Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological b lines on lung ultrasound: A deep learning study

51Citations
Citations of this article
103Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Objectives Lung ultrasound (LUS) is a portable, low-cost respiratory imaging tool but is challenged by user dependence and lack of diagnostic specificity. It is unknown whether the advantages of LUS implementation could be paired with deep learning (DL) techniques to match or exceed human-level, diagnostic specificity among similar appearing, pathological LUS images. Design A convolutional neural network (CNN) was trained on LUS images with B lines of different aetiologies. CNN diagnostic performance, as validated using a 10% data holdback set, was compared with surveyed LUS-competent physicians. Setting Two tertiary Canadian hospitals. Participants 612 LUS videos (121 381 frames) of B lines from 243 distinct patients with either (1) COVID-19 (COVID), non-COVID acute respiratory distress syndrome (NCOVID) or (3) hydrostatic pulmonary edema (HPE). Results The trained CNN performance on the independent dataset showed an ability to discriminate between COVID (area under the receiver operating characteristic curve (AUC) 1.0), NCOVID (AUC 0.934) and HPE (AUC 1.0) pathologies. This was significantly better than physician ability (AUCs of 0.697, 0.704, 0.967 for the COVID, NCOVID and HPE classes, respectively), p<0.01. Conclusions A DL model can distinguish similar appearing LUS pathology, including COVID-19, that cannot be distinguished by humans. The performance gap between humans and the model suggests that subvisible biomarkers within ultrasound images could exist and multicentre research is merited.

References Powered by Scopus

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

15236Citations
1631Readers
Get full text

Xception: Deep learning with depthwise separable convolutions

11547Citations
8339Readers
Get full text

This article is free to access.

Cited by Powered by Scopus

154Citations
257Readers

This article is free to access.

Your institution provides access to this article.

This article is free to access.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Arntfield, R., Vanberlo, B., Alaifan, T., Phelps, N., White, M., Chaudhary, R., … Wu, D. (2021). Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological b lines on lung ultrasound: A deep learning study. BMJ Open, 11(3). https://doi.org/10.1136/bmjopen-2020-045120

Readers over time

‘21‘22‘23‘24‘25015304560

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 35

69%

Lecturer / Post doc 7

14%

Researcher 7

14%

Professor / Associate Prof. 2

4%

Readers' Discipline

Tooltip

Medicine and Dentistry 25

46%

Engineering 14

26%

Computer Science 12

22%

Nursing and Health Professions 3

6%

Article Metrics

Tooltip
Mentions
References: 1
Social Media
Shares, Likes & Comments: 11

Save time finding and organizing research with Mendeley

Sign up for free
0