Histopathological Image Analysis Research Articles

Multiple instance learning for eosinophil quantification of sinonasal histopathology images: A hierarchical determination on whole slide images.

We proposed a hierarchical framework including an unsupervised candidate image selection and a weakly supervised patch image detection based on multiple instance learning (MIL) to effectively estimate eosinophil quantities in tissue samples from whole slide images. MIL is an innovative approach that can help deal with the variability in cell distribution detection and enable automated eosinophil quantification from sinonasal histopathological images with a high degree of accuracy. The study lays the foundation for further research and development in the field of automated histopathological image analysis, and validation on more extensive and diverse datasets will contribute to real-world application.

Combined use of hydrogen-rich water and enzyme-digested edible bird's nest improves PMA/LPS-impaired wound healing in human inflammatory gingival tissue equivalents.

Gingival wound healing plays a critical role in maintaining oral health. However, this process can be delayed by oxidative stress and excessive inflammatory responses. In this study, we established a human inflammatory gingival tissue equivalent (iGTE) to investigate the inhibitory effects of hydrogen-rich water (HW), enzyme-digested edible bird's nest (EBND) and sialic acid (SA) on PMA (an inducer of oxidative free radicals)- and LPS (an inflammatory stimulus)-impaired wound healing. The iGTE was constructed by human gingival fibroblasts (hGFs), keratinocytes and macrophages under three-dimensional conditions. Wounds in the iGTE and hGF/keratinocyte monolayers were created by mechanical injury. Tissues and cells were pretreated with HW, EBND, and SA, and then exposed to the inflammatory and oxidative environment induced by PMA (10ng/mL) and LPS (250ng/mL). The inflammatory cytokines IL-6 and IL-8 were quantitatively analyzed by ELISA. Histopathological image analysis was performed by HE and immunofluorescence staining. In the iGTE, PMA/LPS significantly reduced the epithelial thickness while causing a decrease in K8/18, E-cadherin, laminin and elastin expression and an increase in COX-2 expression along with ulcer-like lesions. In mechanically scratched hGFs and keratinocyte monolayers, PMA/LPS significantly impaired wound healing, and promoted the secretion of IL-6 and IL-8. Pretreatment of HW, EBND, and SA significantly suppressed PMA/LPS-induced wound healing delay and inflammatory responses in cell monolayers, as well as in the iGTE. Remarkably, the combined use of HW and EBND exhibited particularly robust results. Combined use of HW and EBND may be applied for the prevention and treatment of wound healing delay.

Modified Adaptive CNN for Deep Learning based Histopathological Image Analysis for Cancer Diagnosis

This research on cancer diagnosis is motivated by the need for more accurate and efficient diagnostic tools in the field of oncology. Traditional methods of histopathological examination are time-consuming and can be subject to human error. The adoption of deep learning techniques, particularly Convolutional Neural Networks (CNNs), presents an opportunity to significantly improve the precision and speed of cancer diagnosis through automated analysis of tissue samples. This research addresses current challenges, including variability in samples and limited dataset diversity, with the goal of enhancing the reliability and applicability of the developed models. The ultimate aim is to contribute to the advancement of diagnostic methodologies, providing clinicians with more reliable tools for early and accurate cancer detection and ultimately improving patient outcomes and treatment strategies. Using a modified adaptive CNN algorithm, trained on extensive pathology image datasets, the approach enhances the precision and speed of cancer cell detection in tissue samples. By utilizing these artificial intelligence tools, the diagnostic process becomes not only more accurate but also significantly expeditious. Despite the promising strides, certain challenges persist. Variability in tissue samples, limited availability of diverse datasets, and interpretability of deep learning models pose hurdles to widespread adoption. To address these challenges, this research focuses on developing robust models that can generalize well across diverse datasets. Additionally, efforts are being made to create more comprehensive and diverse datasets to improve model training. Results show accuracy exceeding 97%, sensitivity and specificity at 97% and 95%, F1 score reaching 96%, and precision at 96%.

