Melanoma Classification
ABSTRACT : We presented our solution for the SIIM-ISIC melanoma classification challenge. This is a multi-class multi-modal classification model using images and metadata and, we tested both binary and multi-class image-only models and a binary multi-modal model. The keys to success for our solution...
- Autores:
-
Gómez Giraldo, Oscar Nicolás
Arbeláez López, Néstor Iván
- Tipo de recurso:
- Tesis
- Fecha de publicación:
- 2021
- Institución:
- Universidad de Antioquia
- Repositorio:
- Repositorio UdeA
- Idioma:
- eng
- OAI Identifier:
- oai:bibliotecadigital.udea.edu.co:10495/24997
- Acceso en línea:
- http://hdl.handle.net/10495/24997
- Palabra clave:
- Análisis de datos
Data analysis
Procesamiento de datos
Data processing
Melanoma
Melanoma
Multi-modal
Data augmentation
http://aims.fao.org/aos/agrovoc/c_4713
http://vocabularies.unesco.org/thesaurus/concept2214
http://vocabularies.unesco.org/thesaurus/concept522
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-sa/2.5/co/
| Summary: | ABSTRACT : We presented our solution for the SIIM-ISIC melanoma classification challenge. This is a multi-class multi-modal classification model using images and metadata and, we tested both binary and multi-class image-only models and a binary multi-modal model. The keys to success for our solution were the selection of the target variable, using the available metadata, and the data augmentation strategy. Achieving AUC values of 0.95 and F1 of 0.71 for the validation data. |
|---|