Method For Detection Of Cancer Research Articles

Deep learning for enhancing cancer identification and diagnosis

One of the promising and significant fields of technology is the use of automated computer techniques, particularly machine learning, to facilitate and enhance medical analysis and diagnosis. In the area of artificial intelligence (AI), deep learning techniques using artificial neural networks (CNNs) so-called because they superficially resemble biological neural networks - are computational network models for discovering large, high-dimensional data sets (such as medical datasets) for complex structures and patterns. In this paper, the focus is on summarizing contemporary applications of various deep learning algorithms in the direction of cancer identification and diagnosis, and on re-implementing supervised learning for cancer detection after a new database based on the lung cancer detection project from the book Deep Learning with PyTorch. The automatic detection of lung malignancies from patient CT scans was re-implemented by deep learning. In this paper, the technique is applied to data provided by the Iraqi Oncology Teaching Hospital. The author demonstrates that the application of the new data will also maintain the accuracy of the identification, and thus promises to develop into a more comprehensive and general cancer detection and diagnosis method in the future as the algorithm and technology are further refined.

Development of New Diagnostic Methods for Early Detection of Cancer: Integration of Genomic and Bioinformatics Technologies

The relentless pursuit of improved cancer diagnostics has led to the development of novel methods for early detection. This article explores the integration of genomic and bioinformatics technologies to propel advancements in cancer diagnostics. With the increasing understanding of cancer as a molecular disease, genomic technologies play a pivotal role in unraveling the intricate genetic alterations associated with various cancer types. The utilization of next-generation sequencing (NGS) allows for comprehensive genomic profiling, enabling the identification of specific genetic mutations, alterations, and aberrations indicative of early-stage cancer.
 Bioinformatics, as a complementary field, becomes crucial in managing and interpreting the vast datasets generated by genomic technologies. Advanced computational algorithms and machine learning models are employed to analyze genomic data, identify biomarkers, and discern subtle patterns that may serve as early indicators of cancer. The integration of these technologies offers a holistic approach, combining the power of genomics with sophisticated computational analyses to enhance the sensitivity and specificity of cancer diagnostics.
 Moreover, the article explores the potential of liquid biopsy as a non-invasive method for early cancer detection. By analyzing circulating tumor DNA (ctDNA) and other biomolecules in bodily fluids, liquid biopsy provides a minimally invasive means to monitor molecular changes associated with cancer progression. The integration of liquid biopsy with genomic and bioinformatics technologies further amplifies the scope of early cancer detection, offering a real-time, dynamic assessment of the evolving cancer landscape.
 In conclusion, the amalgamation of genomic and bioinformatics technologies represents a paradigm shift in cancer diagnostics, facilitating the identification of molecular alterations at an unprecedented level of detail. This integrated approach holds great promise for the early detection of cancer, paving the way for more effective and personalized therapeutic interventions. The article underscores the transformative potential of these technologies in reshaping the landscape of cancer diagnosis and emphasizes the need for ongoing research and technological innovation in the relentless pursuit of improved cancer care.

Comparative performance analysis of binary variants of FOX optimization algorithm with half-quadratic ensemble ranking method for thyroid cancer detection

Thyroid cancer is a life-threatening condition that arises from the cells of the thyroid gland located in the neck’s frontal region just below the adam’s apple. While it is not as prevalent as other types of cancer, it ranks prominently among the commonly observed cancers affecting the endocrine system. Machine learning has emerged as a valuable medical diagnostics tool specifically for detecting thyroid abnormalities. Feature selection is of vital importance in the field of machine learning as it serves to decrease the data dimensionality and concentrate on the most pertinent features. This process improves model performance, reduces training time, and enhances interpretability. This study examined binary variants of FOX-optimization algorithms for feature selection. The study employed eight transfer functions (S and V shape) to convert the FOX-optimization algorithms into their binary versions. The vision transformer-based pre-trained models (DeiT and Swin Transformer) are used for feature extraction. The extracted features are transformed using locally linear embedding, and binary FOX-optimization algorithms are applied for feature selection in conjunction with the Naïve Bayes classifier. The study utilized two datasets (ultrasound and histopathological) related to thyroid cancer images. The benchmarking is performed using the half-quadratic theory-based ensemble ranking technique. Two TOPSIS-based methods (H-TOPSIS and A-TOPSIS) are employed for initial model ranking, followed by an ensemble technique for final ranking. The problem is treated as multi-objective optimization task with accuracy, F2-score, AUC-ROC and feature space size as optimization goals. The binary FOX-optimization algorithm based on the V_1 transfer function achieved superior performance compared to other variants using both datasets as well as feature extraction techniques. The proposed framework comprised a Swin transformer to extract features, a Fox optimization algorithm with a V1 transfer function for feature selection, and a Naïve Bayes classifier and obtained the best performance for both datasets. The best model achieved an accuracy of 94.75%, an AUC-ROC value of 0.9848, an F2-Score of 0.9365, an inference time of 0.0353 seconds, and selected 5 features for the ultrasound dataset. For the histopathological dataset, the diagnosis model achieved an overall accuracy of 89.71%, an AUC-ROC score of 0.9329, an F2-Score of 0.8760, an inference time of 0.05141 seconds, and selected 12 features. The proposed model achieved results comparable to existing research with small features space.

Method of primary breast cancer detection and the disease-free interval, adjusting for lead time.

Little is known about the impact of screen-detected breast cancer compared with clinically detected breast cancer on the disease-free interval (ie, free from locoregional recurrences, distant metastasis, contralateral breast cancer). Moreover, it is thought that most studies overestimate the beneficial effect of screening, as they do not adjust for lead time. We investigated the association between method of breast cancer detection and disease-free interval, taking lead time into account. Women aged 50-76 years, diagnosed with breast cancer between 2005 and 2008 were selected from the Netherlands Cancer Registry. Women diagnosed in 2005 were divided into screen-detected and clinically detected cancer and had a follow-up of 10 years (2005 cohort). Women diagnosed in 2006-2008 were divided into screen-detected, interval, and nonscreen-related cancer and had a follow-up of 5 years (2006-2008 cohort). A previously published method was used to adjust for lead time. Analyses were repeated correcting for confounding variables instead of lead time. The 2005 cohort included 6215 women. Women with screen-detected cancer had an improved disease-free interval compared with women with clinically detected cancer (hazard ratio [HR] = 0.77, 95% confidence interval [CI] = 0.68 to 0.87). The 2006-2008 cohort included 15 176 women. Women with screen-detected or interval cancer had an improved disease-free interval compared with women with nonscreen-related cancer (HR = 0.76, 95% CI = 0.66 to 0.88; HR = 0.88, 95% CI = 0.78 to 0.99, respectively). Correcting for confounders instead of lead time did not change associations. Women with screen-detected cancer had an improved disease-free interval compared with women with a nonscreen-related or clinically detected cancer, after correction for lead time.

A powerful deep learning method for skin cancer detection

<p>The authors discussed the issues posed by our study’s inability to accurately diagnose skin cancer and distinguish between various skin growths, especially without the aid of cutting-edge medical technology and highly skilled diagnosticians. To that purpose, the authors have developed a deep learning (DL) method that can recognise skin cancer from images. This study investigates the use of a convolutional neural network (CNN) and the Keras Sequential-application programming interface (API) to detect cancer in seven different types of chronic lesions. The researchers used the HAM10000 dataset, which is openly available. 10,015 skin growth images with annotations are included in this dataset. The authors used several data pre-processing techniques after reading the data but before training our model. The authors provide pre-trained data for comparison and reliability assessments. Examples of transfer learning models that are used for comparison include ResNet50, DenseNet121, and VGG11. In the area of skin growth classification for skin cancer diagnosis, this helps in the identification of improved DL application procedures. Over 97.12% of the time, our suggested model accurately predicts the sort of skin that will develop.</p>

A Review on Computational Methods for Breast Cancer Detection in Ultrasound Images Using Multi-Image Modalities

A Review on Computational Methods for Breast Cancer Detection in Ultrasound Images Using Multi-Image Modalities

Detection of Brain Cancer through Enhanced Particle Swarm Optimization in Artificial Intelligence Approach

Brain cancer is deadly and requires prompt detection and treatment. We propose a complete brain cancer detection method using binary encoding, adaptive thresholding, edge-based segmentation, particle swarm optimization (PSO), wavelet transform, and neural networks. First, binary encoding converts categorical patient data and medical history information into binary vectors for fast analysis. Adaptive thresholding then handles image lighting and contrast to optimize brain image segmentation. Brain tumor boundaries are identified via edge-based segmentation. This method isolates tumor areas for investigation by recognizing significant pixel intensities. Particle swarm optimization optimizes segmentation algorithm settings, enhancing efficiency and accuracy. Wavelet transform captures local and global brain picture changes, extracting tumor-related information. This method gives a complete visual representation, improving categorization. Finally, utilizing the collected attributes, a neural network model classifies brain pictures as malignant or non-cancerous. The neural network learns the complicated correlations between retrieved variables and brain cancer to classify accurately and automatically. A dataset of brain pictures, comprising malignant and non-cancerous instances, evaluates the proposed approach. The proposed approach accurately detects brain tumors in experiments. Binary encoding, adaptive thresholding, edge-based segmentation, particle swarm optimization, wavelet transform, and neural networks can help medical professionals diagnose and treat brain cancer early.

Esophageal cancer detection framework based on time series information from smear images

The gold standard for esophageal cancer diagnosis and treatment is the Thinprep Cytologic Test (TCT) of suspected sections. TCT refers to analyze the features of the lesion areas using tissue regions stained with hematoxylin and eosin. However, pathologists are currently subjected to high workloads and limited experiences. Moreover, automatic esophageal cancer detection methods typically screen the smears by focusing on suspicious lesions identified by cytotechnicians, cell misclassification often results in inaccurate and weak robust diagnoses, smear utilization rate is also reduced. Computer-assisted diagnosis also faces challenges such as information loss, non-quantitative analysis, and nonstandard diagnosing processes. To address these issues, this article proposes a deep learning based detection framework called the Esophageal Time Series Thinprep Cytologic Test (ETS-TCT) to provide a quantitative and robust screening of Whole Slide Imaging (WSI) for esophageal cancer. Our system is divided into three modules: Coarse–fine detection model, quantitative analysis model, and Fusion Long Short Term Memory-Support Vector Machine (FLSTM-SVM) model. These modules are organized to map the pathological information from cell-level to smear-level and offer interpretable predictions to pathologists. For each smear, we design the coarse–fine segmentation model for adaptively locating and classifying target cells, give mathematical descriptions for cell Deoxyribonucleic Acid (DNA) values using the quantitative analysis model, establish an early risk screening model for esophageal cancer using the optimized FLSTM-SVM network. To validate the methodology, we use two clinical datasets containing 580 samples, achieving the accuracy, sensitivity, specificity, and area under ROC (AUC) of 92.0%, 93.4%, 94.4%, and 0.913, respectively. In short, the framework provides robust and accurate diagnosis of esophageal cancer WSIs using the time series features. This screening can assist the pathologists in strengthening the diagnosis by robustly presenting the quantitative intermediate results as well as visual interpretations. Moreover, we clearly present and expatiate the concepts of time series features, highlighting the relationship between these features to physiological states of patients. Our results indicate the possibility of using the framework as a second system to the computer-assisted esophageal cancer screening.

Quantum Dot Nanomaterials: Preparation, Characterization, Advanced Bio-Imaging and Therapeutic Applications.

The bio-imaging technology is one of the most significant modern applications used in several fields, including early diagnosis of many illnesses that are most important diseases facing humanity and other vital uses. The primary advancement in nanotechnology is the creation of innovative fluorescence probes called quantum dots (QDs). The use of molecular tagging in research, in vivo, and in vitro studies is revolutionized by quantum dots. The application of QD indicates conversion in natural imaging and photography has demonstrated extraordinary appropriateness in bio-imaging, the discovery of novel drugs, and delivery of targeted genes, biosensing, photodynamic therapy, and diagnosis. New potential methods of early cancer detection and treatment management are being researched as a result of the special physical and chemical characteristics of QD probes. The bio-imaging technique depends on the fluorescent emission of the used materials, which is paired with living cells that are easy to see it in 3D without any surgical intervention. Therefore, the use of QDs many types that have unique and appropriate properties for use in that application; In terms of fluorescent emission strength, duration and luminosity.This review article displays some methods of preparation for QDs nanomaterials and the devices used in this. In addition, it presentssome of challenges that must be avoided for the possibility of using them in the bio-imaging field; as toxicity, bio-compatibility, and hydrophilization. It's reviewed some of the devices that use QDs in bio-imaging technique, the QDs application in cell analysis-imaging, and QDs application in vivo imaging.

