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

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, dia...

Full description

Saved in:
Bibliographic Details
Main Authors: Thamer Alaifan, Robert Arntfield, Blake VanBerlo, Nathan Phelps, Matthew White, Rushil Chaudhary, Jordan Ho, Derek Wu
Format: Article
Language:English
Published: BMJ Publishing Group 2021-03-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/11/3/e045120.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846162002701975552
author Thamer Alaifan
Robert Arntfield
Blake VanBerlo
Nathan Phelps
Matthew White
Rushil Chaudhary
Jordan Ho
Derek Wu
author_facet Thamer Alaifan
Robert Arntfield
Blake VanBerlo
Nathan Phelps
Matthew White
Rushil Chaudhary
Jordan Ho
Derek Wu
author_sort Thamer Alaifan
collection DOAJ
description 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.
format Article
id doaj-art-df12b05c6f204c1a802b9ad48f4f6f00
institution Kabale University
issn 2044-6055
language English
publishDate 2021-03-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-df12b05c6f204c1a802b9ad48f4f6f002024-11-20T18:50:09ZengBMJ Publishing GroupBMJ Open2044-60552021-03-0111310.1136/bmjopen-2020-045120Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning studyThamer Alaifan0Robert Arntfield1Blake VanBerlo2Nathan Phelps3Matthew White4Rushil Chaudhary5Jordan Ho6Derek Wu7Division of Critical Care Medicine, Western University, London, Ontario, CanadaDivision of Critical Care, Western University, London, Ontario, CanadaSchulich School of Medicine and Dentistry, Western University, London, Ontario, CanadaDepartment of Computer Science, Western University, London, Ontario, CanadaDivision of Critical Care Medicine, Western University, London, Ontario, CanadaDepartment of Medicine, Schulich School of Medicine and Dentistry, Western University, London, Ontario, CanadaSchulich School of Medicine and Dentistry, Western University, London, Ontario, CanadaSchulich School of Medicine and Dentistry, Western University, London, Ontario, CanadaObjectives 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.https://bmjopen.bmj.com/content/11/3/e045120.full
spellingShingle Thamer Alaifan
Robert Arntfield
Blake VanBerlo
Nathan Phelps
Matthew White
Rushil Chaudhary
Jordan Ho
Derek Wu
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
title Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study
title_full Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study
title_fullStr Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study
title_full_unstemmed Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study
title_short Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study
title_sort development of a convolutional neural network to differentiate among the etiology of similar appearing pathological b lines on lung ultrasound a deep learning study
url https://bmjopen.bmj.com/content/11/3/e045120.full
work_keys_str_mv AT thameralaifan developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT robertarntfield developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT blakevanberlo developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT nathanphelps developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT matthewwhite developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT rushilchaudhary developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT jordanho developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy
AT derekwu developmentofaconvolutionalneuralnetworktodifferentiateamongtheetiologyofsimilarappearingpathologicalblinesonlungultrasoundadeeplearningstudy