RT Journal Article
T1 Artificial Intelligence for Alzheimer's disease diagnosis through T1-weighted MRI: A systematic review
A1 Basanta Torres, Sara
A1 Rivas Fernández, Miguel Ángel
A1 Galdo Álvarez, Santiago
K1 Alzheimer's disease
K1 Magnetic resonance imaging
K1 T1-weighted
K1 Machine learning
K1 Neural networks
K1 Artificial Intelligence
AB Alzheimer's disease (AD) is a leading cause of dementia worldwide, characterized by heterogeneous neuropathological changes and progressive cognitive decline. Despite the numerous studies, there are still no effective treatments beyond those that aim to slow progression and compensate the impairment. Neuroimaging techniques provide a comprehensive view of brain changes, with magnetic resonance imaging (MRI) playing a key role due to its non-invasive nature and wide availability. The T1-weighted MRI sequence is frequently used due to its prevalence in most MRI protocols, generating large datasets, ideal for artificial intelligence (AI) applications. AI, particularly machine learning (ML) and deep learning (DL) techniques, has been increasingly utilized to model these datasets and classify individuals along the AD continuum. This systematic review evaluates studies using AI to classify more than two stages of AD based on T1-weighted MRI data. Convolutional neural networks (CNNs) are the most widely applied, achieving an average classification accuracy of 85.93 % (range: 51.80–100 %; median: 87.70 %). These good results are due to CNNs' ability to extract hierarchical features directly from raw imaging data, reducing the need for extensive preprocessing. Non-convolutional neural networks and traditional ML approaches also demonstrated strong performance, with mean accuracies of 82.50 % (range: 57.61–99.38 %; median: 86.67 %) and 84.22 % (range: 33–99.10 %; median: 87.75 %), respectively, underscoring importance of input data selection. Despite promising outcomes, challenges remain, including methodological heterogeneity, overfitting risks, and a reliance on the ADNI database, which limits dataset diversity. Addressing these limitations is critical to advancing AI's clinical application for early detection, improved classification, and enhanced patient outcomes.
PB Elsevier
YR 2025
FD 2025-09-05
LK https://hdl.handle.net/10347/42889
UL https://hdl.handle.net/10347/42889
LA eng
NO Computers in Biology and Medicine Volume 197, Part A, October 2025, 111028
NO This work was supported by grants from the Spanish Government, Ministerio de Economía y Competitividad (PID2020-114521RB-C21/C22) and the Galician Government, Axudas para a Consolidación e Estruturación de Unidades de Investigación Competitivas do Sistema Universitario de Galicia: GRC (ED431C-2021/04). All with ERDF/FEDER funds. The first author is grateful for a pre-doctoral fellowship awarded by the Galician Government (Xunta de Galicia, Consellería de Cultura, Educación, Formación Profesional e Universidades, Ref. ED481A).
DS Minerva
RD 24 abr 2026