English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The clinical diagnosis of skin lesion involves the analysis of dermoscopicand clinical modalities. Dermoscopic images provide a detailed view of thesurface structures whereas clinical images offer a complementary macroscopicinformation. The visual diagnosis of melanoma is also based on seven-pointchecklist which involves identifying different visual attributes. Recently,supervised learning approaches such as convolutional neural networks (CNNs)have shown great performances using both dermoscopic and clinical modalities(Multi-modality). The seven different visual attributes in the checklist arealso used to further improve the the diagnosis. The performances of theseapproaches, however, are still reliant on the availability of large-scaledlabeled data. The acquisition of annotated dataset is an expensive andtime-consuming task, more so with annotating multi-attributes. To overcome thislimitation, we propose a self-supervised learning (SSL) algorithm formulti-modality skin lesion classification. Our algorithm enables themulti-modality learning by maximizing the similarities between paireddermoscopic and clinical images from different views. In addition, we generatesurrogate pseudo-multi-labels that represent seven attributes via clusteringanalysis. We also propose a label-relation-aware module to refine eachpseudo-label embedding and capture the interrelationships betweenpseudo-multi-labels. We validated the effectiveness of our algorithm usingwell-benchmarked seven-point skin lesion dataset. Our results show that ouralgorithm achieved better performances than other state-of-the-art SSLcounterparts.

Self-Supervised Multi-Modality Learning for Multi-Label Skin Lesion Classification