Modified Adaptive CNN for Deep Learning based Histopathological Image Analysis for Cancer Diagnosis

This research on cancer diagnosis is motivated by the need for more accurate and efficient diagnostic tools in the field of oncology. Traditional methods of histopathological examination are time-consuming and can be subject to human error. The adoption of deep learning techniques, particularly Convolutional Neural Networks (CNNs), presents an opportunity to significantly improve the precision and speed of cancer diagnosis through automated analysis of tissue samples. This research addresses current challenges, including variability in samples and limited dataset diversity, with the goal of enhancing the reliability and applicability of the developed models. The ultimate aim is to contribute to the advancement of diagnostic methodologies, providing clinicians with more reliable tools for early and accurate cancer detection and ultimately improving patient outcomes and treatment strategies. Using a modified adaptive CNN algorithm, trained on extensive pathology image datasets, the approach enhances the precision and speed of cancer cell detection in tissue samples. By utilizing these artificial intelligence tools, the diagnostic process becomes not only more accurate but also significantly expeditious. Despite the promising strides, certain challenges persist. Variability in tissue samples, limited availability of diverse datasets, and interpretability of deep learning models pose hurdles to widespread adoption. To address these challenges, this research focuses on developing robust models that can generalize well across diverse datasets. Additionally, efforts are being made to create more comprehensive and diverse datasets to improve model training. Results show accuracy exceeding 97%, sensitivity and specificity at 97% and 95%, F1 score reaching 96%, and precision at 96%.

Activity Test of Cassia alata L. Leaf Extract on Kidney Histopathology Damage Score of Diabetes Mellitus Model

Diabetic nephropathy is a disease experienced by diabetic patients. In this disease, damage to the glomerulus occurs. The administration of antidiabetic drugs tends to cause unwanted side effects, so there is a need for alternative treatment from herbs, one of which is Cassia alata L. Cassia alata L. leaves have chemical content such as flavonoids, alkaloids, tannins, and saponins. Flavonoids reduce blood glucose levels by increasing insulin secretion and mimetic agents, tannins slow carbohydrate digestion and saponins repair pancreatic beta cells and increase glycogen in the liver. This study aims to determine the effect of Cassia alata L. ethanol on the histopathology damage score of male white rat kidney (Rattus norvegicus) induced by streptozotocin. The test animals used were 30 male white rats divided into six treatment groups, each group consisting of five male white rats, namely the normal control group, negative control group, positive control group, treatment group with doses of 500 mg/kg BW, 600 mg/kg BW, and 700 mg/kg BW. The parameters evaluated were kidney tissue damage score and histopathology image analysis. The results showed that the ethanol extract of Cassia alata L. leaves contain alkaloids, flavonoids, saponins, and tannins. The ethanol extract of Cassia alata L. leaves in doses of 500 mg/kg BW, 600 mg/kg BW and 700 mg/kg BW has the activity of reducing the score of kidney tissue damage in male white rats and a dose of 700 mg/kg BW is the best dose in reducing the score of kidney tissue damage in diabetes mellitus models with a score of 2.

Ensemble Residual Network with Iterative Randomized Hyperparameter Optimization for Colorectal Cancer Classification

The analysis of WSI images is widely acknowledged as a method, for identifying stages of cancer and evaluating the spread of cancer cells in tissues. In histopathology image analysis deep learning models are gaining increasing importance. To enhance the effectiveness of these models it is crucial to train and fine-tune Convolutional Neural Network algorithms by adjusting hyperparameters like batch size, convolution depth, and learning rate (LR). However, determining the hyperparameters can be challenging as they significantly impact model performance. This study examines how hyperparameters influence cancer classification, in histopathology images using the CNN architecture. A method called iterative randomized hyperparameter optimization is proposed, which gradually reduces variations over time by adjusting parameters after each network layer. The combination of hyperparameters is applied to version 1 of ResNet18, ResNet50, and ResNet101 models and version 2 of ResNet50, ResNet101, and ResNet151. The results are then combined using the Adaptive Boosting algorithm. The results are quite promising on ensemble version 1 residual networks, achieving an accuracy of 98.7% when tested on nine tissue classes.

Adapting SAM to Histopathology Images for Tumor Bud Segmentation in Colorectal Cancer.

Colorectal cancer (CRC) is the third most common cancer in the United States. Tumor Budding (TB) detection and quantification are crucial yet labor-intensive steps in determining the CRC stage through the analysis of histopathology images. To help with this process, we adapt the Segment Anything Model (SAM) on the CRC histopathology images to segment TBs using SAM-Adapter. In this approach, we automatically take task-specific prompts from CRC images and train the SAM model in a parameter-efficient way. We compare the predictions of our model with the predictions from a trained-from-scratch model using the annotations from a pathologist. As a result, our model achieves an intersection over union (IoU) of 0.65 and an instance-level Dice score of 0.75, which are promising in matching the pathologist's TB annotation. We believe our study offers a novel solution to identify TBs on H&E-stained histopathology images. Our study also demonstrates the value of adapting the foundation model for pathology image segmentation tasks.

Uncertainty-Guided Asymmetric Consistency Domain Adaptation for Histopathological Image Classification

Deep learning has achieved remarkable progress in medical image analysis, but its effectiveness heavily relies on large-scale and well-annotated datasets. However, assembling a large-scale dataset of annotated histopathological images is challenging due to their unique characteristics, including various image sizes, multiple cancer types, and staining variations. Moreover, strict data privacy in medicine severely restricts data sharing and poses significant challenges in acquiring large-scale and well-annotated histopathological images. To tackle these constraints, Transfer Learning (TL) provides a promising solution by exploiting knowledge from another domain. This study proposes the Uncertainty-guided asymmetric Consistency Domain Adaptation (UCDA), which does not require accessing the source data and is composed of two essential components, e.g., Uncertainty-guided Source-free Transfer Learning (USTL) and Asymmetric Consistency Learning (ACL). In detail, USTL facilitates a secure mapping of the source domain model’s feature space onto the target domain, eliminating the dependency on source domain data to protect data privacy. At the same time, the ACL module measures the symmetry and asymmetry between the source and target domains, bridging the information gap and preserving inter-domain differences among medical images. We comprehensively evaluate the effectiveness of UCDA on three widely recognized and publicly available datasets, namely NCTCRC-HE-100K, PCam, and LC25000. Impressively, our proposed method achieves remarkable performance on accuracy and F1-scores. Additionally, feature visualizations effectively demonstrate the exceptional generalizability and discriminative power of the learned representations. These compelling results underscore the significant potential of UCDA in driving the advancement of deep learning techniques within the realm of histopathological image analysis.

A deep multi-branch attention model for histopathological breast cancer image classification

AbstractSince the impressive superior performance demonstrated by deep learning methods is widely used in histopathological image analysis and diagnosis, existing work cannot fully extract the information in the breast cancer images due to the limited high resolution of histopathological images. In this study, we construct a novel intermediate layer structure that fully extracts feature information and name it DMBANet, which can extract as much feature information as possible from the input image by up-dimensioning the intermediate convolutional layers to improve the performance of the network. Furthermore, we employ the depth-separable convolution method on the Spindle Structure by decoupling the intermediate convolutional layers and convolving them separately, to significantly reduce the number of parameters and computation of the Spindle Structure and improve the overall network operation speed. We also design the Spindle Structure as a multi-branch model and add different attention mechanisms to different branches. Spindle Structure can effectively improve the performance of the network, the branches with added attention can extract richer and more focused feature information, and the branch with residual connections can minimize the degradation phenomenon in our network and speed up network optimization. The comprehensive experiment shows the superior performance of DMBANet compared to the state-of-the-art method, achieving about 98% classification accuracy, which is better than existing methods. The code is available at https://github.com/Nagi-Dr/DMBANet-main.

Deep learning-based identification of esophageal cancer subtypes through analysis of high-resolution histopathology images.

Esophageal cancer (EC) remains a significant health challenge globally, with increasing incidence and high mortality rates. Despite advances in treatment, there remains a need for improved diagnostic methods and understanding of disease progression. This study addresses the significant challenges in the automatic classification of EC, particularly in distinguishing its primary subtypes: adenocarcinoma and squamous cell carcinoma, using histopathology images. Traditional histopathological diagnosis, while being the gold standard, is subject to subjectivity and human error and imposes a substantial burden on pathologists. This study proposes a binary class classification system for detecting EC subtypes in response to these challenges. The system leverages deep learning techniques and tissue-level labels for enhanced accuracy. We utilized 59 high-resolution histopathological images from The Cancer Genome Atlas (TCGA) Esophageal Carcinoma dataset (TCGA-ESCA). These images were preprocessed, segmented into patches, and analyzed using a pre-trained ResNet101 model for feature extraction. For classification, we employed five machine learning classifiers: Support Vector Classifier (SVC), Logistic Regression (LR), Decision Tree (DT), AdaBoost (AD), Random Forest (RF), and a Feed-Forward Neural Network (FFNN). The classifiers were evaluated based on their prediction accuracy on the test dataset, yielding results of 0.88 (SVC and LR), 0.64 (DT and AD), 0.82 (RF), and 0.94 (FFNN). Notably, the FFNN classifier achieved the highest Area Under the Curve (AUC) score of 0.92, indicating its superior performance, followed closely by SVC and LR, with a score of 0.87. This suggested approach holds promising potential as a decision-support tool for pathologists, particularly in regions with limited resources and expertise. The timely and precise detection of EC subtypes through this system can substantially enhance the likelihood of successful treatment, ultimately leading to reduced mortality rates in patients with this aggressive cancer.

Predicting Breast Cancer Risk from Histopathology Images using Hybrid Deep Learning Classifier

Millions of people per year pass away from breast cancer (BC), which is a fatal illness. To deal with this issue more effectively, diagnoses can be made more scalable and less prone to mistakes by developing automated malignant BC detection systems applied on patient's imaging. Not less significant is the fact that this type of research can be expanded to include additional cancer types, having a greater influence on helping to save lives. Recent BC recognition results demonstrate that Convolution Neural Networks (CNN) can outperform manually crafted feature descriptors in terms of recognition rates. However, this higher recognition rate comes at the cost of a more complex system to develop, one that requires more time for training and specialized knowledge to fine-tune the CNN's architecture. The comprehensive understanding of the structural and cellular attributes of tissue samples that histopathological image analysis imparts is regarded as a crucial component in the rapid detection and diagnosis of breast cancer. By means of this analysis, pathologists are capable of discerning aberrant cellular proliferation, ascertaining the existence of malignant tumours, and evaluating the degree of cancer advancement. The utilization of sophisticated imaging technologies and computational algorithms in histopathological image analysis improves the precision and effectiveness of diagnosis, allowing medical practitioners to expeditiously commence suitable therapeutic strategies. In conclusion, this instrument makes a substantial contribution towards enhancing the efficacy of breast cancer management in the field of clinical practice. However, because to its ineffectiveness, the identification of breast cancer is still an unresolved problem in medical image analysis. By combining deep learning and machine learning techniques, we were able to create a categorization system built on histology images that significantly improved the accuracy of early breast cancer diagnosis while relieving doctors of some of their effort. Multilayer Perceptron and LightGBM classifiers are used in this study's analysis of histology images of breast cancer (BC). Histopathology images are the gold standard when it comes to making a diagnosis of breast cancer. Here, a dataset of 3104 photos is used to train our model, and the image is subsequently successfully identified. This strategy also yields impressive analysis and findings. We test the suggested strategy using histology images from the Breast Cancer dataset, and we achieve a high classification accuracy of 98.28%. The results of the experiments demonstrate that our strategy can perform pretty favourably and exceed cutting-edge approaches.In the near future, using deep learning to predict breast cancer may show to be quite successful.

SegEIR-Net: A Robust Histopathology Image Analysis Framework for Accurate Breast Cancer Classification.

Breast Cancer (BC) is a significant threat affecting women globally. An accurate and reliable disease classification method is required to get an early diagnosis. However, existing approaches lack accurate and robust classification. This study aims to design a model to classify BC Histopathology images accurately by leveraging segmentation techniques. This work proposes a combined segmentation and classification approach for classifying BC using histopathology images to address these issues. Chan-Vese algorithm is used for segmentation to accurately delineate regions of interest within the histopathology images, followed by the proposed SegEIR-Net (Segmentation using EfficientNet, InceptionNet, and ResNet) for classification. Bilateral Filtering is also employed for noise reduction. The proposed model uses three significant networks, ResNet, InceptionNet, and EfficientNet, concatenates the outputs from each block followed by Dense and Dropout layers. The model is trained on the breakHis dataset for four different magnifications and tested on BACH (BreAst Cancer Histology) and UCSB (University of California, Santa Barbara) datasets. SegEIR-Net performs better than the existing State-of-the-Art (SOTA) methods in terms of accuracy on all three datasets, proving the robustness of the proposed model. The accuracy achieved on breakHis dataset are 98.66%, 98.39%, 97.52%, 95.22% on different magnifications, and 93.33% and 96.55% on BACH and UCSB datasets. These performance results indicate the robustness of the proposed SegEIR-Net framework in accurately classifying BC from histopathology images.

