Research output: Contribution to journal › Review article › Academic › peer-review
Artificial intelligence fracture recognition on computed tomography : review of literature and recommendations. / On Behalf of Machine Learning Consortium.
In: European journal of trauma, 2022.Research output: Contribution to journal › Review article › Academic › peer-review
}
TY - JOUR
T1 - Artificial intelligence fracture recognition on computed tomography
T2 - review of literature and recommendations
AU - Dankelman, Lente H. M.
AU - Schilstra, Sanne
AU - IJpma, Frank F. A.
AU - Doornberg, Job N.
AU - Colaris, Joost W.
AU - Verhofstad, Michael H. J.
AU - Wijffels, Mathieu M. E.
AU - Prijs, Jasper
AU - On Behalf of Machine Learning Consortium
AU - Algra, Paul
AU - van den Bekerom, Michel
AU - Bhandari, Mohit
AU - Bongers, Michiel
AU - Court-Brown, Charles
AU - Bulstra, Anne-Eva
AU - Buijze, Geert
AU - Bzovsky, Sofia
AU - Colaris, Joost
AU - Chen, Neil
AU - Doornberg, Job
AU - Duckworth, Andrew
AU - Goslings, J. Carel
AU - Gordon, Max
AU - Gravesteijn, Benjamin
AU - Groot, Olivier
AU - Guyatt, Gordon
AU - Hendrickx, Laurent
AU - Hintermann, Beat
AU - Hofstee, Dirk-Jan
AU - IJpma, Frank
AU - Jaarsma, Ruurd
AU - Janssen, Stein
AU - Jeray, Kyle
AU - Jutte, Paul
AU - Karhade, Aditya
AU - Keijser, Lucien
AU - Kerkhoffs, Gino
AU - Langerhuizen, David
AU - Lans, Jonathan
AU - Mallee, Wouter
AU - Moran, Matthew
AU - McQueen, Margaret
AU - Mulders, Marjolein
AU - Nelissen, Rob
AU - Obdeijn, Miryam
AU - Oberai, Tarandeep
AU - Olczak, Jakub
AU - Oosterhoff, Jacobien H. F.
AU - Petrisor, Brad
AU - Poolman, Rudolf
AU - Prijs, Jasper
AU - Ring, David
AU - Tornetta, Paul
AU - Sanders, David
AU - Schwab, Joseph
AU - Schemitsch, Emil H.
AU - Schep, Niels
AU - Schipper, Inger
AU - Schoolmeesters, Bram
AU - Schwab, Joseph
AU - Swiontkowski, Marc
AU - Sprague, Sheila
AU - Steyerberg, Ewout
AU - Stirler, Vincent
AU - Tornetta, Paul
AU - Walter, Stephen D.
AU - Walenkamp, Monique
AU - Wijffels, Mathieu
AU - Laane, Charlotte
N1 - Publisher Copyright: © 2022, The Author(s).
PY - 2022
Y1 - 2022
N2 - Purpose: The use of computed tomography (CT) in fractures is time consuming, challenging and suffers from poor inter-surgeon reliability. Convolutional neural networks (CNNs), a subset of artificial intelligence (AI), may overcome shortcomings and reduce clinical burdens to detect and classify fractures. The aim of this review was to summarize literature on CNNs for the detection and classification of fractures on CT scans, focusing on its accuracy and to evaluate the beneficial role in daily practice. Methods: Literature search was performed according to the PRISMA statement, and Embase, Medline ALL, Web of Science Core Collection, Cochrane Central Register of Controlled Trials and Google Scholar databases were searched. Studies were eligible when the use of AI for the detection of fractures on CT scans was described. Quality assessment was done with a modified version of the methodologic index for nonrandomized studies (MINORS), with a seven-item checklist. Performance of AI was defined as accuracy, F1-score and area under the curve (AUC). Results: Of the 1140 identified studies, 17 were included. Accuracy ranged from 69 to 99%, the F1-score ranged from 0.35 to 0.94 and the AUC, ranging from 0.77 to 0.95. Based on ten studies, CNN showed a similar or improved diagnostic accuracy in addition to clinical evaluation only. Conclusions: CNNs are applicable for the detection and classification fractures on CT scans. This can improve automated and clinician-aided diagnostics. Further research should focus on the additional value of CNN used for CT scans in daily clinics.
AB - Purpose: The use of computed tomography (CT) in fractures is time consuming, challenging and suffers from poor inter-surgeon reliability. Convolutional neural networks (CNNs), a subset of artificial intelligence (AI), may overcome shortcomings and reduce clinical burdens to detect and classify fractures. The aim of this review was to summarize literature on CNNs for the detection and classification of fractures on CT scans, focusing on its accuracy and to evaluate the beneficial role in daily practice. Methods: Literature search was performed according to the PRISMA statement, and Embase, Medline ALL, Web of Science Core Collection, Cochrane Central Register of Controlled Trials and Google Scholar databases were searched. Studies were eligible when the use of AI for the detection of fractures on CT scans was described. Quality assessment was done with a modified version of the methodologic index for nonrandomized studies (MINORS), with a seven-item checklist. Performance of AI was defined as accuracy, F1-score and area under the curve (AUC). Results: Of the 1140 identified studies, 17 were included. Accuracy ranged from 69 to 99%, the F1-score ranged from 0.35 to 0.94 and the AUC, ranging from 0.77 to 0.95. Based on ten studies, CNN showed a similar or improved diagnostic accuracy in addition to clinical evaluation only. Conclusions: CNNs are applicable for the detection and classification fractures on CT scans. This can improve automated and clinician-aided diagnostics. Further research should focus on the additional value of CNN used for CT scans in daily clinics.
KW - Artificial intelligence
KW - Computed tomography
KW - Convolutional neural networks
KW - Fractures
KW - Orthopedics
UR - http://www.scopus.com/inward/record.url?scp=85141035490&partnerID=8YFLogxK
U2 - 10.1007/s00068-022-02128-1
DO - 10.1007/s00068-022-02128-1
M3 - Review article
C2 - 36284017
JO - European journal of trauma
JF - European journal of trauma
SN - 1439-0590
ER -
ID: 27115792