Automated Medical Diagnosis of Alzheimer´s Disease Using an Efficient Net Convolutional Neural Network.

Autor: Agarwal D; Department of Signal Theory and Communications and Telematics Engineering, University of Valladolid, Paseo de Belén 15, 47011, Valladolid, Spain. deevyankar.agarwal@estudiantes.uva.es., Berbís MÁ; Hospital San Juan de Dios, HT Médica, Avda Brillante 106, 14012, Córdoba, Spain., Luna A; MRI Unit, Radiology Department, HT Médica, Carmelo Torres No. 2, 23007, Jaén, Spain., Lipari V; European Atlantic University, Isabel Torres 21, 39011, Santander, Spain., Ballester JB; European Atlantic University, Isabel Torres 21, 39011, Santander, Spain., de la Torre-Díez I; Department of Signal Theory and Communications and Telematics Engineering, University of Valladolid, Paseo de Belén 15, 47011, Valladolid, Spain.
Jazyk: angličtina
Zdroj: Journal of medical systems [J Med Syst] 2023 May 02; Vol. 47 (1), pp. 57. Date of Electronic Publication: 2023 May 02.
DOI: 10.1007/s10916-023-01941-4
Abstrakt: Alzheimer's disease (AD) poses an enormous challenge to modern healthcare. Since 2017, researchers have been using deep learning (DL) models for the early detection of AD using neuroimaging biomarkers. In this paper, we implement the EfficietNet-b0 convolutional neural network (CNN) with a novel approach-"fusion of end-to-end and transfer learning"-to classify different stages of AD. 245 T1W MRI scans of cognitively normal (CN) subjects, 229 scans of AD subjects, and 229 scans of subjects with stable mild cognitive impairment (sMCI) were employed. Each scan was preprocessed using a standard pipeline. The proposed models were trained and evaluated using preprocessed scans. For the sMCI vs. AD classification task we obtained 95.29% accuracy and 95.35% area under the curve (AUC) for model training and 93.10% accuracy and 93.00% AUC for model testing. For the multiclass AD vs. CN vs. sMCI classification task we obtained 85.66% accuracy and 86% AUC for model training and 87.38% accuracy and 88.00% AUC for model testing. Based on our experimental results, we conclude that CNN-based DL models can be used to analyze complicated MRI scan features in clinical settings.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz: