Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children.
Artificial intelligence
Children
Convolutional neural networks
Deep learning
Emergency medicine, Fracture
Radiography
Journal
Pediatric radiology
ISSN: 1432-1998
Titre abrégé: Pediatr Radiol
Pays: Germany
ID NLM: 0365332
Informations de publication
Date de publication:
07 2023
07 2023
Historique:
received:
30
11
2021
accepted:
30
01
2023
revised:
21
11
2022
medline:
21
7
2023
pubmed:
7
3
2023
entrez:
6
3
2023
Statut:
ppublish
Résumé
Advances have been made in the use of artificial intelligence (AI) in the field of diagnostic imaging, particularly in the detection of fractures on conventional radiographs. Studies looking at the detection of fractures in the pediatric population are few. The anatomical variations and evolution according to the child's age require specific studies of this population. Failure to diagnose fractures early in children may lead to serious consequences for growth. To evaluate the performance of an AI algorithm based on deep neural networks toward detecting traumatic appendicular fractures in a pediatric population. To compare sensitivity, specificity, positive predictive value and negative predictive value of different readers and the AI algorithm. This retrospective study conducted on 878 patients younger than 18 years of age evaluated conventional radiographs obtained after recent non-life-threatening trauma. All radiographs of the shoulder, arm, elbow, forearm, wrist, hand, leg, knee, ankle and foot were evaluated. The diagnostic performance of a consensus of radiology experts in pediatric imaging (reference standard) was compared with those of pediatric radiologists, emergency physicians, senior residents and junior residents. The predictions made by the AI algorithm and the annotations made by the different physicians were compared. The algorithm predicted 174 fractures out of 182, corresponding to a sensitivity of 95.6%, a specificity of 91.64% and a negative predictive value of 98.76%. The AI predictions were close to that of pediatric radiologists (sensitivity 98.35%) and that of senior residents (95.05%) and were above those of emergency physicians (81.87%) and junior residents (90.1%). The algorithm identified 3 (1.6%) fractures not initially seen by pediatric radiologists. This study suggests that deep learning algorithms can be useful in improving the detection of fractures in children.
Sections du résumé
BACKGROUND
Advances have been made in the use of artificial intelligence (AI) in the field of diagnostic imaging, particularly in the detection of fractures on conventional radiographs. Studies looking at the detection of fractures in the pediatric population are few. The anatomical variations and evolution according to the child's age require specific studies of this population. Failure to diagnose fractures early in children may lead to serious consequences for growth.
OBJECTIVE
To evaluate the performance of an AI algorithm based on deep neural networks toward detecting traumatic appendicular fractures in a pediatric population. To compare sensitivity, specificity, positive predictive value and negative predictive value of different readers and the AI algorithm.
MATERIALS AND METHODS
This retrospective study conducted on 878 patients younger than 18 years of age evaluated conventional radiographs obtained after recent non-life-threatening trauma. All radiographs of the shoulder, arm, elbow, forearm, wrist, hand, leg, knee, ankle and foot were evaluated. The diagnostic performance of a consensus of radiology experts in pediatric imaging (reference standard) was compared with those of pediatric radiologists, emergency physicians, senior residents and junior residents. The predictions made by the AI algorithm and the annotations made by the different physicians were compared.
RESULTS
The algorithm predicted 174 fractures out of 182, corresponding to a sensitivity of 95.6%, a specificity of 91.64% and a negative predictive value of 98.76%. The AI predictions were close to that of pediatric radiologists (sensitivity 98.35%) and that of senior residents (95.05%) and were above those of emergency physicians (81.87%) and junior residents (90.1%). The algorithm identified 3 (1.6%) fractures not initially seen by pediatric radiologists.
CONCLUSION
This study suggests that deep learning algorithms can be useful in improving the detection of fractures in children.
