Skip to main content
Top
Published in:

Open Access 16-01-2024 | Magnetic Resonance Imaging

Detecting Avascular Necrosis of the Lunate from Radiographs Using a Deep-Learning Model

Authors: Krista Wernér, Turkka Anttila, Sina Hulkkonen, Timo Viljakka, Ville Haapamäki, Jorma Ryhänen

Published in: Journal of Imaging Informatics in Medicine | Issue 2/2024

Login to get access

Abstract

Deep-learning (DL) algorithms have the potential to change medical image classification and diagnostics in the coming decade. Delayed diagnosis and treatment of avascular necrosis (AVN) of the lunate may have a detrimental effect on patient hand function. The aim of this study was to use a segmentation-based DL model to diagnose AVN of the lunate from wrist postero-anterior radiographs. A total of 319 radiographs of the diseased lunate and 1228 control radiographs were gathered from Helsinki University Central Hospital database. Of these, 10% were separated to form a test set for model validation. MRI confirmed the absence of disease. In cases of AVN of the lunate, a hand surgeon at Helsinki University Hospital validated the accurate diagnosis using either MRI or radiography. For detection of AVN, the model had a sensitivity of 93.33% (95% confidence interval (CI) 77.93–99.18%), specificity of 93.28% (95% CI 87.18–97.05%), and accuracy of 93.28% (95% CI 87.99–96.73%). The area under the receiver operating characteristic curve was 0.94 (95% CI 0.88–0.99). Compared to three clinical experts, the DL model had better AUC than one clinical expert and only one expert had higher accuracy than the DL model. The results were otherwise similar between the model and clinical experts. Our DL model performed well and may be a future beneficial tool for screening of AVN of the lunate.
Literature
1.
go back to reference F. Schuind, S. Eslami, P. Ledoux: Kienbock´s disease. J Bone Joint Surg Br, 90 (2008), pp. 133–139CrossRefPubMed F. Schuind, S. Eslami, P. Ledoux: Kienbock´s disease. J Bone Joint Surg Br, 90 (2008), pp. 133–139CrossRefPubMed
8.
go back to reference Bain G, MacLean S, Yeo C, Perilli E, Lichtman D: The Etiology and Pathogenesis of Kienböck Disease. J Wrist Surg. 2016;5(04):248–254CrossRef Bain G, MacLean S, Yeo C, Perilli E, Lichtman D: The Etiology and Pathogenesis of Kienböck Disease. J Wrist Surg. 2016;5(04):248–254CrossRef
9.
go back to reference Colin Kennedy, Reid Abrams: In Brief: The Lichtman Classification for Kienböck Disease. Clin Orthop Relat Res. 2019;477(6):1516–1520CrossRefPubMed Colin Kennedy, Reid Abrams: In Brief: The Lichtman Classification for Kienböck Disease. Clin Orthop Relat Res. 2019;477(6):1516–1520CrossRefPubMed
12.
go back to reference H A Haenssle, C Fink, R Schneiderbauer, F Toberer, T Buhl, A Blum: Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol. 2018;29(8):1836–1842. https://doi.org/10.1093/annonc/mdy166.CrossRefPubMed H A Haenssle, C Fink, R Schneiderbauer, F Toberer, T Buhl, A Blum: Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol. 2018;29(8):1836–1842. https://​doi.​org/​10.​1093/​annonc/​mdy166.CrossRefPubMed
14.
go back to reference Mary L McHugh: Interrater reliability: the kappa statistic. Biochem Med (Zagreb). 2012;22(3):276–82 Mary L McHugh: Interrater reliability: the kappa statistic. Biochem Med (Zagreb). 2012;22(3):276–82
15.
go back to reference Altman DG, Machin D, Bryant TN, Gardner MJ (Eds): Statistics with confidence, 2nd ed. BMJ Books, 2000 Altman DG, Machin D, Bryant TN, Gardner MJ (Eds): Statistics with confidence, 2nd ed. BMJ Books, 2000
16.
go back to reference Mercaldo ND, Lau KF, Zhou XH: Confidence intervals for predictive values with an emphasis to case-control studies. Statistics in Medicine 2007. 26:2170–2183CrossRefPubMed Mercaldo ND, Lau KF, Zhou XH: Confidence intervals for predictive values with an emphasis to case-control studies. Statistics in Medicine 2007. 26:2170–2183CrossRefPubMed
