Self-supervised multi-modality learning for multi-label skin lesion classification.

Journal: Computer methods and programs in biomedicine
PMID:

Abstract

BACKGROUND: The clinical diagnosis of skin lesions involves the analysis of dermoscopic and clinical modalities. Dermoscopic images provide detailed views of surface structures, while clinical images offer complementary macroscopic information. Clinicians frequently use the seven-point checklist as an auxiliary tool for melanoma diagnosis and identifying lesion attributes. Supervised deep learning approaches, such as convolutional neural networks, have performed well using dermoscopic and clinical modalities (multi-modality) and further enhanced classification by predicting seven skin lesion attributes (multi-label). However, the performance of these approaches is reliant on the availability of large-scale labeled data, which are costly and time-consuming to obtain, more so with annotating multi-attributes METHODS:: To reduce the dependency on large labeled datasets, we propose a self-supervised learning (SSL) algorithm for multi-modality multi-label skin lesion classification. Compared with single-modality SSL, our algorithm enables multi-modality SSL by maximizing the similarities between paired dermoscopic and clinical images from different views. We introduce a novel multi-modal and multi-label SSL strategy that generates surrogate pseudo-multi-labels for seven skin lesion attributes through clustering analysis. A label-relation-aware module is proposed to refine each pseudo-label embedding, capturing the interrelationships between pseudo-multi-labels. We further illustrate the interrelationships of skin lesion attributes and their relationships with clinical diagnoses using an attention visualization technique.

Authors

  • Hao Wang
    Department of Cardiology, Second Medical Center, Chinese PLA General Hospital, Beijing, China.
  • Euijoon Ahn
    School of Computer Science, University of Sydney, NSW, Australia. Electronic address: eahn4614@uni.sydney.edu.au.
  • Lei Bi
  • Jinman Kim
    School of Information Technologies, University of Sydney, Australia; Institute of Biomedical Engineering and Technology, University of Sydney, Australia. Electronic address: jinman.kim@sydney.edu.au.