فهرست نشریات علمی دسترسی آزاد ایران

Objectives In the field of medical and dental image analysis, the development of advanced deep learning architectures for precise classification tasks has become essential. The present study aims to introduce an innovative Attention-based Residual Connection Convolutional Neural Network (ARN-CNN) designed for accurate classification of medical images using the Med-MNIST (Medical Modified National Institute of Standards and Technology) dataset. Methods Attention mechanisms and residual connections were integrated into the ARN-CNN model to enhance feature extraction and prediction accuracy. The model's performance was evaluated through a comparative analysis with state-of-the-art CNN architectures on the challenging MNIST medical dataset, based on key metrics, including accuracy, precision, recall, and F1 score. Results The ARN-CNN model achieves a classification accuracy of 99.96% and a loss of 0.0037. These results showcase the superior performance of ARN-CNN in improving classification accuracy and its potential for enhancing medical image analysis. Conclusion The study demonstrates the crucial role that residual connections and attention processes play in capturing intricate details and maximizing information flow in the network. It highlights the potential of deep learning techniques for revolutionizing medical image analysis and laying the foundation for future investigation into automated medical and dental diagnosis and treatment in healthcare.