A Study on the Fusion of Pixels and Patient Metadata in CNN-Based Classification of Skin Lesion Images
Fiche du document
25 août 2020
- handle: 10670/1.7ukjm6
- hal: hal-03414735
- doi: 10.1007/978-3-030-57321-8_11
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-030-57321-8_11
http://creativecommons.org/licenses/by/ , info:eu-repo/semantics/OpenAccess
Mots-clés
Skin lesion classification Convolutional neural network Machine learning Patient metadata Data fusionSujets proches
Meta-data Data about dataCiter ce document
Fabrizio Nunnari et al., « A Study on the Fusion of Pixels and Patient Metadata in CNN-Based Classification of Skin Lesion Images », HAL-SHS : sciences de l'information, de la communication et des bibliothèques, ID : 10.1007/978-3-030-57321-8_11
Métriques
Partage / Export
Résumé
We present a study on the fusion of pixel data and patient metadata (age, gender, and body location) for improving the classification of skin lesion images. The experiments have been conducted with the ISIC 2019 skin lesion classification challenge data set. Taking two plain convolutional neural networks (CNNs) as a baseline, metadata are merged using either non-neural machine learning methods (tree-based and support vector machines) or shallow neural networks. Results show that shallow neural networks outperform other approaches in all overall evaluation measures. However, despite the increase in the classification accuracy (up to +19.1%), interestingly, the average per-class sensitivity decreases in three out of four cases for CNNs, thus suggesting that using metadata penalizes the prediction accuracy for lower represented classes. A study on the patient metadata shows that age is the most useful metadatum as a decision criterion, followed by body location and gender.