Skip to Main content Skip to Navigation
New interface
Conference papers

A Study on the Fusion of Pixels and Patient Metadata in CNN-Based Classification of Skin Lesion Images

Abstract : 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.
Complete list of metadata
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, November 4, 2021 - 3:57:36 PM
Last modification on : Friday, November 5, 2021 - 3:58:03 AM
Long-term archiving on: : Saturday, February 5, 2022 - 7:08:57 PM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2023-01-01

Please log in to resquest access to the document


Distributed under a Creative Commons Attribution 4.0 International License



Fabrizio Nunnari, Chirag Bhuvaneshwara, Abraham Obinwanne Ezema, Daniel Sonntag. A Study on the Fusion of Pixels and Patient Metadata in CNN-Based Classification of Skin Lesion Images. 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2020, Dublin, Ireland. pp.191-208, ⟨10.1007/978-3-030-57321-8_11⟩. ⟨hal-03414735⟩



Record views