Classification techniques using gray level co-occurrence matrix features for the detection of lung cancer using computed tomography imaging

<span lang="EN-US">Lung cancer, which causes the majority of fatalities worldwide each year, is one of the deadliest diseases. The survival rate of cancer patients could be improved with better cancer detection methods. Image processing and machine learning have both been used to aid in lung cancer detection, but a method that both increase accuracy and increases a patient’s survival rate has yet to be identified. In an effort to find the most effective method for the accurate lung cancer recognition, this paper analyses and compares several classification algorithms. Lung computed tomography (CT) images are enhanced by removing noise using a median filter. For filtered image, threshold segmentation is used to segment it into distinct parts. From the segmented image different features are extracted using the grey level co-occurrence matrix (GLCM). several classification strategies, including support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), and decision tree (DT) methods, are used to classify lung images as malignant or normal based on the extracted features. Methods are evaluated based on a number of various performance measures, like accuracy, a precision, the recall, and the F1-Score. Based on the experimental outcomes, SVM outperforms other classification methods in accurately detecting lung cancer with an accuracy of 99.32%.</span>

Detection of CYFRA 21-1 in human serum by an electrochemical immunosensor based on UiO-66-NH2@CMWCNTs and CS@AuNPs.

In this study, an electrochemical immunosensor was constructed to detect the cytokeratin 19 fragment antigen 21-1 (CYFRA 21-1) in human serum. CYFRA 21-1 is the most sensitive tumor marker of non-small cell lung cancer (NSCLC), its content in normal human serum should be less than 3.3ng/mL. When lung cancer cells dissolve or die, a myriad of CYFRA 21-1 is released into a tumor patient's blood circulation, and its serum content elevates strikingly. Consequently, detecting CYFRA 21-1 by an electrochemical biosensor is expected to provide a new method for the early detection and prevention of lung cancer. In this study, a composite of UiO-66-NH2 and carboxylated multi-walled carbon nanotubes (CMWCNTs) was used as the substrate material of a sensor; the resulting sensor had a large specific surface area and strong electrical conductivity. Moreover, gold nanoparticles (AuNPs) were used to bind to antibodies through an Au-S bonds. Also, a supersensitive detection of CYFRA 21-1 was achieved through the specific bindings of antigens and antibodies. Under optimal detection conditions, the change of current signal intensity of the immunosensor was proportional to the logarithm of CYFRA 21-1 concentration and had a linear relation in the range of 0.005-400ng/mL, while the detection limit was 1.15pg/mL (S/N=3). The proposed immunosensor had high precision, stability, and selectivity. More importantly, the sensor was been successfully applied to detect CYFRA 21-1 in human serum with high recovery, providing a new method for early screening and dynamic monitoring of lung cancer.

Review on Computer Aided Breast Cancer Detection and Diagnosis using Machine Learning Methods on Mammogram Image.

Machine Learning (ML) plays an essential part in the research area of medical image processing. The advantages of ML techniques lead to more intelligent, accurate, and automatic computeraided detection (CAD) systems with improved learning capability. In recent years, deep learning-based ML approaches developed to improve the diagnostic capabilities of CAD systems. This study reviews image enhancement, ML and DL methods for breast cancer detection and diagnosis using mammogram images and provides an overview of these methods. The analysis of different ways of ML and DL shows that the usages of traditional ML approaches are limited. However, DL techniques have an excellent future for implementing medical image analysis and improving the ability to exist CAD systems. Despite the significant advancements in deep learning methods for analyzing medical images to detect breast cancer, challenges still exist regarding data quality, computational cost, and prediction accuracy.

Breast Cancer Segmentation from Ultrasound Images Using ResNext-based U-Net Model

Breast cancer is a type of cancer caused by the uncontrolled growth and proliferation of cells in the breast tissue. Differentiating between benign and malignant tumors is critical in the detection and treatment of breast cancer. Traditional methods of cancer detection by manual analysis of radiological images are time-consuming and error-prone due to human factors. Modern approaches based on image classifier deep learning models provide significant results in disease detection, but are not suitable for clinical use due to their black-box structure. This paper presents a semantic segmentation method for breast cancer detection from ultrasound images. First, an ultrasound image of any resolution is divided into 256×256 pixel patches by passing it through an image cropping function. These patches are sequentially numbered and given as input to the model. Features are extracted from the 256×256 pixel patches with pre-trained ResNext models placed in the encoder network of the U-Net model. These features are processed in the default decoder network of the U-Net model and estimated at the output with three different pixel values: benign tumor areas (1), malignant tumor areas (2) and background areas (0). The prediction masks obtained at the output of the decoder network are combined sequentially to obtain the final prediction mask. The proposed method is validated on a publicly available dataset of 780 ultrasound images of female patients. The ResNext-based U-Net model achieved 73.17% intersection over union (IoU) and 83.42% dice coefficient (DC) on the test images. ResNext-based U-Net models perform better than the default U-Net model. Experts could use the proposed pixel-based segmentation method for breast cancer diagnosis and monitoring.

