Eigenloss: Combined PCA-Based Loss Function for Polyp Segmentation: Combined PCA-based loss function for polyp segmentation

Sánchez-Peralta, Luisa F.Picón, ArtzaiAntequera-Barroso, Juan AntonioOrtega-Morán, Juan FranciscoSánchez-Margallo, Francisco M.Pagador, J. Blas2020-08Sánchez-Peralta , L F , Picón , A , Antequera-Barroso , J A , Ortega-Morán , J F , Sánchez-Margallo , F M & Pagador , J B 2020 , ' Eigenloss: Combined PCA-Based Loss Function for Polyp Segmentation : Combined PCA-based loss function for polyp segmentation ' , Mathematics , vol. 8 , no. 8 , 1316 , pp. 1316 . https://doi.org/10.3390/math80813162227-7390researchoutputwizard: 11556/963Publisher Copyright: © 2020 by the authors.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 coefficients of a non-redundant primal loss function that can outperform the individual loss functions and different linear combinations. The eigenloss is defined as a linear combination of the individual losses using the elements of the eigenvector as coefficients. 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.12067169enginfo:eu-repo/semantics/openAccessEigenloss: Combined PCA-Based Loss Function for Polyp Segmentation: Combined PCA-based loss function for polyp segmentationjournal article10.3390/math8081316Deep learningLoss functionsPrincipal component analysisPolyp segmentationDeep learningLoss functionsPrincipal component analysisPolyp segmentationComputer Science (miscellaneous)General MathematicsEngineering (miscellaneous)SDG 3 - Good Health and Well-beinghttp://www.scopus.com/inward/record.url?scp=85089736346&partnerID=8YFLogxK