Optimizing Vascular Dementia:A Deep Learning Framework Using CNN and RNN on MRI Data

Vascular Dementia (VaD) is a prevalent form of dementia characterized by cognitive decline due to cerebrovascular disease. Accurate and early diagnosis is crucial for effective management and treatment. This project aims to develop a hybrid model that leverages Convolutional Neural Networks (CNNs) for processing image data (e.g., MRI scans) and Recurrent Neural Networks (RNNs) or other classifiers for structured data (e.g., patient history, blood pressure levels). By combining these two approaches, the model can exploit both spatial patterns in the images and temporal or structured patterns in the clinical data, leading to improved classification accuracy for Vascular Dementia. Vascular dementia (VaD) represents a significant cognitive decline linked to vascular issues in the brain, necessitating advanced diagnostic methods to enhance early detection and intervention. This project presents a novel deep learning framework that leverages Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to analyze MRI data for optimizing the diagnosis and understanding of VaD. The proposed framework integrates CNNs for feature extraction from MRI images, capturing spatial hierarchies of features, while RNNs are employed to model temporal sequences of brain changes over time, enabling a comprehensive analysis of disease progression. By utilizing a dataset of annotated MRI scans, the model is trained to classify stages of vascular dementia and predict cognitive decline based on MRI features