Clasificación de enfermedades en la caja torácica por medio de radiografías
The early detection of diseases can be decisive for the life of a person. On medical environment the x-ray are used commonly for diagnosis of illness because the presence of patterns, spots and another kind of visual signals. This document shows the development of models with convolutionals networks...
- Autores:
-
Berón Rivera, Julián David
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2020
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/51552
- Acceso en línea:
- http://hdl.handle.net/1992/51552
- Palabra clave:
- Radiología médica
Redes neuronales convolucionales
Aprendizaje automático (Inteligencia artificial)
Tórax
Ingeniería
- Rights
- openAccess
- License
- https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
| Summary: | The early detection of diseases can be decisive for the life of a person. On medical environment the x-ray are used commonly for diagnosis of illness because the presence of patterns, spots and another kind of visual signals. This document shows the development of models with convolutionals networks: VGG16 and VGG19, used for creation of a binary classificator with an accuracy of 95% and a multiclass classificator with an accuracy of 85%, that catalog 4 different illness. |
|---|