A deep learning based convolutional neural network model with VGG16 feature extractor for the detection of Alzheimer Disease using MRI scans

• DOI: 10.1016/j.measen.2022.100506
• Publication Date: 2022-10-05T16:41:31Z
• Authors: Shagun Sharma; Kalpna Guleria; Sunita Tiwari; Sushil Kumar
• Keywords: Extractor

Alzheimer's disease (AD) is one of the most prevalent types dementia, which primarily affects people over age 60. In clinical practice, it a challenging task to identify AD in its early stages, and there are currently very few reliable diagnostic systems available for identification. Additionally, studies medications have high risk failure, currently, no confirmed cure. There various stages AD: mild demented, mild, moderate. It these due demented case worsens results complete health loss along with weak memory makes unable perform daily tasks without assistance others. Early identification cases can help patients guide additional medical care stop disease's progression avoid brain damage. Recently, has been substantial amount interest applying deep learning (DL) recognition. The limitations algorithms that they cannot detect changes networks functional working networks. However, growth, scientists researchers striving build methods by using MRI images. this article, diagnoses AD, two datasets containing 6400 6330 images used, DL algorithm utilized neural network classifier VGG16 feature extractor diagnosis outcome form accuracy, precision, recall, AUC F1-score as (90.4%, 0.905, 0.904, 0.969, 0.904), (71.1%, 0.71, 0.711, 0.85, 0.71) dataset 1 2, respectively. Furthermore, compared previous studies, concluded proposed model performs better. Lastly, article applicable machine (ML) approaches be study stage