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

Over the last few decades, Lung Ultrasound (LUS) has been increasingly usedto diagnose and monitor different lung diseases in neonates. It is a noninvasive tool that allows a fast bedside examination while minimally handlingthe neonate. Acquiring a LUS scan is easy, but understanding the artifactsconcerned with each respiratory disease is challenging. Mixed artifact patternsfound in different respiratory diseases may limit LUS readability by theoperator. While machine learning (ML), especially deep learning can assist inautomated analysis, simply feeding the ultrasound images to an ML model fordiagnosis is not enough to earn the trust of medical professionals. Thealgorithm should output LUS features that are familiar to the operator instead.Therefore, in this paper we present a unique approach for extracting sevenmeaningful LUS features that can be easily associated with a specificpathological lung condition: Normal pleura, irregular pleura, thick pleura,Alines, Coalescent B-lines, Separate B-lines and Consolidations. Theseartifacts can lead to early prediction of infants developing later respiratorydistress symptoms. A single multi-class region proposal-based object detectionmodel faster-RCNN (fRCNN) was trained on lower posterior lung ultrasound videosto detect these LUS features which are further linked to four common neonataldiseases. Our results show that fRCNN surpasses single stage models such asRetinaNet and can successfully detect the aforementioned LUS features with amean average precision of 86.4%. Instead of a fully automatic diagnosis fromimages without any interpretability, detection of such LUS features leave theultimate control of diagnosis to the clinician, which can result in a moretrustworthy intelligent system.

An interpretable object detection based model for the diagnosis of neonatal lung diseases using Ultrasound images