UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Rapid Lung Ultrasound COVID-19 Severity Scoring with Resource-Efficient Deep Feature Extraction

Raillard, Pierre; Cristoni, Lorenzo; Walden, Andrew; Lazzari, Roberto; Pulimood, Thomas; Grandjean, Louis; Wheeler-Kingshott, Claudia AM Gandini; ... Baum, Zachary MC; + view all (2022) Rapid Lung Ultrasound COVID-19 Severity Scoring with Resource-Efficient Deep Feature Extraction. In: Proceedings of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (ASMUS: Advances in Simplifying Medical UltraSound). (pp. pp. 1-11). MICCAI (In press). Green open access

[thumbnail of 2207.10998.pdf]
Preview
Text
2207.10998.pdf - Accepted Version

Download (558kB) | Preview

Abstract

Artificial intelligence-based analysis of lung ultrasound imaging has been demonstrated as an effective technique for rapid diagnostic decision support throughout the COVID-19 pandemic. However, such techniques can require days- or weeks-long training processes and hyper-parameter tuning to develop intelligent deep learning image analysis models. This work focuses on leveraging 'off-the-shelf' pre-trained models as deep feature extractors for scoring disease severity with minimal training time. We propose using pre-trained initializations of existing methods ahead of simple and compact neural networks to reduce reliance on computational capacity. This reduction of computational capacity is of critical importance in time-limited or resource-constrained circumstances, such as the early stages of a pandemic. On a dataset of 49 patients, comprising over 20,000 images, we demonstrate that the use of existing methods as feature extractors results in the effective classification of COVID-19-related pneumonia severity while requiring only minutes of training time. Our methods can achieve an accuracy of over 0.93 on a 4-level severity score scale and provides comparable per-patient region and global scores compared to expert annotated ground truths. These results demonstrate the capability for rapid deployment and use of such minimally-adapted methods for progress monitoring, patient stratification and management in clinical practice for COVID-19 patients, and potentially in other respiratory diseases.

Type: Proceedings paper
Title: Rapid Lung Ultrasound COVID-19 Severity Scoring with Resource-Efficient Deep Feature Extraction
Event: ASMUS 2022 - 3rd International Workshop of Advances in Simplifying Medical UltraSound (ASMUS) - held in conjunction with MICCAI 2022
Open access status: An open access version is available from UCL Discovery
Publisher version: https://conferences.miccai.org/2022/en/MICCAI2022-...
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Severity Scoring, Deep Learning, Lung Ultrasound, COVID-19
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10153273
Downloads since deposit
2Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item