Desarrollo de software biomédico mediante modelos deep learning para la detección de tumores pulmonares en la aplicación de procesamiento de imágenes espectrales para el departamento médico de la Universidad Técnica de Cotopaxi Extensión La Maná.
The implementation and development of models based on Deep Learning applied in the biomedical field is obtaining success in several aspects of medicine, this includes the detection of diseases in humans, for this scope a correct evaluation of the processes is required. However, there is a wide varie...
Guardat en:
| Autor principal: | |
|---|---|
| Altres autors: | |
| Format: | bachelorThesis |
| Idioma: | spa |
| Publicat: |
2022
|
| Matèries: | |
| Accés en línia: | http://repositorio.utc.edu.ec/handle/27000/8438 |
| Etiquetes: |
Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
Afegir etiqueta | Sumari: | The implementation and development of models based on Deep Learning applied in the biomedical field is obtaining success in several aspects of medicine, this includes the detection of diseases in humans, for this scope a correct evaluation of the processes is required. However, there is a wide variety of diseases that cause cancer; one of them is the carcinogenic infection of the pulmonary alveoli, which reproduces with greater intensity in the pulmonary organic structure when there is a large concentration of these cancer cells. The present research aims to determine the detection of lung cancer through its positioning through DICOM (Image Transmission Standard) images. The development of biomedical software with the deployment of deep learning models allowed cancer detection in the evaluation of the diagnosis, applying the use of spatial image metrics as an image exchange format in obtaining information and special treatment through screening and application of gamma in grayscales; complementing with the use of MATLAB GUI environments based on the calculation programming language, thus allowing to implement artificial models and spectra of computerized artificial vision as complements in the treatment of each image, therefore obtaining the expected results based on the positioning and detection of cancer in the lungs. |
|---|