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

Recent advancements in self-supervised learning have demonstrated thateffective visual representations can be learned from unlabeled images. This hasled to increased interest in applying self-supervised learning to the medicaldomain, where unlabeled images are abundant and labeled images are difficult toobtain. However, most self-supervised learning approaches are modeled as imagelevel discriminative or generative proxy tasks, which may not capture the finerlevel representations necessary for dense prediction tasks like multi-organsegmentation. In this paper, we propose a novel contrastive learning frameworkthat integrates Localized Region Contrast (LRC) to enhance existingself-supervised pre-training methods for medical image segmentation. Ourapproach involves identifying Super-pixels by Felzenszwalb's algorithm andperforming local contrastive learning using a novel contrastive sampling loss.Through extensive experiments on three multi-organ segmentation datasets, wedemonstrate that integrating LRC to an existing self-supervised method in alimited annotation setting significantly improves segmentation performance.Moreover, we show that LRC can also be applied to fully-supervised pre-trainingmethods to further boost performance.

Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation