Progressive transfer learning and adversarial domain adaptation for cross-domain skin disease classification

Yanyang Gu, Zongyuan Ge, C. Paul Bonnington, Jun Zhou

Research output: Contribution to journalArticleResearchpeer-review

16 Citations (Scopus)

Abstract

Deep learning has been used to analyze and diagnose various skin diseases through medical imaging. However, recent researches show that a well-trained deep learning model may not generalize well to data from different cohorts due to domain shift. Simple data fusion techniques such as combining disease samples from different data sources are not effective to solve this problem. In this paper, we present two methods for a novel task of cross-domain skin disease recognition. Starting from a fully supervised deep convolutional neural network classifier pre-trained on ImageNet, we explore a two-step progressive transfer learning technique by fine-tuning the network on two skin disease datasets. We then propose to adopt adversarial learning as a domain adaptation technique to perform invariant attribute translation from source to target domain in order to improve the recognition performance. In order to evaluate these two methods, we analyze generalization capability of the trained model on melanoma detection, cancer detection, and cross-modality learning tasks on two skin image datasets collected from different clinical settings and cohorts with different disease distributions. The experiments prove the effectiveness of our method in solving the domain shift problem.

Original languageEnglish
Article number8846038
Pages (from-to)1379-1393
Number of pages15
JournalIEEE Journal of Biomedical and Health Informatics
Volume24
Issue number5
DOIs
Publication statusPublished - May 2020

Keywords

  • Automatic melanoma detection
  • cycle-GAN
  • deep learning
  • dermoscopy image
  • domain adaptation
  • transfer learning

Cite this