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.

The network connection of the surahs of the Qur'an is all about the structural and content relationship between the surahs. In this style of studies, it deals with finding types of connections between non-adjacent but similar surahs, which are known as "the same group". Although one surah may be in the same group with different surahs in various ways, this itself not only does not pose a challenge to the process of these studies, but can also indicate the high potential of the Qur'an in meaning. This study examines the connections of Surah Fath with Surah Nuh, Qadr, and Kawthar, all of which begin with the expression "Ina (meaning indeed)", using a descriptive-analytical method. The findings of the study suggest that there are different types of structural and content connections between these surahs, including good beginning, saj’e, common tone and rhythm, common themes and purpose and they have similar verses in terms of form and content, which strengthens their network connection. Some of the findings of this study are providing the context for better understanding of these surahs of the same group, the better recognition and explanation of the textual structure of the Qur'an, providing the context for expanding the methods of interpreting the Qur'an to the Qur'an and finding similarities in the verses

By using Berwald connection, we show that there are linear connections Ñ which are projectively equivalent and belong to the same projective structure on TM. We found a condition for the geodesics of the Berwald connection under which Ñ is complete.