Authors:
Mojdeh Rastgoo
1
;
Guillaume Lemaitre
1
;
Joan Massich
2
;
Olivier Morel
2
;
Franck Marzani
2
;
Rafael Garcia
3
and
Fabrice Meriaudeau
2
Affiliations:
1
Université de Bourgogne Franche-Comté and Universitat de Girona, France
;
2
Université de Bourgogne Franche-Comté, France
;
3
Universitat de Girona, Spain
Keyword(s):
Imbalanced, Classification, Melanoma, Dermoscopy.
Related
Ontology
Subjects/Areas/Topics:
Bioimaging
;
Biomedical Engineering
;
Feature Recognition and Extraction Methods
;
Medical Imaging and Diagnosis
Abstract:
Malignant melanoma is the most dangerous type of skin cancer, yet melanoma is the most treatable kind of cancer when diagnosed at an early stage. In this regard, Computer-Aided Diagnosis systems based on machine learning have been developed to discern melanoma lesions from benign and dysplastic nevi in dermoscopic images. Similar to a large range of real world applications encountered in machine learning, melanoma classification faces the challenge of imbalanced data, where the percentage of melanoma cases in comparison with benign and dysplastic cases is far less. This article analyzes the impact of data balancing strategies at the training step. Subsequently, Over-Sampling (OS) and Under-Sampling (US) are extensively compared in both feature and data space, revealing that NearMiss-2 (NM2) outperform other methods achieving Sensitivity (SE) and Specificity (SP) of 91.2% and 81.7%, respectively. More generally, the reported results highlight that methods based on US or combination of
OS and US in feature space outperform the others.
(More)