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

Chest X-rays (CXRs) are a widely used imaging modality for the diagnosis andprognosis of lung disease. The image analysis tasks vary. Examples includepathology detection and lung segmentation. There is a large body of work wheremachine learning algorithms are developed for specific tasks. A significantrecent example is Coronavirus disease (covid-19) detection using CXR data.However, the traditional diagnostic tool design methods based on supervisedlearning are burdened by the need to provide training data annotation, whichshould be of good quality for better clinical outcomes. Here, we propose analternative solution, a new self-supervised paradigm, where a generalrepresentation from CXRs is learned using a group-masked self-supervisedframework. The pre-trained model is then fine-tuned for domain-specific taskssuch as covid-19, pneumonia detection, and general health screening. We showthat the same pre-training can be used for the lung segmentation task. Ourproposed paradigm shows robust performance in multiple downstream tasks whichdemonstrates the success of the pre-training. Moreover, the performance of thepre-trained models on data with significant drift during test time proves thelearning of a better generic representation. The methods are further validatedby covid-19 detection in a unique small-scale pediatric data set. Theperformance gain in accuracy (~25%) is significant when compared to asupervised transformer-based method. This adds credence to the strength andreliability of our proposed framework and pre-training strategy.

SPCXR: Self-supervised Pretraining using Chest X-rays Towards a Domain Specific Foundation Model