Jul 2026· International Conference on Information and Communicatiaon Technology· pp. 1-6· 0 citations· 39 references
Abstract
Breast cancer is still one of the most common cancers worldwide, with about 2.26 million new cases in 2020. Ultrasound (USG) images are an important screening method because they are non-invasive and affordable. However, USG images often have speckle noise and low contrast, which can make diagnosis less consistent. While deep learning has significantly improved classification accuracy, many complex models require substantial computational resources, limiting their application on portable or edge devices. Furthermore, the opaque nature of these models often hinders clinical trust and interpretability. In this study, we propose a precise and interpretable classification system for breast ultrasound images using a combined dataset of 1,030 samples from the BUSI and Mendeley repositories. We evaluated six distinct deep learning architectures: DenseNet121, EfficientNetB3, EfficientNetB4, MobileNetV2, MobileNetV3, and VGG16. To address the black box nature of deep learning, we integrated the Grad-CAM technique, which generates visual saliency maps to highlight relevant pathological features. Our experiments showed that MobileNetV3 had the best overall performance, with 92.41% accuracy and a 91.19% F1-score. EfficientNetB3 had the highest sensitivity, with a recall of 96.98%. Grad-CAM visualizations showed that the models focused on the important areas of the lesions. These results suggest that using lightweight models with Explainable AI (XAI) can offer an effective, reliable, and efficient diagnostic tool for real-world clinical use, especially where resources are limited.
Breast cancer remains a predominant cause of mortality among women, highlighting the importance of accurate early detection. Mammography can be hampered by breast density and radiation exposure, while ultrasound is safer and more accessible. However, ultrasound images have speckle noise, low contrast, and often blurred lesion boundaries, making readings subjective. Transfer learning-based Convolutional Neural Network (CNN) approaches are widely used, but structured comparisons of architectures for three-class breast cancer classification (benign, malignant, and normal) on the combined BUSI and Mendeley datasets, particularly with respect to computational efficiency, remain limited. This study evaluates five transfer learning models (VGG16, VGG19, InceptionV3, Xception, ResNet50) on 1,030 images from BUSI and Mendeley. The images were standardised to PNG, converted to RGB, resized to 224×224, noise-reduced with a 3×3 median filter, normalised according to the architecture preprocessing, and augmented conservatively. The dataset was split into an 80% training set, a 10% validation set, and a 10% testing set, utilizing ImageNet weights and implementing partial fine-tuning. ResNet50 exhibited superior performance, attaining an accuracy of 90.29%, a precision of 90.48%, a recall of 90.29%, and an F1-score of 88.74%, outperforming VGG19 (F1-score 87.58%) and Xception (F1-score 86.51%). These findings suggest that computationally efficient models can deliver reliable results and may support computer-aided ultrasound diagnosis in resource-limited environments.
Gena Darma, Made Naradeon, Handika Pramesta et al.· International Conference on...· 0 citations
Breast cancer is a significant cause of cancer-related deaths among women worldwide. Its early identification and screening are essential for improved patient outcomes and reduced mortality rates. Histopathological image analysis is considered as the gold standard for the diagnosis and prognosis of breast cancer. Nevertheless, the complexity of Whole-Slide Images (WSI) and their manual examination make this task time consuming, and prone to pathologist subjectivity. Recently, Deep Learning (DL) technology has achieved remarkable success in computer vision. However, their application still faces critical challenges in pathology analysis, including Region-of-Interest (RoI) scale variations, inter- and intra-class heterogeneity, diverse staining protocols, and the scarcity of annotated datasets. Furthermore, DL model’s findings are opaque and lack decision-level transparency. This study proposes a novel explainable multi-model DL framework for breast cancer classification leveraging histopathological images. The framework integrates Contrast Limited Adaptive Histogram Equalization (CLAHE) for image contrast enhancement, and diverse data augmentation to mitigate class imbalance and overfitting. Proposed architecture ensembles two branches, one employes DenseNet201 benefiting from Transfer Learning (TL) via ImageNet weights, while other utilizes a custom light weight attention based Hierarchal Feature Fusion (HFF) Network. DenseNet201 utilizes multilevel features to effectively tackle gradient vanishing issues and capture intricate feature representations, while HFF-Net, designed specifically for biomedical imaging, leverages HFF stem and multiscale feature extraction with Swish activation to enhance learning stability. Attention mechanism introduced within HFF-Net further refines the output features. Final feature vectors from the two branches are fused at the Global Average Pooling (GAP) layer, consolidating discriminative information. Experimental results on BRACS dataset demonstrate the proposed framework achieves 97.15% accuracy, 92.59% precision, 93.81% recall, and a 93.19% F1-score in screening tasks, while for grading tasks, it attains 84.08% accuracy, 83.39% precision, 83.64% recall, and 83.44% F1-score on 4391 test samples. Additionally, Gradient-Class Activation Mapping (Grad-CAM) saliency heatmap are generated for visual representation of proposed model’s choices, thereby increased transparency. The integration of these advanced techniques significantly enhances diagnostic reliability, addressing the challenges in histopathological image analysis.
Muhammad Nabeel Mehmood, Muhammad Hassaan Ashraf· Informatica· 0 citations
Breast cancer remains a leading cause of mortality among women in low- and middle-income countries (LMICs), compounded by fewer radiologists available and resources for diagnosis. A narrative review that summarizes 45 peer-reviewed publications to date from 2018 to 2025 is presented for deep learning (DL) models for mammography detection for breast cancer, targeting low-resource-critical architectures for development in LMIC settings. We compare convolutional neural networks (CNNs), hybrid CNN-support vector machine (SVM) models, recurrent/LSTM networks, and lightweight architectures such as MobileNet and EfficientNet. In quantitative synthesis the reported diagnostic accuracy for MobileNet is between 89 and 92%, supported with 128 MB RAM and 0.3 GFLOPs. Therefore it is appropriate for offline edge devices (smartphones, NVIDIA Jetson Nano). EfficientNet achieves 91–94% accuracy—though it requires stable internet to enable cloud deployment, due to its greater parameter size (5.3 million). Both architectures reduce false positives by 7 to 69% and false negatives by 9% compared to traditional computer-aided detection, though most evidence is retrospective. The most important contributions from this review are: (1) a quantitative comparison of efficiency for edge versus cloud deployment, (2) detection of dataset bias (no LMIC-specific validation exists), and (3) practical recommendations regarding infrastructure, regulatory pathways, and privacy-preserving federated learning. Limitations include cross-study heterogeneity in datasets (CBIS-DDSM, INbreast, MIAS) and evaluation protocols. We conclude that MobileNet and EfficientNet provide good trade-offs for LMICs but call for prospective trials and locally curated datasets before clinical implementation.
Kennedy T. Chitiza, Abid Yahya, Nechibvute Action et al.· Discover Data· 0 citations
Breast cancer is a leading cause of cancer morbidity and mortality among women globally, emphasizing the need for accurate and timely diagnostic methods. A systematic but innovative two phases transfer learning based deep learning classification framework is developed using popular EfficientNetB7 architecture architecture for breast cancer classification. Breast ultrasound imaging proves a high degree of complexity to extract features with limited available medical datasets to address it and the proposed methodology attributes to it. We develop a framework which encompasses formalisation into components like data augmentation, progressive fine-tuning and adaptive learning rate optimization as methods for model generalisation. Experiments on the Breast Ultrasound Images (BUSI) dataset show that the model achieves best accuracy of over 91. 25% when classifying breast lesions into benign, malignant, and normal. It shows good discriminative abilities (validation accuracy: 93.62%) and a trained model converge well. We compare our method with the current ones and show significant advancements over all previous methods making our approach suitable for computer-aided diagnosis systems in clinical workflows.
Madishetti Kavya, G. Thirupati· International Journal of Sci...· 0 citations
Breast density is associated with a higher risk of developing breast cancer and complicates mammographic interpretation because dense tissue can obscure suspicious findings. Deep learning (DL) models are increasingly used for automated breast density classification, yet their limited interpretability remains a concern in safety-critical medical applications. In this paper, we compare several DL backbones for four-class BI-RADS density classification and analyze their predictions using three heatmap explanation methods—GradCAM, GradCAM++, and ScoreCAM. Our results show that transformer-based models achieve marginally stronger classification performance than the evaluated convolutional neural network (CNN) baselines, with the ViT model obtaining the best overall results and showing improved recognition of extremely dense cases. Qualitative heatmap analysis suggests that ScoreCAM produces the most spatially coherent and clinically plausible explanations, particularly for transformer-based models for which gradient-based maps are often diffuse or unstable. We further present an exploratory procedure that converts ScoreCAM heatmaps into coarse binary masks through thresholding, illustrating the potential of explanation maps for weak localization of dense tissue. Rather than claiming a validated segmentation framework, we position this step as a proof of concept that may support future studies on annotation-efficient dense-tissue localization.
Salah Jabreel, Hatem A. Rashwan, N. Jebreel et al.· 2026 6th International Confe...· 0 citations
Accurate and efficient diagnosis of breast cancer from histopathological images remains a major challenge in clinical practice due to subjective interpretation, inter-observer variability, and labor-intensive manual examination. To address these limitations, this work introduces a transfer learning–based framework for automated breast cancer classification using the Breast Cancer Histology Images (BACH) dataset. Several pre-trained deep architectures—including MobileNet, ResNet variants, EfficientNet, and Vision Transformers—were evaluated and extended with a Multi-Scale Feature Fusion (MSFF) module to capture morphological heterogeneity across spatial resolutions. Among these, the Enhanced MobileNet (E‑MobileNet) with MSFF outperforming recent state‑of‑the‑art models and achieving a classification accuracy of 95%, precision of 95%, recall of 94%, and F1‑score of 96%. The framework was further validated on the BreaKHis dataset across multiple magnifications, achieving an average accuracy of 90.6%. These results confirm the robustness and generalization capability of the proposed model for practical clinical deployment in digital pathology.
M. E. Ali, A. Ghalwash, Amany Abdo· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
