Identificador persistente para citar o vincular este elemento:
http://hdl.handle.net/10662/19917
Títulos: | Eigenloss: combined PCA-based loss function for polyp segmentation |
Autores/as: | Sánchez Peralta, Luisa Fernanda Picón Ruiz, Artzai Antequera Barroso, Juan Antonio Ortega Morán, Juan Francisco Sánchez Margallo, Francisco Miguel Pagador Carrasco, José Blas |
Palabras clave: | Deep learning;Loss functions;Principal component analysis;Polyp segmentation;Aprendizaje profundo;Funciones de pérdida;Análisis de componentes principales;Segmentación de polípos |
Fecha de publicación: | 2020 |
Editor/a: | MDPI |
Resumen: | Colorectal cancer is one of the leading cancer death causes worldwide, but its early diagnosis highly improves the survival rates. The success of deep learning has also benefited this clinical field. When training a deep learning model, it is optimized based on the selected loss function. In this work, we consider two networks (U-Net and LinkNet) and two backbones (VGG-16 and Densnet121). We analyzed the influence of seven loss functions and used a principal component analysis (PCA) to determine whether the PCA-based decomposition allows for the defining of the coe cients of a non-redundant primal loss function that can outperform the individual loss functions and di erent linear combinations. The eigenloss is defined as a linear combination of the individual losses using the elements of the eigenvector as coe cients. Empirical results show that the proposed eigenloss improves the general performance of individual loss functions and outperforms other linear combinations when Linknet is used, showing potential for its application in polyp segmentation problems. |
URI: | http://hdl.handle.net/10662/19917 |
DOI: | 10.3390/math8081316 |
Colección: | DDCEM - Artículos |
Archivos
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
math8081316.pdf | 1,22 MB | Adobe PDF | Descargar |
Este elemento está sujeto a una licencia Licencia Creative Commons