images. Firstly, this approach pre-processes data through various augmentation methods to increase the size of dataset images, then a stain normalization technique is applied to these augmented images to isolate nuclei features from tissue structures. Secondly, data enhancement techniques namely; erosion, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted regions from the highlighted nuclei objects on the image. Consequently, the connected components method groups these highlighted pixel components with similar intensity values and, assigns them to their relevant labeled component binary mask. Once all binary masked groups have been determined, a deep-learning recurrent neural network from the Keras architecture uses this information to automatically segment nuclei objects with cancerous lesions and their edges on the image via watershed filling. This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 11,151 images. This proposed method produced a significant evaluation result of 98% F1-accuracy score.

HRCUNet: Hierarchical Region Contrastive Learning for Segmentation of Breast Tumors in DCE‐MRI

ABSTRACTSegmenting breast tumors from dynamic contrast‐enhanced magnetic resonance images is a critical step in the early detection and diagnosis of breast cancer. However, this task becomes significantly more challenging due to the diverse shapes and sizes of tumors, which make it difficult to establish a unified perception field for modeling them. Moreover, tumor regions are often subtle or imperceptible during early detection, exacerbating the issue of extreme class imbalance. This imbalance can lead to biased training and challenge accurately segmenting tumor regions from the predominant normal tissues. To address these issues, we propose a hierarchical region contrastive learning approach for breast tumor segmentation. Our approach introduces a novel hierarchical region contrastive learning loss function that addresses the class imbalance problem. This loss function encourages the model to create a clear separation between feature embeddings by maximizing the inter‐class margin and minimizing the intra‐class distance across different levels of the feature space. In addition, we design a novel Attention‐based 3D Multi‐scale Feature Fusion Residual Module to explore more granular multi‐scale representations to improve the feature learning ability of tumors. Extensive experiments on two breast DCE‐MRI datasets demonstrate that the proposed algorithm is more competitive against several state‐of‐the‐art approaches under different segmentation metrics.

A Machine Learning Approach to Early Detection and Malignancy Prediction in Breast Cancer

Breast cancer is the most common cancer among women, making early detection crucial for effective treatment. Traditional diagnostic methods often face limitations, leading to potential errors in diagnosis. This study explores the transformative potential of artificial intelligence (AI) and machine learning (ML) in breast cancer diagnosis, particularly through models like AdaBoost, SVM, Random Forest, and logistic regression. By analyzing key variables—such as age, tumor size, and menopausal status—this research aims to accurately differentiate between malignant and benign lesions. The findings reveal that the AdaBoost model significantly outperforms others, achieving an impressive AUC of 93.60% and a precision rate of 95.65%. This indicates its exceptional ability to accurately classify cases, minimizing false positives and ensuring reliable detection of true positives. With an F1 score of 86.27%, AdaBoost effectively balances precision and recall, positioning it as a valuable tool in clinical settings. Overall, this study underscores the importance of integrating AI-driven approaches in breast cancer diagnosis, enhancing accuracy and improving patient outcomes while reducing unnecessary invasive procedures. The promising results advocate for the adoption of these advanced techniques in healthcare, paving the way for more personalized and effective treatment strategies.

Breast cancer in women with previous gestational diabetes: a nationwide register-based cohort study

