Early prediction of Schizophrenia using FMRI and Deep learning

Schizophrenia is a severe and chronic mental disorder that significantly impacts cognitive, emotional,
and behavioral functioning. Early diagnosis is critical for effective intervention and improved long-term
outcomes. Functional Magnetic Resonance Imaging (fMRI) offers valuable insights into brain activity
and connectivity patterns that can serve as biomarkers for the early detection of schizophrenia. This
project aims to develop a deep learning-based framework for the early prediction of schizophrenia using fMRI data.
The proposed approach involves preprocessing raw fMRI data to extract meaningful features that capture both spatial and temporal brain dynamics. Advanced deep learning architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and hybrid models are employed to learn complex patterns associated with schizophrenia. Feature extraction and dimensionality reduction techniques, including Principal Component Analysis (PCA) and Autoencoders, are applied to enhance model performance and reduce overfitting.