A Deep Hybrid CNN–Transformer Framework Combining EfficientNet and Vision Transformer for Multiclass Skin Cancer Classification

Attention-Guided Ensemble Deep Learning Framework for Automated Skin Cancer Classification

Skin cancer is one of the most common malignancies in the world and early and accurate dermoscopic diagnosis is crucial for better survival outcomes of patients. There are various limitations in current single model convolutional and transformer models, such as limited ability to capture local texture, multi-scale morphology, and global contextual information, as well as high intra-class visual similarity and extreme class imbalance. To overcome these problems, this paper proposes an Attention-Guided Ensemble Deep Learning (AGEDL) framework which integrates the EfficientNet-B3, InceptionV3 and Swin Transformer to simultaneously learn complementary dermoscopic representations from the seven-class ISIC 2018 dataset. The Squeeze-and-Excitation (SE) attention blocks dynamically modulate feature responses in each channel, which reduces background noise and enhances discriminative features of lesions. The Lion optimizer offers stable and efficient training in both base training and fine-tuning stages. An XGBoost stacking metalearner is used to combine all backbone networks, and hyperparameters of the XGBoost are optimized by the Dhole Optimizer. The proposed AGEDL achieved 98.02% accuracy, 97.09% precision, 97.05% recall and 94.07% F1 score with 95% confidence interval of 97.41%–98.59%, surpassing the state-of-the-art CNN, transformer-based and hybrid ensemble baselines.

HybridSkinLes: An Explainable CNN-and Transformer-Based Multi-Class Skin Lesion Classification Framework

Skin cancer is considered a deadly disease globally, and the timely identification of the disease may save human life. This research presents a CNN–Transformer-based fusion framework for automated multi-class skin lesion classification. This approach combines ResNet50 and Vision Transformer (ViT) to categorize skin lesions using the HAM10000 dataset. To assess their efficacy, a comparison with CNN and ViT models is also carried out. Seven classes of skin cancer are used for training the models, and class weighting is used to correct dataset asymmetry. According to the experimental dataset, the suggested hybrid framework shows improved performance over CNN and ViT, considering the accuracy (0.97) and macro-averaged F1-score (0.95). Furthermore, the efficiency of the suggested model is demonstrated by the fact that it delivers performance that is competitive with several existing approaches. Overall results indicate that hybrid CNN–Transformer architectures present a viable path for automated skin lesion categorization. Grad-CAM++ is integrated to enhance model understanding and promote medical confidence by enabling physicians to view visualizations that show the areas impacting the model’s conclusions. But there are still issues, including poor generalization, computational complexity, and a lack of external validation. Future research will concentrate on enhancing interpretability for practical implementation, integrating clinical information, and evaluating several datasets.

A Novel Hybrid Deep Learning Architecture Combining CNNs, Vision Transformers, and Multi-Scale Attention for Enhanced Detection of Breast Cancer in Histopathology Images

Breast cancer has been one of the major causes of cancer mortality in the world. According to WHO report 2.5 million deaths are predicted as a result of breast cancer in the world in 2040. Although deep learning has demonstrated encouraging histopathology image analysis, the current methods frequently fail to provide local morphological information and global contextual information at the same time. In this paper, we present our HrybridViT-CAM, a hybrid deep learning system that integrates convolution neural networks( CNN ), Vision Transformers( ViT ) and multi-scale attention system in order to classify breast cancer using histopathology images. Its architecture has a two-way structure: a CNN arm (EfficientNetB7) to extract local features and a vision transformer arm to analyze the global context, fused together with a cross-attention fusion block. We use convolution block attention modules(CBAM) and deformal attention to improve feature discrimination. The model was tested on the BreaKHis dataset with various magnifications (40x, 100x, 200x, 400x) in binary as well as in multi-class classification. For binary classification (benign vs. malignant), HybridViT-CAM achieved accuracies of 99.87%, 99.42%, 98.95%, and 98.31% at 40χ, 100χ, 200x, and 400x magnifications, respectively. For eight-class subtype classification, the corresponding accuracies were 98.76%, 97.89%, 97.23%, and 96.54%, respectively. Grad-CAM++ and attention visualization techniques allowed explaining the results, which showed high correspondence(93.7% agreement) with pathologist diagnostic criterial. The proposed model was able to detect the malignant regions of interest (ROIs) like nuclei pleomorphism, atypia chromatin patterns and architectural distortions which are comparable to clinical diagnostic standards.

Hybrid CNN–BiLSTM with Multi-Transformer Stacking for Skin Lesion Classification

Skin cancer is one of the most common diseases worldwide and, if left untreated, it can be life threatening. In this work, we propose a dual-branch deep learning framework that integrates a CNN–BiLSTM module for local spatial–sequential feature modeling with multiple transformer models (ViT, DeiT, SwinV2, and BEiT) for global representation learning. Each input image is processed in parallel by two branches. The first branch consists of a lightweight convolutional network, followed by row-wise and column-wise Bidirectional LSTM layers to capture spatial and sequential dependencies. The second branch employs a high-resolution transformer to extract features from the image. The features extracted from both branches of the hybrid CNN–BiLSTM–Transformer model are fused to construct a unified classifier for accurate skin lesion recognition. To further improve robustness, four CNN–BiLSTM–Transformer hybrid models are combined using a stacking strategy based on logistic regression that aggregates their prediction probabilities. Experimental results on the binary Kaggle and multi-class HAM10000 datasets demonstrate that stacking achieves better performance than the individual hybrid CNN–BiLSTM–Transformer models, reaching accuracies of 91.21% on the binary Kaggle dataset and 86.08 ± 0.47% on the HAM10000 dataset, respectively. These findings confirm the efficiency of using complementary local and global features for skin lesion classification.

A Multi-head Attention Transformer with Convolutional Projections for Skin Cancer Image Classification

An Explainable Hybrid Deep Learning Framework Integrating SepConv2D, DenseNet121, and Vision Transformer for Automated Skin Lesion Classification

Early and accurate diagnosis of skin lesions is essential for reducing the mortality associated with skin cancer and improving patient outcomes. Although deep learning has significantly advanced automated dermatological diagnosis, existing approaches often struggle to simultaneously achieve high classification accuracy, computational efficiency, and model interpretability. Conventional convolutional neural networks effectively learn local texture patterns but are limited in capturing long-range contextual information, whereas transformer-based models provide superior global feature representation at the expense of increased computational complexity. To address these challenges, this paper proposes an explainable hybrid deep learning framework that integrates Depthwise Separable Convolution (SepConv2D), Vision Transformer (ViT), and DenseNet121 for automated skin lesion classification and localization. The proposed architecture exploits SepConv2D for efficient local feature extraction, ViT for modelling global contextual relationships through self-attention, and DenseNet121 for enhanced feature propagation and semantic representation. The complementary features are fused to improve discriminative learning, while Gradient-weighted Class Activation Mapping (Grad-CAM) is incorporated to provide visual explanations by highlighting clinically relevant lesion regions. The framework is evaluated using the ISIC-2019 and HAM10000 benchmark datasets under identical experimental settings. Experimental results demonstrate an overall classification accuracy of 99.94%, with corresponding precision, recall, and F1-score of 99.94%, while maintaining competitive computational complexity in terms of model parameters, MACs, and FLOPs. Comparative evaluation against recent state-of-the-art methods indicates that the proposed framework consistently achieves superior predictive performance and enhanced interpretability. These findings demonstrate that the proposed architecture can serve as an efficient and trustworthy computer-aided diagnostic tool for supporting dermatologists in clinical decision-making and facilitating the adoption of explainable artificial intelligence in healthcare applications.