What can machine vision do for lymphatic histopathology image analysis: a comprehensive review

Over the past 10 years, machine vision (MV) algorithms for image analysis have been developing rapidly with computing power. At the same time, histopathological slices can be stored as digital images. Therefore, MV algorithms can provide diagnostic references to doctors. In particular, the continuous improvement of deep learning algorithms has further improved the accuracy of MV in disease detection and diagnosis. This paper reviews the application of image processing techniques based on MV in lymphoma histopathological images in recent years, including segmentation, classification and detection. Finally, the current methods are analyzed, some potential methods are proposed, and further prospects are made.

A Histopathologic Image Analysis for the Classification of Endocervical Adenocarcinoma Silva Patterns Depend on Weakly Supervised Deep Learning

25% of cervical cancers are classified as endocervical adenocarcinomas (EACs), which comprise a highly heterogeneous group of tumors. A histopathological risk stratification system known as the Silva pattern system was developed based on morphology. However, accurately classifying such patterns can be challenging. The objective was to develop a deep learning pipeline (Silva3-AI) that automatically analyzes whole-slide-image-based histopathological images and identifies Silva patterns with high accuracy. Initially, a total of 202 patients with EACs and histopathological slides were obtained from QLHSDU for developing and internally testing the Silva3-AI model. Subsequently, an additional 161 patients and slides were collected from seven other medical centers for independent testing. The Silva3-AI model was developed using a ViT and RNN architecture, utilizing multi-magnification patches, and its performance was evaluated based on class-specific AUROC. Silva3-AI achieved a class-specific AUROC of 0.947 for Silva A, 0.908 for Silva B, and 0.947 for Silva C on the independent test set. Notably, the performance of Silva3-AI was consistent with that of professional pathologists possessing 10 years of diagnostic experience. The findings in this study implicate Silva3-AI, which could predict Silva pattern in an interpretable manner, achieved comparable performance to that of experienced pathologists. Furthermore, the visualization of prediction heatmaps facilitated the identification of TME heterogeneity, which is known to contribute to variations in Silva patterns.

Deep Learning for Histopathological Image Analysis: A Convolutional Neural Network Approach to Colon Cancer Classification

Colon cancer is a type of cancer that attacks the last part of the human digestive tract. Factors such as an unhealthy diet, low fiber consumption, and high animal protein and fat intake can increase the risk of developing this disease. Diagnosis of colon cancer requires sophisticated diagnostic procedures such as CT scan, MRI, PET scan, ultrasound, or biopsy, which are often time-consuming and require particular expertise. This study aims to classify colon cancer based on histopathological images using a dataset of 10,000 images. This data is divided into 7,950 images for training, 2,000 for testing, and 50 for validation, aiming to achieve effective generalization. The Convolutional Neural Network (CNN) method was applied in this research with a relatively shallow architecture consisting of 4 convolution layers, 2 fully connected layers, and 1 output layer. Research results were evaluated by looking at the accuracy value of 99.55%, precision value of 99.49%, recall of 99.59%, prediction experiments on several images, and loss and accuracy graphs to detect signs of overfitting. However, this research has limitations in determining hyperparameters and layer depth, which was only tested from 1 to 5 convolution layers. Therefore, there are still opportunities for further development, such as applying unique feature extraction before the classification process

A novel Nine-SequenceNet with attention for liver histopathological classification

Liver cancer is a prevalent cancer worldwide and is also the leading cause of cancer-related deaths. Histopathological image diagnosis is taken as the standard to identify liver cancer. However, manually histopathological examination of liver cancer WSIs (Whole Slide Image) is time consuming. To address this issue, researchers have applied the automatic classification methods to recognize cancerous tissues in histopathological images, which can effectively reduce the examination time and improving the recognition efficiency. In recent years, deep learning based methods have been widely used in histopathological image analysis because of their impressive performance level. But only a little research work based on transfer learning has been done on liver cancer histopathological images because the sample dataset is difficult to collected and the classification results lack of effectiveness and pertinence. One issue with fine-grained classification is that using a single patch for classification results in the loss of edge information, degrading classification performance. To solve the problem, this paper proposes a novel deep learning model based on sequence prediction with attention, which is used to identify and classify liver cancer histopathological images. The proposed method uses the surrounding 8 patches to supplement information to the current patch, resulting in better results than other methods. The experimental results show that this method achieves the best F1-score of 95.23% which illustrates that the proposed method is efficient in liver cancer histopathological image classification.

