Systematic literature review of dermoscopic pigmented skin lesions classification using convolutional neural network (CNN)

• Published in: International journal of advances in intelligent informatics Vol. 9; no. 3; pp. 363 - 382
• Main Authors: Nugroho, Erwin Setyo, Ardiyanto, Igi, Nugroho, Hanung Adi
• Format: Journal Article
• Language: English
• Published: Yogyakarta Universitas Ahmad Dahlan 01.11.2023
• Subjects: Artificial neural networks; Classification; convolutional neural network; Datasets; dermoscopy; Lesions; Literature reviews; melanoma; Mortality; Neural networks; Online data bases; Performance evaluation; pigmented skin lesion; Skin cancer
• ISSN: 2442-6571; 2442-6571
• DOI: 10.26555/ijain.v9i3.961

The occurrence of pigmented skin lesions (PSL), including melanoma, are rising, and early detection is crucial for reducing mortality. To assist Pigmented skin lesions, including melanoma, are rising, and early detection is crucial in reducing mortality. To aid dermatologists in early detection, computational techniques have been developed. This research conducted a systematic literature review (SLR) to identify research goals, datasets, methodologies, and performance evaluation methods used in categorizing dermoscopic lesions. This review focuses on using convolutional neural networks (CNNs) in analyzing PSL. Based on specific inclusion and exclusion criteria, the review included 54 primary studies published on Scopus and PubMed between 2018 and 2022. The results showed that ResNet and self-developed CNN were used in 22% of the studies, followed by Ensemble at 20% and DenseNet at 9%. Public datasets such as ISIC 2019 were predominantly used, and 85% of the classifiers used were softmax. The findings suggest that the input, architecture, and output/feature modifications can enhance the model's performance, although improving sensitivity in multiclass classification remains a challenge. While there is no specific model approach to solve the problem in this area, we recommend simultaneously modifying the three clusters to improve the model's performance.