Por favor, use este identificador para citar o enlazar este ítem:
https://rd.uffs.edu.br/handle/prefix/9168| Type: | Monografia |
| Título : | Applications of deep learning to measure skin lesions |
| Author: | Penha, Cecília de Oliveira |
| First advisor: | Feitosa, Samuel da Silva |
| metadata.dc.contributor.advisor-co1: | Lima, Julyane Felipette |
| Resume: | When treating skin lesions, accurate assessment of wound healing re- mains a challenge for health professionals. Precise estimation of the wound area is required to determine if the current approach is efficient or if a new interven- tion is required. This paper proposes a study on the ability of computer vision algorithms and deep learning networks to measure the size of dermatological wounds based on images. By employing an approach based on the U-Net archi- tecture, the study evaluates the model’s ability to segment wounds and provide area estimations. Results demonstrate that the proposed method can support decision making by health professionals by offering consistent measurements, contributing to faster and efficient patient care. |
| Palabras clave : | Aprendizagem profunda Inteligência artificial Doenças da pele e do tecido conjuntivo Ferimentos e lesões Processamento de imagens |
| Language: | por |
| Country: | Brasil |
| Editorial : | Universidade Federal da Fronteira Sul |
| Acronym of the institution: | UFFS |
| College, Institute or Department: | Campus Chapecó |
| Type of Access: | Acesso Aberto |
| URI : | https://rd.uffs.edu.br/handle/prefix/9168 |
| Fecha de publicación : | 2025 |
| Aparece en las colecciones: | Ciência da Computação |
Ficheros en este ítem:
| Fichero | Descripción | Tamaño | Formato | |
|---|---|---|---|---|
| PENHA.pdf | 1.34 MB | Adobe PDF | Visualizar/Abrir |
Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.