BackgroundGestational diabetes mellitus (GDM) is a common pregnancy complication characterized by insulin resistance. A link has been suggested between insulin resistance and breast cancer, which is the most common cancer in women. Hence, women with previous GDM may be at increased risk of developing breast cancer, yet, the existing evidence is conflicting. This study explored the association between GDM and incident breast cancer, including age at cancer diagnosis. Additionally, we investigated the potential impact of severity of insulin resistance during pregnancy and of subsequent diabetes development on the breast cancer risk.MethodsWe conducted a nationwide, register-based cohort study including all women giving birth in Denmark from 1997 to 2018. We defined GDM and breast cancer based on ICD-10 codes. Premenopausal and postmenopausal breast cancer was pragmatically defined as age at outcome < 50 years and ≥ 50 years, respectively. A proxy for severity of insulin resistance during pregnancy was based on insulin treatment; subsequent diabetes was defined as presence of ICD-10 codes and/or antidiabetic medication after pregnancy. The statistical analyses included Cox regression, logistic regression and t-test.ResultsOf 708,121 women, 3.4% had GDM. The median follow-up period was 11.9 years (range 0-21.9). The overall breast cancer risk was comparable in women with and without previous GDM (adjusted hazard ratio 0.96 [95% CI 0.83–1.12]). Premenopausal and postmenopausal breast cancer risk also did not differ; however, women with previous GDM had a breast cancer diagnosis at younger age (42.6 vs. 43.5 years, p-value 0.01). All-cause mortality was similar regardless of GDM history. Severity of insulin resistance during pregnancy and subsequent diabetes did not affect breast cancer risk.ConclusionsThis large, population-based cohort study showed no higher risk of incident breast cancer in women with previous GDM compared to women without previous GDM after a median of almost 12 years of follow-up. This was evident irrespective of menopausal state. The breast cancer risk was not influenced by the severity of insulin resistance during pregnancy and by subsequent diabetes development. Regardless of GDM history, attention towards prevention, early detection and treatment of breast cancer should be prioritized.

Predicting the Early Detection of Breast Cancer Using Hybrid Machine Learning Systems and Thermographic Imaging

ABSTRACTBreast cancer is a leading cause of mortality among women, emphasizing the critical need for precise early detection and prognosis. However, conventional methods often struggle to differentiate precancerous lesions or tailor treatments effectively. Thermal imaging, capturing subtle temperature variations, presents a promising avenue for non‐invasive cancer detection. While some studies explore thermography for breast cancer detection, integrating it with advanced machine learning for early diagnosis and personalized prediction remains relatively unexplored. This study proposes a novel hybrid machine learning system (HMLS) incorporating deep autoencoder techniques for automated early detection and prognostic stratification of breast cancer patients. By exploiting the temporal dynamics of thermographic data, this approach offers a more comprehensive analysis than static single‐frame approaches. Data processing involves splitting the dataset for training and testing. A predominant infrared image was selected, and matrix factorization was applied to capture temperature changes over time. Integration of convex factor analysis and bell‐curve membership function embedding for dimensionality reduction and feature extraction. The autoencoder deep neural network further reduces dimensionality. HMLS model development included feature selection and optimization of survival prediction algorithms through cross‐validation. Model performance was assessed using accuracy and F‐measure metrics. HMLS, integrating clinical data, achieved 81.6% accuracy, surpassing 77.6% using only convex‐NMF. The best classifier attained 83.2% accuracy on test data. This study demonstrates the effectiveness of thermographic imaging and HMLS for accurate early detection and personalized prediction of breast cancer. The proposed framework holds promise for enhancing patient care and potentially reducing mortality rates.

Discovery of Plasma Lipids as Potential Biomarkers Distinguishing Breast Cancer Patients from Healthy Controls.

The development of a sensitive and specific blood test for the early detection of breast cancer is crucial to improve screening and patient outcomes. Existing methods, such as mammography, have limitations, necessitating the exploration of alternative approaches, including circulating factors. Using 598 prospectively collected blood samples, a multivariate plasma-derived lipid biomarker signature was developed that can distinguish healthy control individuals from those with breast cancer. Liquid chromatography with high-resolution and tandem mass spectrometry (LC-MS/MS) was employed to identify lipids for both extracellular vesicle-derived and plasma-derived signatures. For each dataset, we identified a signature of 20 lipids using a robust, statistically rigorous feature selection algorithm based on random forest feature importance applied to cross-validated training samples. Using an ensemble of machine learning models, the plasma 20-lipid signature generated an area under the curve (AUC) of 0.95, sensitivity of 0.91, and specificity of 0.79. The results from this study indicate that lipids extracted from plasma can be used as target analytes in the development of assays to detect the presence of early-stage breast cancer.

Referral and disease patterns of patients treated at the Nicosia General Hospital Breast Centre

Abstract Background Cyprus has one of the lowest mortality rates from breast cancer in Europe. The reasons behind this have not been investigated but it is speculated that the ease of access to Breast Centers in combination with an increased public awareness play a role. The aim of this study was to investigate referral and disease presentation patterns of patients treated at the Nicosia General Hospital (NGH) Breast Centre and define opportunities for effective public health interventions. Methods A retrospective study of all patients (585) with in situ or invasive breast cancer treated at the NGH Breast Centre between February 2017 and November 2023 was conducted. Data on referral sources, symptoms, and cancer stage at the time of diagnosis were analyzed using Stata 18. Results Most patients were referrals from the national population screening program (42.2%), followed by self-referrals (40.6%), and General Practitioner (GP)/or other specialist referrals (17.2%). Half of the patients (50.3%) were asymptomatic at diagnosis. In addition, 8% of the patients diagnosed with invasive breast cancer were Stage I, 65% Stage II, and 27% Stage III. Conclusions Our study provides important insights forming the basis of public health activities for the early detection of breast cancer based on the fact that 20% of newly diagnosed breast cancer cases in Cyprus receive treatment in NGH Breast Center. Although adherence to the national population screening program does not meet desired expectations, a significant proportion of breast cancers were detected via this program highlighting its effectiveness in early detection of asymptomatic cancers. A large proportion of patients were self-referred underlining the high degree of breast cancer awareness in Cyprus but also the media-induced anxiety which leads to early investigations. Key messages • Screening program and breast cancer awareness campaigns are effective in detecting breast cancers early. • These activities should be sustained to further reduce breast cancer mortality rate.

Key LncRNAs Associated with Distant Metastasis in Breast Cancer: A System Biology Analysis.

Breast cancer (BC) is the most prevalent cancer among women globally. Metastasis is the leading cause of mortality in most cancers. Early BC detection before metastasis can enhance survival rates. Understanding BC metastasis mechanisms could aid in developing metastasis-specific treatments. The role of long non-coding RNAs (lncRNA) in cancer progression is recognized, yet the importance of specific lncRNAs in BC, despite potential alterations, remains inadequately explored. We utilized bioinformatics tools to identify novel lncRNAs dysregulated in metastasis. To achieve this objective, the gene expression profile of GSE102484, encompassing metastatic and non-metastatic BC tissue samples, was analyzed using the limma package in R with cut-off criteria set at an adjusted p-value < 0.005 and |fold change (FC)| ≥ 0.5. We used WGCNA analysis to find co-expression genes for lncRNAs. Then, we identified hub genes and performed pathway enrichment to better understand the results. Considering the defined criteria, eight novels of dysregulated lncRNAs and top 10 miRNAs were identified. Dysregulated lncRNAs are found in yellow, green, brown, purple, and turquoise co-expression modules from WGCNA analysis. Enrichment analysis of these co-expressed modules revealed relevant pathways to metastasis, such as epithelial-to-mesenchymal transition and integrin cell-surface interactions, as well as regulation of HIF1-alpha. In addition, SDPR, TGFB1I1, ILF3, KIF4A, and COL5A1 were identified as hub genes. Based on DElncRNA-miRNADEmRNA connections and co-expression, we ultimately constructed lncRNA-associated ceRNA axes. The current study may identify novel lncRNAs implicated in BC metastasis; still, additional research is required to determine the potential functions of these lncRNAs in BC metastasis.

Proportion of Breast Self Examination Practice and its Associated Factors among Female Health Professionals in Government Medical College Hospital , Thiruvananthapuram.

Breast cancer is a leading cause of death among females across the globe. Breast self- examination is considered as a cornerstone testing method for breast cancer screening and early detection. Breast Self Examination is one of the simple, quick and cost free procedures for early detection of breast cancer among women. The Present study was intended to estimate the proportion of Breasts self examination practice and its associated factors among female health professionals in Government Medical College Hospital, Thiruvananthapuram. The research design adopted for this study was descriptive cross sectional design. The sample consists of 330 female health professionals. Sample fulfilling the eligibility criteria were selected through simple random sampling method and data were collected by giving questionnaire. The collected data was analyzed by using SPSS version 23 and the results were expressed in descriptive and inferential statistics. The collected data showed that about 68% of the participants were doing breast self examination practice and there was a significant association between breast self examination practice and associated factors such as age, basic qualification, highest qualification, profession, years of experience, screening for breast cancer and knowledge and attitude regarding breast self examination practice.The study concluded that adressing all these factors can improve breast self examination practice among female health professionals.

