Cargando…

How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?

The growing need for emergency imaging has greatly increased the number of conventional X-rays, particularly for traumatic injury. Deep learning (DL) algorithms could improve fracture screening by radiologists and emergency room (ER) physicians. We used an algorithm developed for the detection of ap...

Descripción completa

Detalles Bibliográficos
Autores principales: Reichert, Guillaume, Bellamine, Ali, Fontaine, Matthieu, Naipeanu, Beatrice, Altar, Adrien, Mejean, Elodie, Javaud, Nicolas, Siauve, Nathalie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321374/
http://dx.doi.org/10.3390/jimaging7070105
_version_ 1783730837452226560
author Reichert, Guillaume
Bellamine, Ali
Fontaine, Matthieu
Naipeanu, Beatrice
Altar, Adrien
Mejean, Elodie
Javaud, Nicolas
Siauve, Nathalie
author_facet Reichert, Guillaume
Bellamine, Ali
Fontaine, Matthieu
Naipeanu, Beatrice
Altar, Adrien
Mejean, Elodie
Javaud, Nicolas
Siauve, Nathalie
author_sort Reichert, Guillaume
collection PubMed
description The growing need for emergency imaging has greatly increased the number of conventional X-rays, particularly for traumatic injury. Deep learning (DL) algorithms could improve fracture screening by radiologists and emergency room (ER) physicians. We used an algorithm developed for the detection of appendicular skeleton fractures and evaluated its performance for detecting traumatic fractures on conventional X-rays in the ER, without the need for training on local data. This algorithm was tested on all patients (N = 125) consulting at the Louis Mourier ER in May 2019 for limb trauma. Patients were selected by two emergency physicians from the clinical database used in the ER. Their X-rays were exported and analyzed by a radiologist. The prediction made by the algorithm and the annotation made by the radiologist were compared. For the 125 patients included, 25 patients with a fracture were identified by the clinicians, 24 of whom were identified by the algorithm (sensitivity of 96%). The algorithm incorrectly predicted a fracture in 14 of the 100 patients without fractures (specificity of 86%). The negative predictive value was 98.85%. This study shows that DL algorithms are potentially valuable diagnostic tools for detecting fractures in the ER and could be used in the training of junior radiologists.
format Online
Article
Text
id pubmed-8321374
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83213742021-08-26 How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room? Reichert, Guillaume Bellamine, Ali Fontaine, Matthieu Naipeanu, Beatrice Altar, Adrien Mejean, Elodie Javaud, Nicolas Siauve, Nathalie J Imaging Article The growing need for emergency imaging has greatly increased the number of conventional X-rays, particularly for traumatic injury. Deep learning (DL) algorithms could improve fracture screening by radiologists and emergency room (ER) physicians. We used an algorithm developed for the detection of appendicular skeleton fractures and evaluated its performance for detecting traumatic fractures on conventional X-rays in the ER, without the need for training on local data. This algorithm was tested on all patients (N = 125) consulting at the Louis Mourier ER in May 2019 for limb trauma. Patients were selected by two emergency physicians from the clinical database used in the ER. Their X-rays were exported and analyzed by a radiologist. The prediction made by the algorithm and the annotation made by the radiologist were compared. For the 125 patients included, 25 patients with a fracture were identified by the clinicians, 24 of whom were identified by the algorithm (sensitivity of 96%). The algorithm incorrectly predicted a fracture in 14 of the 100 patients without fractures (specificity of 86%). The negative predictive value was 98.85%. This study shows that DL algorithms are potentially valuable diagnostic tools for detecting fractures in the ER and could be used in the training of junior radiologists. MDPI 2021-06-25 /pmc/articles/PMC8321374/ http://dx.doi.org/10.3390/jimaging7070105 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Reichert, Guillaume
Bellamine, Ali
Fontaine, Matthieu
Naipeanu, Beatrice
Altar, Adrien
Mejean, Elodie
Javaud, Nicolas
Siauve, Nathalie
How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?
title How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?
title_full How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?
title_fullStr How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?
title_full_unstemmed How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?
title_short How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?
title_sort how can a deep learning algorithm improve fracture detection on x-rays in the emergency room?
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321374/
http://dx.doi.org/10.3390/jimaging7070105
work_keys_str_mv AT reichertguillaume howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT bellamineali howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT fontainematthieu howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT naipeanubeatrice howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT altaradrien howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT mejeanelodie howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT javaudnicolas howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom
AT siauvenathalie howcanadeeplearningalgorithmimprovefracturedetectiononxraysintheemergencyroom