Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction
Radiology · 01.01.2024 · 310 (1)
DOI: 10.1148/radiol.230981 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology, erschienen am 01.01.2024. Verfasst von Kicky G van Leeuwen und 38 weiteren Autor:innen. Beteiligte Einrichtung: From the Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA Nijmegen, the Netherlands (K.G.v.L., S.…. Hauptthemen laut MEDLINE: Artificial Intelligence, Software. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 32 Literaturangaben.
Abstract (Originalsprache)
Background
Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited.
Purpose
To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience.
Results
Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range,
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- From the Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA Nijmegen, the Netherlands (K.G.v.L., S.S., M.J.C.M.R., M.H., C.M.S.P., M.d.R., B.v.G., B.H.J.G., J.M.); Depar…
ORCID-Profile: Kicky G van Leeuwen, Steven Schalekamp, Merel Huisman, Cornelia M Schaefer-Prokop, Maarten de Rooij, Bram van Ginneken, Bas Maresch, Bram H J Geurts, Cornelius F van Dijke, Emmeline Laupman-Koedam, Enzo V Hulleman, Eric L Verhoeff, Evelyne M J Meys, Firdaus A A Mohamed Hoesein, Floor M Ter Brugge, Inge A H van den Berk, James Meakin, Jesse Habets, Jonathan I M L Verbeke, Joost Nederend, Laura N Deden, Lucianne C M Langezaal, Mahtab Nasrollah, Martijn F Boomsma, Matthijs Vermeulen, Myrthe M Vestering, Onno Vijlbrief, Stijn M Bollen, Tijs Samson, Yntor H G von Brucken Fock
Zitieren
APA
van Leeuwen, K. G., Schalekamp, S., Rutten, M. J. C. M., Huisman, M., Schaefer-Prokop, C. M., de Rooij, M., van Ginneken, B., Maresch, B., Geurts, B. H. J., van Dijke, C. F., Laupman-Koedam, E., Hulleman, E. V., Verhoeff, E. L., Meys, E. M. J., Mohamed Hoesein, F. A. A., Ter Brugge, F. M., van Hoorn, F., van der Wel, F., van den Berk, I. A. H., …, & Project AIR Working Group (2024). Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction. Radiology, 310(1). https://doi.org/10.1148/radiol.230981
Vancouver
van Leeuwen KG, Schalekamp S, Rutten MJCM, Huisman M, Schaefer-Prokop CM, de Rooij M, et al. Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction. Radiology. 2024;310(1). doi:10.1148/radiol.230981
BibTeX
@article{vanLeeuwen2024,
author = {van Leeuwen, Kicky G and Schalekamp, Steven and Rutten, Matthieu J C M and Huisman, Merel and Schaefer-Prokop, Cornelia M and de Rooij, Maarten and van Ginneken, Bram and Maresch, Bas and Geurts, Bram H J and van Dijke, Cornelius F and Laupman-Koedam, Emmeline and Hulleman, Enzo V and Verhoeff, Eric L and Meys, Evelyne M J and Mohamed Hoesein, Firdaus A A and Ter Brugge, Floor M and van Hoorn, Francois and van der Wel, Frank and van den Berk, Inge A H and Luyendijk, Jacqueline M and Meakin, James and Habets, Jesse and Verbeke, Jonathan I M L and Nederend, Joost and Meys, Karlijn M E and Deden, Laura N and Langezaal, Lucianne C M and Nasrollah, Mahtab and Meij, Marleen and Boomsma, Martijn F and Vermeulen, Matthijs and Vestering, Myrthe M and Vijlbrief, Onno and Algra, Paul and Algra, Selma and Bollen, Stijn M and Samson, Tijs and von Brucken Fock, Yntor H G and Project AIR Working Group, Project AIR Working Group},
title = {Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction},
journal = {Radiology},
year = {2024},
volume = {310},
number = {1},
doi = {10.1148/radiol.230981}
}
EUVIMED