Pseudo Skin Image Generator (PSIG-Net): Ambiguity-free sample generation and outlier control for skin lesion classification

Isack Farady, Elvin Nur Furqon, Chia Chen Kuo, Yih Kuen Jan, Chih Yang Lin

Research output: Contribution to journalArticlepeer-review


Automated skin lesion classification in dermoscopic images is essential for improving diagnostic performance and reducing melanoma-related deaths. Although deep learning models for image classification have made breakthroughs in classifying skin lesions with intra-class and inter-class similarity issues, some ambiguous features of original samples in the training data still remain unresolved. The ambiguity of the samples remains a challenge for the model's performance on overlapping training data. To address these challenges, we introduce a novel framework called Pseudo Skin Image Generator network (PSIG-Net). The framework not only removes the ambiguous samples but also generates new pseudo samples to enrich the training data. Our approach targets the low-variation samples by generating new pseudo samples using a generative adversarial network (GAN) model that emulates the characteristics of the original respective classes. We regulate the pseudo samples through a series of processing stages to control their similarity and exclude outliers. We employ a Siamese-based network to control the distance between these pseudo samples and the original clusters. The assessment of density-based distance is utilized to select only the closest relationships with the original samples. Through a series of experiments, we observed the significant improvement of our proposed PSIG network, achieving competitive results when compared to similar methods on two challenging skin lesion datasets.

Original languageEnglish (US)
Article number106112
JournalBiomedical Signal Processing and Control
StatePublished - Jul 2024


  • GAN
  • Melanoma
  • Pseudo image
  • Siamese network
  • Skin lesion classification

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Health Informatics


Dive into the research topics of 'Pseudo Skin Image Generator (PSIG-Net): Ambiguity-free sample generation and outlier control for skin lesion classification'. Together they form a unique fingerprint.

Cite this