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

Well-annotated medical datasets enable deep neural networks (DNNs) to gainstrong power in extracting lesion-related features. Building such large andwell-designed medical datasets is costly due to the need for high-levelexpertise. Model pre-training based on ImageNet is a common practice to gainbetter generalization when the data amount is limited. However, it suffers fromthe domain gap between natural and medical images. In this work, we pre-trainDNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap inmedical US applications. To learn US image representations based on unlabeledUS videos, we propose a novel meta-learning-based contrastive learning method,namely Meta Ultrasound Contrastive Learning (Meta-USCL). To tackle the keychallenge of obtaining semantically consistent sample pairs for contrastivelearning, we present a positive pair generation module along with an automaticsample weighting module based on meta-learning. Experimental results onmultiple computer-aided diagnosis (CAD) problems, including pneumoniadetection, breast cancer classification, and breast tumor segmentation, showthat the proposed self-supervised method reaches state-of-the-art (SOTA). Thecodes are available at https://github.com/Schuture/Meta-USCL.

Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning