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

BACKGROUND AND OBJECTIVES: The multiple chest x-ray datasets released in thelast years have ground-truth labels intended for different computer visiontasks, suggesting that performance in automated chest-xray interpretation mightimprove by using a method that can exploit diverse types of annotations. Thiswork presents a Deep Learning method based on the late fusion of differentconvolutional architectures, that allows training with heterogeneous data witha simple implementation, and evaluates its performance on independent testdata. We focused on obtaining a clinically useful tool that could besuccessfully integrated into a hospital workflow. MATERIALS AND METHODS: Basedon expert opinion, we selected four target chest x-ray findings, namely lungopacities, fractures, pneumothorax and pleural effusion. For each finding wedefined the most adequate type of ground-truth label, and built four trainingdatasets combining images from public chest x-ray datasets and ourinstitutional archive. We trained four different Deep Learning architecturesand combined their outputs with a late fusion strategy, obtaining a unifiedtool. Performance was measured on two test datasets: an externalopenly-available dataset, and a retrospective institutional dataset, toestimate performance on local population. RESULTS: The external and local testsets had 4376 and 1064 images, respectively, for which the model showed an areaunder the Receiver Operating Characteristics curve of 0.75 (95%CI: 0.74-0.76)and 0.87 (95%CI: 0.86-0.89) in the detection of abnormal chest x-rays. For thelocal population, a sensitivity of 86% (95%CI: 84-90), and a specificity of 88%(95%CI: 86-90) were obtained, with no significant differences betweendemographic subgroups. We present examples of heatmaps to show the accomplishedlevel of interpretability, examining true and false positives.

Chest x-ray automated triage: a semiologic approach designed for  clinical implementation, exploiting different types of labels through a  combination of four Deep Learning architectures