Intraclass Clustering-Based CNN Approach for Detection of Malignant Melanoma

Adrian D Bandy; Yannis Spyridis; Barbara Villarini; Vasileios Argyriou

doi:10.3390/s23020926

Intraclass Clustering-Based CNN Approach for Detection of Malignant Melanoma

Sensors (Basel). 2023 Jan 13;23(2):926. doi: 10.3390/s23020926.

Authors

Adrian D Bandy¹, Yannis Spyridis², Barbara Villarini³, Vasileios Argyriou¹

Affiliations

¹ Department of Networks and Digital Media, Kingston University, London KT1 1LQ, UK.
² Department of Electronic and Electrical Engineering, The University of Sheffield, Sheffield S1 3JD, UK.
³ School of Computer Science and Engineering, University of Westminster, London W1B 2HW, UK.

Abstract

This paper describes the process of developing a classification model for the effective detection of malignant melanoma, an aggressive type of cancer in skin lesions. Primary focus is given on fine-tuning and improving a state-of-the-art convolutional neural network (CNN) to obtain the optimal ROC-AUC score. The study investigates a variety of artificial intelligence (AI) clustering techniques to train the developed models on a combined dataset of images across data from the 2019 and 2020 IIM-ISIC Melanoma Classification Challenges. The models were evaluated using varying cross-fold validations, with the highest ROC-AUC reaching a score of 99.48%.

Keywords: CNN; classification; machine learning; malignant melanoma; medical image processing; skin lesion clustering.

MeSH terms

Artificial Intelligence*
Cluster Analysis
Dermoscopy / methods
Humans
Melanoma* / diagnosis
Melanoma, Cutaneous Malignant
Neural Networks, Computer

Grants and funding

This research received no external funding.