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

Purpose: Congenital heart defect (CHD) is the most common birth defect.Thoracic echocardiography (TTE) can provide sufficient cardiac structureinformation, evaluate hemodynamics and cardiac function, and is an effectivemethod for atrial septal defect (ASD) examination. This paper aims to study adeep learning method based on cardiac ultrasound video to assist in ASDdiagnosis. Materials and methods: We select two standard views of the atrialseptum (subAS) and low parasternal four-compartment view (LPS4C) as the twoviews to identify ASD. We enlist data from 300 children patients as part of adouble-blind experiment for five-fold cross-validation to verify theperformance of our model. In addition, data from 30 children patients (15positives and 15 negatives) are collected for clinician testing and compared toour model test results (these 30 samples do not participate in model training).We propose an echocardiography video-based atrial septal defect diagnosissystem. In our model, we present a block random selection, maximal agreementdecision and frame sampling strategy for training and testing respectively,resNet18 and r3D networks are used to extract the frame features and aggregatethem to build a rich video-level representation. Results: We validate our modelusing our private dataset by five-cross validation. For ASD detection, weachieve 89.33 AUC, 84.95 accuracy, 85.70 sensitivity, 81.51 specificity and81.99 F1 score. Conclusion: The proposed model is multiple instanceslearning-based deep learning model for video atrial septal defect detectionwhich effectively improves ASD detection accuracy when compared to theperformances of previous networks and clinical doctors.

Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning