Detection of Line Artefacts in Lung Ultrasound Images of COVID-19 Patients via Non-Convex Regularization

Oktay Karakuş*, Nantheera Anantrasirichai, Amazigh Aguersif, Stein Silva, Adrian Basarab, Alin Achim

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)

21 Downloads (Pure)

Abstract

In this paper, we present a novel method for line artefacts quantification in lung ultrasound (LUS) images of COVID-19 patients. We formulate this as a non-convex regularisation 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 artefacts. Despite being non-convex, the proposed technique is guaranteed to convergence through our proposed Cauchy proximal splitting (CPS) method and accurately identifies both horizontal and vertical line artefacts in LUS images. In order 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. In addition, owing to its fast convergence, our proposed method is readily applicable for processing LUS image sequences.
Original languageEnglish
Number of pages12
JournalIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Early online date12 Aug 2020
DOIs
Publication statusPublished - 12 Aug 2020

Bibliographical note

Provisional acceptance date added, based on publication information.

Structured keywords

  • Covid19

Keywords

  • Lung Ultrasound
  • COVID-19
  • Line Artefacts
  • Radon Transform
  • Cauchy-based penalty

Fingerprint Dive into the research topics of 'Detection of Line Artefacts in Lung Ultrasound Images of COVID-19 Patients via Non-Convex Regularization'. Together they form a unique fingerprint.

  • Cite this