Detection of Line Artifacts in Lung Ultrasound Images of COVID-19 Patients Via Nonconvex Regularization

In this article, we present a novel method for line artifacts quantification in lung ultrasound (LUS) images of COVID-19 patients. We formulate this as a nonconvex regularization problem involving a sparsity-enforcing, Cauchy-based penalty function, and the inverse Radon transform. We employ a simpl...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on ultrasonics, ferroelectrics, and frequency control ferroelectrics, and frequency control, 2020-11, Vol.67 (11), p.2218-2229
Main Authors: Karakus, Oktay, Anantrasirichai, Nantheera, Aguersif, Amazigh, Silva, Stein, Basarab, Adrian, Achim, Alin
Format: Article
Language:English
Subjects:
Acoustics
Aged
Algorithms
Betacoronavirus
Cauchy-based penalty
Coronavirus Infections - diagnostic imaging
Coronaviruses
COVID-19
Diseases
Domains
Female
Frequency control
Humans
Identification methods
Image Interpretation, Computer-Assisted - methods
line artifacts
Lung
Lung - diagnostic imaging
lung ultrasound (LUS)
Lungs
Male
Maxima
Middle Aged
Pandemics
Penalty function
Performance evaluation
Pleura - diagnostic imaging
Pneumonia, Viral - diagnostic imaging
Radon transform
Radon transformation
Regularization
ROC Curve
SARS-CoV-2
Transforms
Ultrasonic imaging
Ultrasonography - methods
Ultrasound
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this article, we present a novel method for line artifacts quantification in lung ultrasound (LUS) images of COVID-19 patients. We formulate this as a nonconvex regularization problem involving a sparsity-enforcing, Cauchy-based penalty function, and the inverse Radon transform. We employ a simple local maxima detection technique in the Radon transform domain, associated with known clinical definitions of line artifacts. Despite being nonconvex, the proposed technique is guaranteed to convergence through our proposed Cauchy proximal splitting (CPS) method, and accurately identifies both horizontal and vertical line artifacts in LUS images. To reduce the number of false and missed detection, our method includes a two-stage validation mechanism, which is performed in both Radon and image domains. We evaluate the performance of the proposed method in comparison to the current state-of-the-art B-line identification method, and show a considerable performance gain with 87% correctly detected B-lines in LUS images of nine COVID-19 patients.
ISSN:0885-3010
1525-8955
DOI:10.1109/TUFFC.2020.3016092