| Journal: | Latin-American Journal of Computing (LAJC) |
| Database: | |
| System number: | 000565155 |
| ISSN: | 1390-9134 |
| Authors: | Ucañay Barreto, Werner Shtaniklao1 Coral Ygnacio, Marco Antonio1 |
| Institutions: | 1Universidad Católica Sedes Sapientiae, |
| Year: | 2024 |
| Volumen: | 11 |
| Number: | 1 |
| Pages: | 90-105 |
| Country: | Ecuador |
| Language: | Español |
| English abstract | Early diagnosis of Alzheimer's disease is essential to provide timely treatment to patients. In this regard, a system for diagnosing Alzheimer's disease based on magnetic resonance imaging and utilizing a convolutional neural network algorithm called VGG16, has been developed. Magnetic resonance images of patients with and without Alzheimer's disease were collected and processed. These images were used to train the algorithm, which learned to identify and associate patterns with the disease. Subsequently, tests were performed with a set of unseen images to evaluate the diagnostic ability of the system. Through the analysis of magnetic resonance images, the VGG16 algorithm has shown a capacity of over 82% to correctly recognize these signs. These results validate the effectiveness of the artificial intelligence-based approach for diagnosing Alzheimer's disease. |
| Spanish abstract | El diagnóstico temprano del Alzheimer es fundamental para brindar un tratamiento oportuno a los pacientes. En este sentido se ha desarrollado un sistema de diagnóstico del Alzheimer basado en imágenes de resonancia magnética que utiliza un algoritmo de redes neuronales convolucionales denominado VGG16. Se recopilaron y procesaron imágenes de resonancia magnética de pacientes con y sin Alzheimer. Estas imágenes se utilizaron para entrenar al algoritmo, el cual aprendió a identificar y asociar patrones con la enfermedad. Posteriormente, se realizaron pruebas con un conjunto de imágenes no vistas para evaluar la capacidad de diagnóstico del sistema. Mediante el análisis de las imágenes de resonancia magnética, el algoritmo VGG16 ha demostrado una capacidad superior al 82% para reconocer correctamente dichos signos. Estos resultados validan la efectividad del enfoque basado en inteligencia artificial para el diagnóstico del Alzheimer. |
| Keyword: | Imágenes de resonancia magnética, VGG16, detección temprana, Diagnóstico del Alzheimer |
| Keyword: | Alzheimer's diagnosis, Magnetic resonance imaging, VGG16, Early detection |
| Full text: | Texto completo (Ver PDF) Texto completo (Ver HTML) |
