Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study

Lung ultrasound (LUS) is an accurate thoracic imaging technique distinguished by its handheld size, low-cost, and lack of radiation. User dependence and poor access to training have limited the impact and dissemination of LUS outside of acute care hospital environments. Automated interpretation of L...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Robert Arntfield, Derek Wu, Jared Tschirhart, Blake VanBerlo, Alex Ford, Jordan Ho, Joseph McCauley, Benjamin Wu, Jason Deglint, Rushil Chaudhary, Chintan Dave, Bennett VanBerlo, John Basmaji, Scott Millington
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning ultrasound lung ultrasound artificial intelligence automation imaging Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/bfb274b5fee04c3982319bfa973308ca
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bfb274b5fee04c3982319bfa973308ca
record_format	dspace
spelling	oai:doaj.org-article:bfb274b5fee04c3982319bfa973308ca2021-11-25T17:21:10ZAutomation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study10.3390/diagnostics111120492075-4418https://doaj.org/article/bfb274b5fee04c3982319bfa973308ca2021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/2049https://doaj.org/toc/2075-4418Lung ultrasound (LUS) is an accurate thoracic imaging technique distinguished by its handheld size, low-cost, and lack of radiation. User dependence and poor access to training have limited the impact and dissemination of LUS outside of acute care hospital environments. Automated interpretation of LUS using deep learning can overcome these barriers by increasing accuracy while allowing point-of-care use by non-experts. In this multicenter study, we seek to automate the clinically vital distinction between A line (normal parenchyma) and B line (abnormal parenchyma) on LUS by training a customized neural network using 272,891 labelled LUS images. After external validation on 23,393 frames, pragmatic clinical application at the clip level was performed on 1162 videos. The trained classifier demonstrated an area under the receiver operating curve (AUC) of 0.96 (±0.02) through 10-fold cross-validation on local frames and an AUC of 0.93 on the external validation dataset. Clip-level inference yielded sensitivities and specificities of 90% and 92% (local) and 83% and 82% (external), respectively, for detecting the B line pattern. This study demonstrates accurate deep-learning-enabled LUS interpretation between normal and abnormal lung parenchyma on ultrasound frames while rendering diagnostically important sensitivity and specificity at the video clip level.Robert ArntfieldDerek WuJared TschirhartBlake VanBerloAlex FordJordan HoJoseph McCauleyBenjamin WuJason DeglintRushil ChaudharyChintan DaveBennett VanBerloJohn BasmajiScott MillingtonMDPI AGarticledeep learningultrasoundlung ultrasoundartificial intelligenceautomationimagingMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 2049, p 2049 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning ultrasound lung ultrasound artificial intelligence automation imaging Medicine (General) R5-920
spellingShingle	deep learning ultrasound lung ultrasound artificial intelligence automation imaging Medicine (General) R5-920 Robert Arntfield Derek Wu Jared Tschirhart Blake VanBerlo Alex Ford Jordan Ho Joseph McCauley Benjamin Wu Jason Deglint Rushil Chaudhary Chintan Dave Bennett VanBerlo John Basmaji Scott Millington Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study
description	Lung ultrasound (LUS) is an accurate thoracic imaging technique distinguished by its handheld size, low-cost, and lack of radiation. User dependence and poor access to training have limited the impact and dissemination of LUS outside of acute care hospital environments. Automated interpretation of LUS using deep learning can overcome these barriers by increasing accuracy while allowing point-of-care use by non-experts. In this multicenter study, we seek to automate the clinically vital distinction between A line (normal parenchyma) and B line (abnormal parenchyma) on LUS by training a customized neural network using 272,891 labelled LUS images. After external validation on 23,393 frames, pragmatic clinical application at the clip level was performed on 1162 videos. The trained classifier demonstrated an area under the receiver operating curve (AUC) of 0.96 (±0.02) through 10-fold cross-validation on local frames and an AUC of 0.93 on the external validation dataset. Clip-level inference yielded sensitivities and specificities of 90% and 92% (local) and 83% and 82% (external), respectively, for detecting the B line pattern. This study demonstrates accurate deep-learning-enabled LUS interpretation between normal and abnormal lung parenchyma on ultrasound frames while rendering diagnostically important sensitivity and specificity at the video clip level.
format	article
author	Robert Arntfield Derek Wu Jared Tschirhart Blake VanBerlo Alex Ford Jordan Ho Joseph McCauley Benjamin Wu Jason Deglint Rushil Chaudhary Chintan Dave Bennett VanBerlo John Basmaji Scott Millington
author_facet	Robert Arntfield Derek Wu Jared Tschirhart Blake VanBerlo Alex Ford Jordan Ho Joseph McCauley Benjamin Wu Jason Deglint Rushil Chaudhary Chintan Dave Bennett VanBerlo John Basmaji Scott Millington
author_sort	Robert Arntfield
title	Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study
title_short	Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study
title_full	Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study
title_fullStr	Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study
title_full_unstemmed	Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study
title_sort	automation of lung ultrasound interpretation via deep learning for the classification of normal versus abnormal lung parenchyma: a multicenter study
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/bfb274b5fee04c3982319bfa973308ca
work_keys_str_mv	AT robertarntfield automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT derekwu automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT jaredtschirhart automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT blakevanberlo automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT alexford automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT jordanho automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT josephmccauley automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT benjaminwu automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT jasondeglint automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT rushilchaudhary automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT chintandave automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT bennettvanberlo automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT johnbasmaji automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy AT scottmillington automationoflungultrasoundinterpretationviadeeplearningfortheclassificationofnormalversusabnormallungparenchymaamulticenterstudy
_version_	1718412493733232640

Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study

Ejemplares similares