Detecting Mild Cognitive Impairment to Alzheimer's Disease Progression by fMRI Using Convolutional Neural Network and Long-short Term Memory.

Introduction: Mild cognitive impairment (MCI) is the stage that occurs 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 remaining at this stage. This study aimed to diagnose possible AD progression among patients with MCI using 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. Methods: Deep learning (DL) methods, including three-dimensional convolutional neural networks (CNN) and long short-term memory (LSTM) networks, were used in this study. The models were developed using 266 samples from 81 MCI subjects, with an average of five years between baseline and the last timepoint. Results: The results showed that the best validation scores were achieved by the CNN-LSTM model after integrating clinical attributes, with an accuracy of 92.47%. Conclusion: The proposed algorithm demonstrated high performance in predicting MCI-to-AD progression, indicating the potential of DL approaches for processing fMRI data and the efficiency of data type integration.