Automated Breast Ultrasound With Remote Reading for Primary Breast Cancer Screening: A Prospective Study Involving 46 Community Health Centers in China.

Background: China has faced barriers to implementation of a population-based mammographic screening program. Breast ultrasound provides an alternative screening modality to mammography in low-resource settings. Objective: To evaluate the performance of ABUS with remote reading as the primary screening modality for breast cancer. Methods: This prospective study enrolled asymptomatic women 35-69 years old from 46 community health centers across 18 provinces representing all six regions of China from January 2021 to December 2021. Participants underwent screening ABUS as the sole breast cancer screening modality, with images acquired by a technologist at the community health center. The 3D volumetric data were transferred via cloud-based software to a single remote reading center, where examinations were interpreted independently in batches by two subspecialized breast radiologists using BI-RADS; a third radiologist at the remote reader center resolved discrepancies. Diagnostic reports were returned to the community centers, and patients sought follow-up care at local hospitals. The reference standard incorporated a combination of histopathology and 24-month follow-up. Outcomes measures included cancer detection rate, abnormal interpretation rate (AIR), sensitivity, specificity, biopsy rate, and PPV. Results: The final analysis included 5978 enrolled participants (median age, 46 years [IQR 40-52 years]) who underwent screening ABUS at the community health centers with subsequent remote reading. A total of 24 ABUS-detected cancers and two interval cancers were diagnosed. The cancer detection rate was 4.0 per 1000 women (95% CI: 2.7-5.9), and the AIR was 11.9% (95% CI: 11.1-12.7). A total of 95.8% (23/24) of ABUS-detected cancers were invasive. The 23 invasive cancers had a median diameter of 10.0 mm; 73.9% (17/23) were node-negative. Sensitivity was 92.3% (95% CI: 75.9-97.9), and specificity was 88.4% (95% CI: 87.6-89.2). The biopsy rate was 1.7% (95% CI: 1.4-2.0), and the PPV of biopsy was 24.0% (95% CI: 16.7-33.2). Conclusion: ABUS screening with remote reading met benchmark performance for cancer detection in comparison to mammography, with infrequent interval cancers. Clinical Impact: ABUS with remote reading holds promise in enhancing access to breast cancer screening and early detection in low-resource settings or underserved regions where mammographic screening is not established.

Breast Cancer Detection System Using Machine Learning

AI is transforming the medical field, especially in early detection and categorization of breast cancer. Deep learning models like CNNI-BCC are displaying impressive capabilities in examining MRI images to precisely recognize different types of breast cancer. This advancement in technology has significant implications for enhancing patient outcomes. By utilizing AI, healthcare professionals can now receive more accurate and prompt diagnoses. CNNI- BCC's exceptional accuracy in analyzing MRI images allows for earlier detection of breast cancer, which is crucial for successful treatment. This technology enables doctors to identify potential abnormalities that may have been missed by traditional methods, leading to more effective interventions.

How social class shapes breast cancer risk perspectives and prevention practices of Australian midlife women: a qualitative study using the concept of ‘breast cancer candidacy’