An Update on Potential Molecular Biomarkers of Dietary Phytochemicals Targeting Lung Cancer Interception and Prevention.

Since ancient times, dietary phytochemicals are known for their medicinal properties. They are broadly classified into polyphenols, terpenoids, alkaloids, phytosterols, and organosulfur compounds. Currently, there is considerable interest in their potential health effects against various diseases, including lung cancer. Lung cancer is the leading cause of cancer deaths with an average of five-year survival rate of lung cancer patients limited to just 14%. Identifying potential early molecular biomarkers of pre-malignant lung cancer cells may provide a strong basis to develop early cancer detection and interception methods. In this review, we will discuss molecular changes, including genetic alterations, inflammation, signal transduction pathways, redox imbalance, epigenetic and proteomic signatures associated with initiation and progression of lung carcinoma. We will also highlight molecular targets of phytochemicals during lung cancer development. These targets mainly consist of cellular signaling pathways, epigenetic regulators and metabolic reprogramming. With growing interest in natural products research, translation of these compounds into new cancer prevention approaches to medical care will be urgently needed. In this context, we will also discuss the overall pharmacokinetic challenges of phytochemicals in translating to humans. Lastly, we will discuss clinical trials of phytochemicals in lung cancer patients.

Beyond liver cancer, more application scenarios for alpha-fetoprotein in clinical practice.

Alpha-fetoprotein (AFP) is a commonly used clinical biomarker. Before 1970, the two-way agar diffusion method was mainly used, and the specificity of AFP in the diagnosis of primary liver cancer was satisfactory. However, its positivity rate was not very high. The diagnostic value of AFP is changing with the evolution of detection methods. Here, we performed a literature search to identify English-language publications. The search was performed from January 2015 to April 2023 using the PubMed database and the following terms in [Titles/Abstracts]: alpha-fetoprotein, clinical practice, detection, etc. The references of retrieved articles were also screened to broaden the search. Studies referring to liver cancer and AFP detection methods were excluded. In this review, several clinical application scenarios for AFP were systematically reviewed, and its potential detection value in the future was discussed.

Optimizing Drug Delivery Systems for Enhanced Therapeutic Efficacy in Cancer Treatment: A Multidisciplinary Approach

This research aims to develop an early detection method for breast cancer through the analysis of specific biomarkers. The method leverages advanced drug delivery technology to enhance the efficacy of cancer therapy. Employing a multidisciplinary approach, this study integrates medical and pharmaceutical sciences to achieve optimal results. Specific biomarkers utilized in this research will be identified to improve the sensitivity and specificity of cancer detection. The findings of this research are anticipated to make a significant contribution to enhancing early breast cancer detection capabilities and optimizing therapy utilization in patients.

Advancing Healthcare: Synergizing Biosensors and Machine Learning for Early Cancer Diagnosis.

Cancer is a fatal disease and a significant cause of millions of deaths. Traditional methods for cancer detection often have limitations in identifying the disease in its early stages, and they can be expensive and time-consuming. Since cancer typically lacks symptoms and is often only detected at advanced stages, it is crucial to use affordable technologies that can provide quick results at the point of care for early diagnosis. Biosensors that target specific biomarkers associated with different types of cancer offer an alternative diagnostic approach at the point of care. Recent advancements in manufacturing and design technologies have enabled the miniaturization and cost reduction of point-of-care devices, making them practical for diagnosing various cancer diseases. Furthermore, machine learning (ML) algorithms have been employed to analyze sensor data and extract valuable information through the use of statistical techniques. In this review paper, we provide details on how various machine learning algorithms contribute to the ongoing development of advanced data processing techniques for biosensors, which are continually emerging. We also provide information on the various technologies used in point-of-care cancer diagnostic biosensors, along with a comparison of the performance of different ML algorithms and sensing modalities in terms of classification accuracy.

