Cargando…

Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries

Wrist trauma is common in children, typically requiring radiography for diagnosis and treatment planning. However, many children do not have fractures and are unnecessarily exposed to radiation. Ultrasound performed at bedside could detect fractures prior to radiography. Modern tools including three...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Jack, Boora, Naveenjyote, Melendez, Sarah, Rakkunedeth Hareendranathan, Abhilash, Jaremko, Jacob
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224020/
https://www.ncbi.nlm.nih.gov/pubmed/34063945
http://dx.doi.org/10.3390/children8060431
_version_ 1783711805946724352
author Zhang, Jack
Boora, Naveenjyote
Melendez, Sarah
Rakkunedeth Hareendranathan, Abhilash
Jaremko, Jacob
author_facet Zhang, Jack
Boora, Naveenjyote
Melendez, Sarah
Rakkunedeth Hareendranathan, Abhilash
Jaremko, Jacob
author_sort Zhang, Jack
collection PubMed
description Wrist trauma is common in children, typically requiring radiography for diagnosis and treatment planning. However, many children do not have fractures and are unnecessarily exposed to radiation. Ultrasound performed at bedside could detect fractures prior to radiography. Modern tools including three-dimensional ultrasound (3DUS) and artificial intelligence (AI) have not yet been applied to this task. Our purpose was to assess (1) feasibility, reliability, and accuracy of 3DUS for detection of pediatric wrist fractures, and (2) accuracy of automated fracture detection via AI from 3DUS sweeps. Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned on both the affected and unaffected limb. Radiographs of the symptomatic limb were obtained for comparison. Ultrasound scans were read by three individuals to determine reliability. An AI network was trained and compared against the human readers. Thirty participants were enrolled, resulting in scans from fifty-five wrists. Readers had a combined sensitivity of 1.00 and specificity of 0.90 for fractures. AI interpretation was indistinguishable from human interpretation, with all fractures detected in the test set of 36 images (sensitivity = 1.0). The high sensitivity of 3D ultrasound and automated AI ultrasound interpretation suggests that ultrasound could potentially rule out fractures in the emergency department.
format Online
Article
Text
id pubmed-8224020
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82240202021-06-25 Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries Zhang, Jack Boora, Naveenjyote Melendez, Sarah Rakkunedeth Hareendranathan, Abhilash Jaremko, Jacob Children (Basel) Article Wrist trauma is common in children, typically requiring radiography for diagnosis and treatment planning. However, many children do not have fractures and are unnecessarily exposed to radiation. Ultrasound performed at bedside could detect fractures prior to radiography. Modern tools including three-dimensional ultrasound (3DUS) and artificial intelligence (AI) have not yet been applied to this task. Our purpose was to assess (1) feasibility, reliability, and accuracy of 3DUS for detection of pediatric wrist fractures, and (2) accuracy of automated fracture detection via AI from 3DUS sweeps. Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned on both the affected and unaffected limb. Radiographs of the symptomatic limb were obtained for comparison. Ultrasound scans were read by three individuals to determine reliability. An AI network was trained and compared against the human readers. Thirty participants were enrolled, resulting in scans from fifty-five wrists. Readers had a combined sensitivity of 1.00 and specificity of 0.90 for fractures. AI interpretation was indistinguishable from human interpretation, with all fractures detected in the test set of 36 images (sensitivity = 1.0). The high sensitivity of 3D ultrasound and automated AI ultrasound interpretation suggests that ultrasound could potentially rule out fractures in the emergency department. MDPI 2021-05-21 /pmc/articles/PMC8224020/ /pubmed/34063945 http://dx.doi.org/10.3390/children8060431 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
Zhang, Jack
Boora, Naveenjyote
Melendez, Sarah
Rakkunedeth Hareendranathan, Abhilash
Jaremko, Jacob
Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries
title Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries
title_full Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries
title_fullStr Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries
title_full_unstemmed Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries
title_short Diagnostic Accuracy of 3D Ultrasound and Artificial Intelligence for Detection of Pediatric Wrist Injuries
title_sort diagnostic accuracy of 3d ultrasound and artificial intelligence for detection of pediatric wrist injuries
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224020/
https://www.ncbi.nlm.nih.gov/pubmed/34063945
http://dx.doi.org/10.3390/children8060431
work_keys_str_mv AT zhangjack diagnosticaccuracyof3dultrasoundandartificialintelligencefordetectionofpediatricwristinjuries
AT booranaveenjyote diagnosticaccuracyof3dultrasoundandartificialintelligencefordetectionofpediatricwristinjuries
AT melendezsarah diagnosticaccuracyof3dultrasoundandartificialintelligencefordetectionofpediatricwristinjuries
AT rakkunedethhareendranathanabhilash diagnosticaccuracyof3dultrasoundandartificialintelligencefordetectionofpediatricwristinjuries
AT jaremkojacob diagnosticaccuracyof3dultrasoundandartificialintelligencefordetectionofpediatricwristinjuries