BackgroundThe increasing incidence of breast cancer and disease burden is a significant public health concern. While 30% of breast cancers could be prevented through addressing modifiable risk factors, misconceptions among women about breast cancer risks hamper primary prevention. In the absence of primary prevention, secondary prevention such as mammography increases the early detection of breast cancer and improves health outcomes. However, current population-level screening rates indicate secondary prevention is suboptimal. More effective public health efforts to improve breast cancer prevention are required. Given breast cancer is socially patterned, this work explores how social class impacts women’s breast cancer prevention practices. This study uses the concepts of lay epidemiology and candidacy as a mechanism to understand women’s breast cancer risk perspectives. It engages Bourdieu’s relational social class theory to unpack how women’s social, cultural, and structured life contexts shape these perspectives and their considerations regarding primary and secondary prevention.MethodsIn this qualitative study 43 Australian midlife women (aged 45–64 years), were interviewed to explore their understandings of breast cancer risks, how they perceived their own risk, and how this shaped their prevention behaviours. A theory-informed thematic analysis applying Bourdieu’s concepts of habitus, capital, and fields to understand how women’s social class positions shapes risk perspectives and prevention practices was conducted.ResultsThis social class analysis showed differences in how women engage in breast cancer discourse, consider risks, and participate in breast cancer prevention. Middle-class women prioritise health promoting practices and were more likely than working-class and affluent women to attend mammography screening. Working-class women experience structural factors, like low income, stress and difficult life circumstances, which hamper primary prevention practices and for some screening is not considered or prioritised, and their decisions not to screen are less active. Affluent women often do not consider themselves at-risk due to their healthier ‘lifestyles. ’They suggest that this, and their knowledge of screening benefits and harms allows them to make informed decisions not to screen.ConclusionsWomen interpret and understand breast cancer risks differently and enact prevention practices within the parameters afforded by their social class positions. These findings are useful to inform improved public health approaches regarding both modifiable breast cancer risks and increasing mammography screening. To improve equity in breast cancer prevention efforts, such approaches must respond to limitations based on social class and address structural factors that impact prevention practices.

Integrating IoT and Machine Learning for Advanced Breast Cancer Detection: A Secure Framework for Enhanced Diagnostic Accuracy

Background: Breast cancer continues to be a major global health issue, with outmoded analytic methods often limited in their capacity for early detection. The emergence of telehealth care emphasizes the need for advanced, advanced diagnostic explanations. Objective: This study explores the possibility of integrating advanced technologies, such as thermal imaging cameras, with sophisticated ML algorithms, particularly CNNs, to enhance breast cancer discovery beyond the capabilities of conventional risk models. Method: We propose a pioneering predictive healthcare system that harnesses the IoT and EHRs for real-time, automated breast cancer detection. This system is designed to operate in various healthcare environments, including hospitals, nursing homes, and schools. Beyond early breast cancer detection, it seeks to identify other health issues using the shared rule of DL and IoT techniques. To maintain data integrity and protect patient confidentiality, the system implements strong security protocols, including encrypted data transmission, secure access controls, and adherence to healthcare data protection regulations. Results: The study explores the methodologies and technological frameworks necessary for developing this comprehensive cancer detection system. Emphasis is placed on secure data management practices and the implementation of security protocols to safeguard sensitive health information. Main Findings: This research assesses whether the proposed system can effectively address global challenges related to breast cancer detection and contribute to enhanced patient outcomes. The integration of advanced security features aims to defend patient data and certify the system's reliability and trustworthiness in diverse healthcare settings. Conclusion: This investigate evaluates capabilities of new health care system that combines smart technologies with ML methods to identify breast cancer and possibly other health problems at an early stage. Future investigate should focus on assessing the system’s practical feasibility and effectiveness in real-world scenarios, as well as its ability to uphold stringent security standards. This emphasizes its efficiency when operating on a lightweight and portable processor. Our experimental results indicate that our system achieves a 96.32% accuracy on the BreakHis database and can operate on a Raspberry Pi device with minimal resources.

