Prince Mohammad Bin Fahd University

Khaled S Fawagreh

Muhammad Attique Khan

A computer-implemented system, and method for classifying Parkinson's Disease (PD) from magnetic resonance imaging (MRI) data. The method includes receiving an MRI image. The method includes processing the MRI image through a C3BAM-Net convolutional neural network (CNN) architecture to obtain a plurality of attention-enhanced feature maps. The method includes classifying the input MRI image into one of a plurality of the PD categories based on the plurality of attention-enhanced feature maps. Where the C3BAM-Net CNN includes a plurality of convolutional layers, a plurality of Rectified Linear Unit (ReLU) activations, a plurality of max pooling layers, a plurality of Convolutional Block Attention Modules (CBAMs), a flattening layer, and a plurality of dense layers. The method includes each CBAM of the plurality of CBAMs includes a Channel Attention Module (CAM) and a Spatial Attention Module (SAM) arranged sequentially.

Parkinson disease prediction using magnetic resonance imaging (MRI) based on a convolutional block attention module and explainable ai architecture (C3BAM-XAI) architecture

Growing community of inventors

Dhahran, Saudi Arabia

Khaled S Fawagreh