Show simple item record

dc.contributor.authorGu, Yanyang
dc.contributor.authorGe, Zongyuan
dc.contributor.authorBonnington, C Paul
dc.contributor.authorZhou, Jun
dc.date.accessioned2020-09-09T00:12:52Z
dc.date.available2020-09-09T00:12:52Z
dc.date.issued2020
dc.identifier.issn2168-2194
dc.identifier.doi10.1109/JBHI.2019.2942429
dc.identifier.urihttp://hdl.handle.net/10072/397215
dc.description.abstractDeep 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.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofpagefrom1379
dc.relation.ispartofpageto1393
dc.relation.ispartofissue5
dc.relation.ispartofjournalIEEE Journal of Biomedical and Health Informatics
dc.relation.ispartofvolume24
dc.subject.fieldofresearchInformation and computing sciences
dc.subject.fieldofresearchcode46
dc.subject.keywordsScience & Technology
dc.subject.keywordsLife Sciences & Biomedicine
dc.subject.keywordsComputer Science, Information Systems
dc.subject.keywordsComputer Science, Interdisciplinary Applications
dc.titleProgressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationGu, Y; Ge, Z; Bonnington, CP; Zhou, J, Progressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification, IEEE Journal of Biomedical and Health Informatics, 2020, 24 (5), pp. 1379-1393
dc.date.updated2020-09-09T00:11:46Z
gro.hasfulltextNo Full Text
gro.griffith.authorZhou, Jun


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record