Fallopian tube cytology as a diagnostic tool for adnexal malignancy: the CytoSaLPs score.

During the past decade, the theory that high-grade extrauterine pelvic tumors originate from the fallopian tube has been strongly suggested. Our study aims to illuminate the possible role of tubal cytology as an accessory identification tool for gynecologic extrauterine malignancies, allowing in the long term the implementation of population-level cytologic tube evaluation during all benign gynecologic surgeries that do not result in salpingectomy. We exvivo collect salpingeal epithelial cells from the fibria directly from fresh fallopian tube specimens from women undergoing salpingectomy for any indication. The cytomorphologic characteristics of the salpingeal cells are subsequently evaluated and categorized into malignant and non-malignant. Finally, the ipsilateral adnexa are examined with the SEE-FIM (Sectioning and Extensively Examining the FIMbriated End) protocol and the pathology reports are corelated with the cytologic findings. Our research protocol is ongoing and is designed to include a total of 300 patients in order to confirm the sensitivity and specificity of salpingeal cytology as a method in the early diagnosis of extrauterine gynecologic malignancies. So far, we have obtained 343 salpingeal brushings from a total of 214 patients. The sensitivity of cytology regarding distinguishing malignant from non-malignant tumors is 69.64% (95% CI: 55.90%-81.22%), and its specificity 75.96% (95% CI: 70.59%-80.79%). Cytology's positive predictive value (PPV) is 16.33% (95% CI: 12.57%-20.67%), while the negative predictive value (NPP) reached 92.77% (95% CI: 89.56%-95.04%). In general, the diagnostic accuracy of the cytologic evaluation reaches 74.93% (95% CI: 66.99%-79.43%). Salpingeal cytomorphologic evaluation appears to be a promising method for early detection of adnexal cancer.

Peripheral Blood Serum NMR Metabolomics Is a Powerful Tool to Discriminate Benign and Malignant Ovarian Tumors.

Ovarian cancer is the major cause of death from gynecological cancer and the third most common gynecological malignancy worldwide. Despite a slight improvement in the overall survival of ovarian carcinoma patients in recent decades, the cure rate has not improved. This is mainly due to late diagnosis and resistance to therapy. It is therefore urgent to develop effective methods for early detection and prognosis. We hypothesized that, besides being able to distinguish serum samples of patients with ovarian cancer from those of patients with benign ovarian tumors, 1H-NMR metabolomics analysis might be able to predict the malignant potential of tumors. For this, serum 1H-NMR metabolomics analyses were performed, including patients with malignant, benign and borderline ovarian tumors. The serum metabolic profiles were analyzed by multivariate statistical analysis, including principal component analysis (PCA) and orthogonal partial least squares discriminant analysis (OPLS-DA) methods. A metabolic profile associated with ovarian malignant tumors was defined, in which lactate, 3-hydroxybutyrate and acetone were increased and acetate, histidine, valine and methanol were decreased. Our data support the use of 1H-NMR metabolomics analysis as a screening method for ovarian cancer detection and might be useful for predicting the malignant potential of borderline tumors.

An efficient deep learning scheme to detect breast cancer using mammogram and ultrasound breast images

Breast cancer is the second major reason of death among women around the world. Early and accurate breast cancer detection is important for proper treatment planning to save a life. In this paper, a deep learning-based ensemble classifier is proposed for the detection of breast cancer. The primary contributions are: (1) an efficient deep learning-based breast cancer detection method that can exhibit admirable performance with a small dataset; (2) the integration of three efficient transfer learning models (AlexNet, ResNet, and MobileNetV2), which lead to more accurate results; (3) the use of residual learning, depthwise separable convolution, and inverted residual bottleneck structure to make the system faster, as well as skip connection to make optimization easier and lastly, employing Laplacian of Gaussian (LoG) and modified high-boosting to improve performance. The experimental results convey that the suggested scheme gives superior classification performance by achieving an accuracy of 99.17% to detect abnormality and 97.75% to detect malignancy on the mini-DDSM dataset. Similarly, on the ultrasound dataset (BUSI), it provides accuracies of 96.92% and 94.62% to detect abnormality and malignancy, respectively. It also gives the best performance in another ultrasound dataset, BUS2, with 97.50% accuracy. Therefore, because of its versatility and reliability, the proposed model can be used for breast cancer detection in multimodal datasets.