An introduction to double stain normalization technique for brain tumour histopathological images

Stain normalization is an image pre-processing method extensively used to standardize multiple variances of staining intensity in histopathology image analysis. Staining variations may occur for several reasons, such as unstandardized protocols while preparing the specimens, using dyes from different manufacturers, and varying parameters set while capturing the digital images. In this study, a double stain normalization technique based on immunohistochemical staining is developed to improve the performance of the conventional Reinhard’s algorithm. The proposed approach began with preparing a target image by applying the contrast-limited adaptive histogram equalization (CLAHE) technique to the targeted cells. Later, the colour distribution of the input image will be matched to the colour distribution of the target image through the linear transformation process. In this study, the power-law transformation was applied to address the over-enhancement and contrast degradation issues in the conventional method. Five quality metrics comprised of entropy, tenengrad criterion (TEN), mean square error (MSE), structural similarity index (SSIM) and correlation coefficient were used to measure the performance of the proposed system. The experimental results demonstrate that the proposed method outperformed all conventional techniques. The proposed method achieved the highest average values of 5.59, 3854.11 and 94.65 for entropy, TEN, and MSE analyses.

RETRACTED: Liu et al. Prediction of Ovarian Cancer Response to Therapy Based on Deep Learning Analysis of Histopathology Images. Cancers 2023, 15, 4044

The journal and authors wish to retract the article entitled ‘Prediction of Ovarian Cancer Response to Therapy Based on Deep Learning Analysis of Histopathology Images’ cited above [...]

Colorectal cancer histopathology image analysis: A comparative study of prognostic values of automatically extracted morphometric nuclear features in multispectral and red-blue-green imagery.

Multispectral imaging (MSI) has been utilized to predict the prognosis of colorectal cancer (CRC) patients, however, our understanding of the prognostic value of nuclear morphological parameters of bright-field MSI in CRC is still limited. This study was designed to compare the efficiency of MSI and standard red-green-blue (RGB) images in predicting the prognosis of CRC. We compared the efficiency of MS and conventional RGB images on the quantitative assessment of hematoxylin-eosin (HE) stained histopathology images. A pipeline was developed using a pixel-wise support vector machine (SVM) classifier for gland-stroma segmentation, and a marker-controlled watershed algorithm was used for nuclei segmentation. The correlation between extracted morphological parameters and the five-year disease-free survival (5-DFS) was analyzed. Forty-seven nuclear morphological parameters were extracted in total. Based on Kaplan-Meier analysis, eight features derived from MS images and seven featured derived from RGB images were significantly associated with 5-DFS, respectively. Compared with RGB images, MSI showed higher accuracy, precision, and Dice index in nuclei segmentation. Multivariate analysis indicated that both integrated parameters 1 (factors negatively correlated with CRC prognosis including nuclear number, circularity, eccentricity, major axis length) and 2 (factors positively correlated with CRC prognosis including nuclear average area, area perimeter, total area/total perimeter ratio, average area/perimeter ratio) in MS images were independent prognostic factors of 5-DFS, in contrast with only integrated parameter 1 (P<0.001) in RGB images. More importantly, the quantification of HE-stained MS images displayed higher accuracy in predicting 5-DFS compared with RGB images (76.9% vs 70.9%). Quantitative evaluation of HE-stained MS images could yield more information and better predictive performance for CRC prognosis than conventional RGB images, thereby contributing to precision oncology.

Using hybrid pre-trained models for breast cancer detection.

Breast cancer is a prevalent and life-threatening disease that affects women globally. Early detection and access to top-notch treatment are crucial in preventing fatalities from this condition. However, manual breast histopathology image analysis is time-consuming and prone to errors. This study proposed a hybrid deep learning model (CNN+EfficientNetV2B3). The proposed approach utilizes convolutional neural networks (CNNs) for the identification of positive invasive ductal carcinoma (IDC) and negative (non-IDC) tissue using whole slide images (WSIs), which use pre-trained models to classify breast cancer in images, supporting pathologists in making more accurate diagnoses. The proposed model demonstrates outstanding performance with an accuracy of 96.3%, precision of 93.4%, recall of 86.4%, F1-score of 89.7%, Matthew's correlation coefficient (MCC) of 87.6%, the Area Under the Curve (AUC) of a Receiver Operating Characteristic (ROC) curve of 97.5%, and the Area Under the Curve of the Precision-Recall Curve (AUPRC) of 96.8%, which outperforms the accuracy achieved by other models. The proposed model was also tested against MobileNet+DenseNet121, MobileNetV2+EfficientNetV2B0, and other deep learning models, proving more powerful than contemporary machine learning and deep learning approaches.