Predicting Alzheimer’s Disease Using Deep Learning Artificial Intelligence Together with a Pre-Trained VGG19 and Inception_v3 Models

• Published in: Informatica economica Vol. 28; no. 2/2024; pp. 17 - 34
• Main Authors: TEODORESCU, Paul, OVREIU, Silvia, ZAMFIR, Madalina, TIRLEA, Cristian
• Format: Journal Article
• Language: English
• Published: Bucharest INFOREC Association 30-06-2024; Inforec Association
• Subjects: Accuracy; Algorithms; Alzheimer's disease; Artificial intelligence; Artificial neural networks; Brain research; convolutional; Datasets; Deep learning; demented; Experiments; feature extractor; imagenet; Machine learning; Magnetic resonance imaging; matrix; Medical imaging; Medical research; mri images; Neural networks; pre-trained; Python; R&D; Research & development; target
• ISSN: 1453-1305; 1842-8088
• DOI: 10.24818/issn14531305/28.2.2024.02

This paper presents two experiments in which, using artificial intelligence (specifically Deep Learning with convolutional neural networks), we were able to predict Alzheimer's disease based on MRI images. In order to have better results and to minimize the computational effort in the laboratory, two pre-trained AI models were used, models trained previously on more than a million images from the ImageNet database (which provide tens of millions of clean, labelled and sorted images). The top-layers of the models were trained, for our specific task of Alzheimer s prediction, with 500public MRI images from Kaggle, an online community of data scientists and machine learning engineers and a subsidiary of Google. In this paper we describe the code used in the laboratory for the specific task.