چکیده:
Mild Cognitive Impairment (MCI) is the stage that happens before Alzheimer's Disease (AD) and there is a high risk of progression to AD. However, this progression is not guaranteed and there is a chance of staying at this stage. In this study, we aim to diagnose possible AD progression among MCI subjects from a combination of resting-state functional Magnetic Resonance Imaging (fMRI), clinical assessment, and demographic information for starting treatments in case of progression or reducing medical expenses in case of future stability. For this work, we have used Deep Learning methods called three-dimensional Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM). The models were developed using 266 samples from 81 MCI subjects over an average of five years between baseline and the last timepoint. Results showed, the best validation scores belonged to the CNN-LSTM model after integrating with clinical attributes based on accuracy of 92.47%. Consequently, our proposed algorithm demonstrated high performance in predicting MCI to AD progression, indicating the potential of deep learning approaches in processing fMRI data and the efficiency of integrating data types.
| بازنشر اطلاعات | |
 |
این مقاله تحت شرایط Creative Commons Attribution-NonCommercial 4.0 International License قابل بازنشر است. |
