Assessing a Proposed Dynamic Ratio in Dataset Class Imbalance with GAN's Generated Melanoma Images
- 18 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 500-503
Abstract
Skin cancer cases has increased in the last years and melanoma cases have a high rank in the incidence of mortality. However class imbalance in melanoma dataset produces a challenge for researcher to tackle a classification model. This work proposes the use of a dynamic ratio in dataset imbalance with the addition of synthetic image generation by Progressive Growth of Generative Adversarial Networks (PGGAN) and the assessment of this ratio problem. Our methodology involved the preprocessing of the ISIC 2019 challenge dataset, selection between PGGAN and Wasserstein GAN with Gradient Penalty (WGAN-GP) for image generation, dynamic ratio addition in original dataset, use of Resnet 50 pretrained model and evaluation of classification metrics. Our study demonstrated selected ratios that improved precision, recall and F1-score metrics on melanoma detection against original dataset with traditional image transformations.Keywords
This publication has 20 references indexed in Scilit:
- Early‐Stage Melanoma Cancer Diagnosis Framework for Imbalanced Data From Dermoscopic ImagesMicroscopy Research and Technique, 2024
- SkinDiff: A Novel Data Synthesis Method Based on Latent Diffusion Model for Skin Lesion Segmentation2024
- Conditional adversarial segmentation and deep learning approach for skin lesion sub-typing from dermoscopic imagesNeural Computing and Applications, 2024
- A Novel framework of Adaptive fuzzy-GLCM Segmentation and Fuzzy with Capsules Network (F-CapsNet) ClassificationNeural Computing and Applications, 2023
- Advanced Skin Cancer Detection Using Deep Learning2023
- Characteristics of publicly available skin cancer image datasets: a systematic reviewThe Lancet Digital Health, 2022
- Data augmentation for skin lesion using self-attention based progressive generative adversarial networkExpert Systems with Applications, 2021
- A GAN-based image synthesis method for skin lesion classificationComputer Methods and Programs in Biomedicine, 2020
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Dullrazor®: A software approach to hair removal from imagesComputers in Biology and Medicine, 1997