Identifiants
pubmed: 36877239
doi: 10.1007/s00247-023-05621-w
pii: 10.1007/s00247-023-05621-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1675-1684Informations de copyright
© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Références
He K, Zhang X, Ren S, Sun J (2015) Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In: 2015 IEEE International Conference on Computer Vision (ICCV) pp 1026–1034
Hua K-L, Hsu C-H, Hidayati SC et al (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Onco Targets Ther 8:2015–2022
pubmed: 26346558
pmcid: 4531007
Nishio M, Sugiyama O, Yakami M et al (2018) Computer-aided diagnosis of lung nodule classification between benign nodule, primary lung cancer, and metastatic lung cancer at different image size using deep convolutional neural network with transfer learning. PLoS ONE 13:e0200721
doi: 10.1371/journal.pone.0200721
pubmed: 30052644
pmcid: 6063408
Kleppe A, Skrede O-J, De Raedt S et al (2021) Designing deep learning studies in cancer diagnostics. Nat Rev Cancer 21:199–211
doi: 10.1038/s41568-020-00327-9
pubmed: 33514930
Kalmet PHS, Sanduleanu S, Primakov S et al (2020) Deep learning in fracture detection: a narrative review. Acta Orthop 91:215–220
doi: 10.1080/17453674.2019.1711323
pubmed: 31928116
pmcid: 7144272
Duron L, Ducarouge A, Gillibert A et al (2021) Assessment of an AI aid in detection of adult appendicular skeletal fractures by emergency physicians and radiologists: A multicenter cross-sectional diagnostic study. Radiology 300:120–129
doi: 10.1148/radiol.2021203886
pubmed: 33944629
Reichert G, Bellamine A, Fontaine M et al (2021) How can a deep learning algorithm improve fracture detection on x-rays in the emergency room? J Imaging 7:105
doi: 10.3390/jimaging7070105
pmcid: 8321374
Cheng C-T, Wang Y, Chen H-W et al (2021) A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs. Nat Commun 12:1066
doi: 10.1038/s41467-021-21311-3
pubmed: 33594071
pmcid: 7887334
Kitamura G (2020) Deep learning evaluation of pelvic radiographs for position, hardware presence, and fracture detection. Eur J Radiol 130:109139
doi: 10.1016/j.ejrad.2020.109139
pubmed: 32623269
pmcid: 7483754
Gan K, Xu D, Lin Y et al (2019) Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop 90:394–400
doi: 10.1080/17453674.2019.1600125
pubmed: 30942136
pmcid: 6718190
Chung SW, Han SS, Lee JW et al (2018) Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop 89:468–473
doi: 10.1080/17453674.2018.1453714
pubmed: 29577791
pmcid: 6066766
Raisuddin AM, Vaattovaara E, Nevalainen M et al (2021) Critical evaluation of deep neural networks for wrist fracture detection. Sci Rep 11:6006
doi: 10.1038/s41598-021-85570-2
pubmed: 33727668
pmcid: 7971048
Jones RM, Sharma A, Hotchkiss R et al (2020) Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. Npj Digit Med 3:1–6
doi: 10.1038/s41746-020-00352-w
Olczak J, Fahlberg N, Maki A et al (2017) Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms-are they on par with humans for diagnosing fractures? Acta Orthop 88:581–586
doi: 10.1080/17453674.2017.1344459
pubmed: 28681679
pmcid: 5694800
Kim DH, MacKinnon T (2018) Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol 73:439–445
doi: 10.1016/j.crad.2017.11.015
pubmed: 29269036
Guermazi A, Tannoury C, Kompel AJ et al (2022) Improving radiographic fracture recognition performance and efficiency using Artificial Intelligence. Radiology 302:627–636
doi: 10.1148/radiol.210937
pubmed: 34931859
Hayashi D, Kompel AJ, Ventre J et al (2022) Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning. Skeletal Radiol 51:2129–2139
doi: 10.1007/s00256-022-04070-0
pubmed: 35522332
Nguyen T, Maarek R, Hermann AL et al (2022) Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists. Pediatr Radiol 52:2215–2226
doi: 10.1007/s00247-022-05496-3
pubmed: 36169667
Cheng JC, Shen WY (1993) Limb fracture pattern in different pediatric age groups: a study of 3,350 children. J Orthop Trauma 7:15–22
doi: 10.1097/00005131-199302000-00004
pubmed: 8433194
Wei C-J, Tsai W-C, Tiu C-M et al (2006) Systematic Analysis of Missed Extremity Fractures in Emergency Radiology. Acta Radiol 47:710–717
doi: 10.1080/02841850600806340
pubmed: 16950710
Moonen P-J, Mercelina L, Boer W, Fret T (2017) Diagnostic error in the Emergency Department: follow up of patients with minor trauma in the outpatient clinic. Scand J Trauma Resusc Emerg Med 25:13
doi: 10.1186/s13049-017-0361-5
pubmed: 28196544
pmcid: 5309992
Lin T-Y, Goyal P, Girshick R, He K, Dollar P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42:318–327
doi: 10.1109/TPAMI.2018.2858826
pubmed: 30040631
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. ArXiv Prepr ArXiv14091556. Available from https://arxiv.org/abs/1409.1556 . Accessed 29 Oct 2022
Kingma DP, Ba J. Adam: A Method for Stochastic Optimization. ArXiv14126980 Cs [Internet]. 2017 Jan 29 [cited 2021 May 9]; Available from: http://arxiv.org/abs/1412.6980 . Accessed 29 Oct 2022
Urakawa T, Tanaka Y, Goto S et al (2019) Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal Radiol 48:23–244
doi: 10.1007/s00256-018-3016-3
Offiah AC (2022) Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology. Pediatr Radiol 52:2149–2158
doi: 10.1007/s00247-021-05130-8
pubmed: 34272573
Gaube S, Suresh H, Raue M et al (2021) Do as AI say: susceptibility in deployment of clinical decision-aids. Npj Digit Med 4:1–8
doi: 10.1038/s41746-021-00385-9