An efficient deep learning algorithm for early Alzheimer’s disease stage identification using CNN compared with mobilenet

This study is being conducted with the intention of determining whether or not a distinct convolutional neural network (CNN) methodology is much more accurate than a MobileNet method when it comes to diagnosing Alzheimer’s disease (AD). Materials and methods: The dataset that was obtained from the ADNI database needs to go through a number of processes that involve the processing of pictures and the extraction of features. For the purpose of making a prediction regarding Alzheimer’s disease (AD), this study utilized a total of 26 participants, 13 of whom were comprised of each of the two groups, a G-power of 0.8, alpha and beta values of 0.05 and 0.2, and a confidence interval of 95%. The innovative Convolutional Neural Network (CNN) for Alzheimer’s disease can be identified in magnetic resonance imaging (MRI) scans by employing a MobileNet model and a classifier with a large sample size (N=13). This allows for the detection of the disease. Results:With an amazing accuracy rate of 94.65%, the innovative convolutional neural network (CNN) classifier exceeds the MobileNet model in terms of performance. Discussion and conclusion:-In the investigation, the setting of a significance threshold of p=0.001 (p<0.05) confirmed that there was a statistically significant difference between the groups that were being tested.A considerable improvement in accuracy of 83.43% can be observed between the MobileNet model and the newly developed convolutional neural network (CNN) image classifier for Alzheimer’s disease (MRI).