Welcome to the InfoSci Platform
Reference Hub2
Computer-Aided Diagnosis for Spitzoid Lesions Classification Using Artificial Intelligence Techniques

Computer-Aided Diagnosis for Spitzoid Lesions Classification Using Artificial Intelligence Techniques

Abir Belaala, Labib Sadek Terrissa, Noureddine Zerhouni, Christine Devalland
Copyright: © 2021 |Volume: 16 |Issue: 1 |Pages: 22
ISSN: 1555-3396|EISSN: 1555-340X|EISBN13: 9781799859789|DOI: 10.4018/IJHISI.2021010102
Cite Article Cite Article

MLA

Belaala, Abir, et al. "Computer-Aided Diagnosis for Spitzoid Lesions Classification Using Artificial Intelligence Techniques." IJHISI vol.16, no.1 2021: pp.16-37. http://doi.org/10.4018/IJHISI.2021010102

APA

Belaala, A., Terrissa, L. S., Zerhouni, N., & Devalland, C. (2021). Computer-Aided Diagnosis for Spitzoid Lesions Classification Using Artificial Intelligence Techniques. International Journal of Healthcare Information Systems and Informatics (IJHISI), 16(1), 16-37. http://doi.org/10.4018/IJHISI.2021010102

Chicago

Belaala, Abir, et al. "Computer-Aided Diagnosis for Spitzoid Lesions Classification Using Artificial Intelligence Techniques," International Journal of Healthcare Information Systems and Informatics (IJHISI) 16, no.1: 16-37. http://doi.org/10.4018/IJHISI.2021010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Spitzoid lesions may be largely categorized into Spitz Nevus, Atypical Spitz Tumors, and Spitz Melanomas. Classifying a lesion precisely as Atypical Spitz Tumors or AST is challenging and often requires the integration of clinical, histological, and immunohistochemical features to differentiate AST from regular Spitz Nevus and malignant Spitz Melanomas. Specifically, this paper aims to test several artificial intelligence techniques so as to build a computer-aided diagnosis system. A proposed three-phase approach is being implemented. In Phase 1, collected data are preprocessed with an effective SMOTE-based method being implemented to treat the imbalance data problem. Then, a feature selection mechanism using genetic algorithm (GA) is applied in Phase 2. Finally, in Phase 3, a 10-fold cross-validation method is used to compare the performance of seven machine-learning algorithms for classification. Results obtained with SMOTE-Multilayer Perceptron with GA-based 14 features show the highest classification accuracy, specificity (0.98), and a sensitivity of 0.99.