A Novel CNN Architecture for Alzheimer’s Disease Classification Using MRI Data

<p>Accurate categorization of Alzheimer’s disease is crucial for medical diagnosis<br />and the development of therapeutic strategies. Deep learning models<br />have demonstrated significant potential in this endeavor, however, they frequently<br />encounter difficulties because of the intricate and varied characteristics<br />of Alzheimer’s disease. To tackle this difficulty, we suggest a new and innovative<br />architecture for Alzheimer’s disease classification using MRI data. This<br />design is named Res-BRNet, and it combines deep residual and boundary-based<br />convolutional neural networks (CNNs). Res-BRNet utilizes a methodical fusion<br />of boundary-focused procedures within adapted spatial and residual blocks. The<br />spatial blocks retrieve information relating to uniformity, diversity, and boundaries<br />of Alzheimer’s disease, although the residual blocks successfully capture<br />texture differences at both local and global levels. We conducted a performance<br />assessment of Res-BRNe. The Res-BRNet surpassed conventional CNN models,<br />with outstanding levels of accuracy (99.22%). The findings indicate that<br />Res-BRNet has promise as a tool for classifying Alzheimer’s disease, with the<br />ability to enhance the precision and effectiveness of clinical diagnosis and treatment<br />planning.</p>