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

Deep learning (DL)-based rib fracture detection has shown promise of playingan important role in preventing mortality and improving patient outcome.Normally, developing DL-based object detection models requires a huge amount ofbounding box annotation. However, annotating medical data is time-consuming andexpertise-demanding, making obtaining a large amount of fine-grainedannotations extremely infeasible. This poses a pressing need {for} developinglabel-efficient detection models to alleviate radiologists' labeling burden. Totackle this challenge, the literature on object detection has witnessed anincrease of weakly-supervised and semi-supervised approaches, yet still lacks aunified framework that leverages various forms of fully-labeled,weakly-labeled, and unlabeled data. In this paper, we present a novelomni-supervised object detection network, ORF-Netv2, to leverage as muchavailable supervision as possible. Specifically, a multi-branch omni-superviseddetection head is introduced with each branch trained with a specific type ofsupervision. A co-training-based dynamic label assignment strategy is thenproposed to enable flexible and robust learning from the weakly-labeled andunlabeled data. Extensive evaluation was conducted for the proposed frameworkwith three rib fracture datasets on both chest CT and X-ray. By leveraging allforms of supervision, ORF-Netv2 achieves mAPs of 34.7, 44.7, and 19.4 on thethree datasets, respectively, surpassing the baseline detector which uses onlybox annotations by mAP gains of 3.8, 4.8, and 5.0, respectively. Furthermore,ORF-Netv2 consistently outperforms other competitive label-efficient methodsover various scenarios, showing a promising framework for label-efficientfracture detection. The code is available at:https://github.com/zhizhongchai/ORF-Net.

Deep Omni-supervised Learning for Rib Fracture Detection from Chest Radiology Images