Skin Cancer Disease Detection Using Two-Stream Hybrid Attention-Based Deep Learning Model

Skin cancer is a serious health issue that requires early detection and treatment for effective management. Timely and accurate evaluation of skin lesions is crucial, as delays can lead to more severe outcomes. However, identifying skin lesions accurately can be challenging due to differences in color, shape, and the various types of imaging equipment used for diagnosis. While recent studies have demonstrated the potential of ensemble convolutional neural networks (CNNs) for early diagnosis of skin disorders, these models are often too large and inefficient for processing contextual information. Although lightweight networks like MobileNetV3 and EfficientNet have been developed to reduce parameters and enable deep neural networks on mobile devices, their performance is limited by inadequate feature representation depth. To mitigate these limitations, we proposed a hybrid attention dual-stream deep learning model for skin lesion detection. With just one training loss, this model preprocesses the input images and uses two branches, each of which extracts local and global features using multi-stage and multi-branch attention techniques. The first branch processes the original image using a convolutional layer integrated with three novel attention modules: Enhanced Separable Depthwise Convolution (SCAttn), stage attention, and branch attention. The second branch utilizes Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the input image, improving local contrast and revealing finer details. The first branch processes the CLAHE-enhanced image using a similar feature extraction pipeline. The integration of CLAHE with SCAttn modules leverages enhanced local contrast to capture more nuanced features while maintaining computational efficiency. A classification module receives the concatenated hierarchical characteristics that were taken from both branches. Utilizing the PAD2020 and ISIC 2019 datasets, we assessed the proposed model and obtained an accuracy rate of 98.59%, of the PAD2020 surpassing the state-of-the-art performance by 2% and stable performance accuracy for the ISIC 2019 dataset. This illustrates how well the model can integrate several attention mechanisms and feature enhancement methods, providing a reliable and effective means of detecting skin cancer.