Progressive Transfer Learning and Adversarial Domain Adaptation for Cross-Domain Skin Disease Classification
- 23 September 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 24 (5), 1379-1393
- https://doi.org/10.1109/jbhi.2019.2942429
Abstract
Deep learning has been used to analyze and diag-nose various skin diseases through medical imaging. However,recent researches show that a well trained deep learning modelmay not generalize well to data from different cohorts due todomain shift. Simple data fusion techniques such as combiningdisease samples from different data sources are not effective tosolve this problem. In this paper, we present two methods for anovel task of cross-domain skin disease recognition. Starting froma fully supervised deep convolutional neural network classifierpre-trained on ImageNet, we explore a two-step progressivetransfer learning technique by fine-tuning the network on twoskin disease datasets. We then propose to adopt adversariallearning as a domain adaptation technique to perform invariantattribute translation from source to target domain in orderto improve the recognition performance. In order to evaluatethese two methods, we analyze generalization capability of thetrained model on melanoma detection, cancer detection andcross-modality learning tasks on two skin image datasets collectedfrom different clinical settings and cohorts with different diseasedistributions. The experiments prove the effectiveness of ourmethod in solving the domain shift problem.Keywords
This publication has 37 references indexed in Scilit:
- Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual NetworksIEEE Transactions on Medical Imaging, 2016
- Melanoma Classification on Dermoscopy Images Using a Neural Network Ensemble ModelIEEE Transactions on Medical Imaging, 2016
- Toward a Robust Analysis of Dermoscopy Images Acquired under Different ConditionsPublished by Informa UK Limited ,2015
- Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy ImagesPublished by Springer Science and Business Media LLC ,2015
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Hair removal methods: A comparative study for dermoscopy imagesBiomedical Signal Processing and Control, 2011
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Melanoma biology and new targeted therapyNature, 2007
- Segmentation of digitized dermatoscopic images by two-dimensional color clusteringIEEE Transactions on Medical Imaging, 1999