An effcient convolutional neural network for diagnosis of Alzheimer’s disease

Alzheimer’s disease (AD) is a neurodegenerative disease that causes many brain functions to weaken. Early AD diagnosis has attracted much research attention and immediate additional medical treatment to prevent its progression. Lately, the use of deep learning for the early identification of AD has generated much interest. This research develops a deep learning-based pipeline for accurate diagnosis and stratification of AD stages. The proposed analysis pipeline involves data pre-processing and developing Convolutional Neural Network (CNN), respectively. First, for making ۲D brain MRIs, ۳D MRI pictures are slid at a particular location and ready for classification,. After pre-processing, MobileNet was applied to ۴۰۰۰۰ MRI images of males and females aged ۵۰ to ۱۰۰. This dataset consists of two classes, people who do not have and have AD. The MobileNet adjusts the trade-off between accuracy and computational load with the help of depth-wise separable convolution. This separable convolution decomposes the convolution layer into depth-wise and pointwise convolution for computation. This feature causes the process to require less memory space and provides good quality and faster results compared to other large models such as VGG۱۶, inception, etc. In addition, the compact size of MobileNet makes it effective in medical issues, mobile, embedded vision applications, and IOT applications in many fields . The experimental analysis showed that the proposed model was able to achieve ۹۴.۶% accuracy in two-classes classification. The findings show that MobileNet can be used by doctors to classify and predict MRI images in neurodegenerative diseases such as AD

کلیدواژه ها:

Alzheimer’s disease ، Early diagnosis ، Convolutional neural network ، MobileNet ، MRI image