A New Computer-Aided Diagnosis System for Breast Cancer Detection from Thermograms Using Metaheuristic Algorithms and Explainable AI

Advances in the early detection of breast cancer and treatment improvements have significantly increased survival rates. Traditional screening methods, including mammography, MRI, ultrasound, and biopsies, while effective, often come with high costs and risks. Recently, thermal imaging has gained attention due to its minimal risks compared to mammography, although it is not widely adopted as a primary detection tool since it depends on identifying skin temperature changes and lesions. The advent of machine learning (ML) and deep learning (DL) has enhanced the effectiveness of breast cancer detection and diagnosis using this technology. In this study, a novel interpretable computer aided diagnosis (CAD) system for breast cancer detection is proposed, leveraging Explainable Artificial Intelligence (XAI) throughout its various phases. To achieve these goals, we proposed a new multi-objective optimization approach named the Hybrid Particle Swarm Optimization algorithm (HPSO) and Hybrid Spider Monkey Optimization algorithm (HSMO). These algorithms simultaneously combined the continuous and binary representations of PSO and SMO to effectively manage trade-offs between accuracy, feature selection, and hyperparameter tuning. We evaluated several CAD models and investigated the impact of handcrafted methods such as Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gabor Filters, and Edge Detection. We further shed light on the effect of feature selection and optimization on feature attribution and model decision-making processes using the SHapley Additive exPlanations (SHAP) framework, with a particular emphasis on cancer classification using the DMR-IR dataset. The results of our experiments demonstrate in all trials that the performance of the model is improved. With HSMO, our models achieved an accuracy of 98.27% and F1-score of 98.15% while selecting only 25.78% of the HOG features. This approach not only boosts the performance of CAD models but also ensures comprehensive interpretability. This method emerges as a promising and transparent tool for early breast cancer diagnosis.

Abbreviated Breast MRI as a Supplement to Mammography in Family Risk History of Breast Cancer within the Croatian National Breast Screening Program.

To evaluate the diagnostic performance of abbreviated breast MRI compared with mammography in women with a family history of breast cancer included in the Croatian National Breast Screening Program. 178 women with a family history of breast cancer aged 50 to 69 underwent abbreviated breast MRI and mammography. Radiological findings for each method were categorized according to the BI-RADS classification. The gold standard for assessing the diagnostic accuracy of breast MRI and mammography, in terms of suspicious BI-RADS 4 and BI-RADS 5 findings, was the histopathological diagnosis. Performance measures, including cancer detection rates, specificity, sensitivity, and positive and negative predictive values, were calculated for both imaging methods. Twelve new cases of breast cancer were detected, with seven (58.3%) identified only by abbreviated breast MRI, four (33.3%) detected by both mammography and breast MRI, and one (8.3%) diagnosed only by mammography. Diagnostic accuracy parameters for abbreviated breast MRI were 91.67% sensitivity, 94.58% specificity, 55.0% positive predictive value (PPV), and 99.37% negative predictive value (NPV), while for mammography, the corresponding values were 41.67%, 96.39%, 45.46%, and 95.81%, respectively. Abbreviated breast MRI is a useful supplement to screening mammography in women with a family history of breast cancer. Considering the results of the conducted research, it is recommended to assess whether women with a family history of breast cancer have an increased risk and subsequently provide annual abbreviated breast MRI in addition to mammography for early detection of breast cancer.

Classifying Digital Medical Images for Breast Cancer Prediction Using Machine Learning

Statistics show that among the 1.67 million cancer reported cases worldwide, breast cancer is the most common cancer among women and constitutes the largest burden of the disease in developing countries. However, if detected early enough, it can be managed. Mammography is one of the best ways to identify and diagnose breast abnormalities among various medical imaging modalities. It typically detects signs and symptoms of breast cancer, including microcalcifications, lumps, nodules, architectural abnormalities, asymmetry, bilateral asymmetry, etc. These features can be benign or cancerous when they appear in the breast. Researchers have focused on creating fully automated computer-aided design methods to help radiologists combat this type of cancer. Artificial Intelligence( AI) -based algorithms have been essential in creating systems that allow for automated diagnosis, rapid response, and low mortality. In this work, several machine learning methods were compared—such as logistic regression, naive Bayesian Gaussian algorithms, support vector machines (SVM), linear support vector machines (SVM), and artificial neural networks (ANN). Processing time and accuracy were the main evaluation metrics where naive Bayes outperformed SVM, followed by linear SVM and logistic regression, with ANNs failing in accuracy. These results highlight how naive Bayes algorithms can help in early detection of breast cancer, leading to faster and more efficient treatments and ultimately better patient care.