17.
go back to reference Choong Guen Chee, Youngjune Kim, Yusuhn Kang, Kyong Joon Lee, Hee-Dong Chae, Jungheum Cho, Chang-Mo Nam, Dongjun Choi, Eugene Lee, Joon Woo Lee, Sung Hwan Hong, Joong Mo Ahn, Heung Sik Kang: Performance of a Deep Learning Algorithm in Detecting Osteonecrosis of the Femoral Head on Digital Radiography: A Comparison With Assessments by Radiologists AJR Am J Roentgenol. 213(1):155–162 https://doi.org/10.2214/AJR.18.20817 Epub 2019 Mar 27 Choong Guen Chee, Youngjune Kim, Yusuhn Kang, Kyong Joon Lee, Hee-Dong Chae, Jungheum Cho, Chang-Mo Nam, Dongjun Choi, Eugene Lee, Joon Woo Lee, Sung Hwan Hong, Joong Mo Ahn, Heung Sik Kang: Performance of a Deep Learning Algorithm in Detecting Osteonecrosis of the Femoral Head on Digital Radiography: A Comparison With Assessments by Radiologists AJR Am J Roentgenol. 213(1):155–162 https://​doi.​org/​10.​2214/​AJR.​18.​20817 Epub 2019 Mar 27
18.
go back to reference Xianyue Shen, Jia Luo, Xiongfeng Tang, Bo Chen, Yanguo Qin, You Zhou, Jianlin Xiao: Deep Learning Approach for Diagnosing Early Osteonecrosis of the Femoral Head Based on Magnetic Resonance Imaging. J Arthroplasty. 2022;S0883–5403(22)00900–7. https://doi.org/10.1016/j.arth.2022.10.003. Online ahead of print. Xianyue Shen, Jia Luo, Xiongfeng Tang, Bo Chen, Yanguo Qin, You Zhou, Jianlin Xiao: Deep Learning Approach for Diagnosing Early Osteonecrosis of the Femoral Head Based on Magnetic Resonance Imaging. J Arthroplasty. 2022;S0883–5403(22)00900–7. https://​doi.​org/​10.​1016/​j.​arth.​2022.​10.​003. Online ahead of print.
19.
go back to reference Michail E Klontzas, Evangelia E Vassalou, Konstantinos Spanakis, Felix Meurer, Klaus Woertler, Aristeidis Zibis, Kostas Marias, Apostolos H Karantanas: Deep learning enables the differentiation between early and late stages of hip avascular necrosis. Eur Radiol. 2023 Aug 15. https://doi.org/10.1007/s00330-023-10104-5 Michail E Klontzas, Evangelia E Vassalou, Konstantinos Spanakis, Felix Meurer, Klaus Woertler, Aristeidis Zibis, Kostas Marias, Apostolos H Karantanas: Deep learning enables the differentiation between early and late stages of hip avascular necrosis. Eur Radiol. 2023 Aug 15. https://​doi.​org/​10.​1007/​s00330-023-10104-5
21.
go back to reference Adrian C Ruckli, Andreas K Nanavati, Malin K Meier, Till D Lerch, Simon D Steppacher, Sébastian Vuilleumier, Adam Boschung, Nicolas Vuillemin, Moritz Tannast, Klaus A Siebenrock, Nicolas Gerber, Florian Schmaranzer: A Deep Learning Method for Quantification of Femoral Head Necrosis Based on Routine Hip MRI for Improved Surgical Decision Making. J Pers Med. 2023;13(1):153. https://doi.org/10.3390/jpm13010153. Adrian C Ruckli, Andreas K Nanavati, Malin K Meier, Till D Lerch, Simon D Steppacher, Sébastian Vuilleumier, Adam Boschung, Nicolas Vuillemin, Moritz Tannast, Klaus A Siebenrock, Nicolas Gerber, Florian Schmaranzer: A Deep Learning Method for Quantification of Femoral Head Necrosis Based on Routine Hip MRI for Improved Surgical Decision Making. J Pers Med. 2023;13(1):153. https://​doi.​org/​10.​3390/​jpm13010153.
22.
25.
go back to reference David W G Langerhuizen, Anne Eva J Bulstra, Stein J Janssen, David Ring, Gino M M J Kerkhoffs, Ruurd L Jaarsma, Job N Doornberg: Is Deep Learning On Par with Human Observers for Detection of Radiographically Visible and Occult Fractures of the Scaphoid? Clin Orthop Relat Res. 2020;478(11):2653–2659. https://doi.org/10.1097/CORR.0000000000001318.CrossRef David W G Langerhuizen, Anne Eva J Bulstra, Stein J Janssen, David Ring, Gino M M J Kerkhoffs, Ruurd L Jaarsma, Job N Doornberg: Is Deep Learning On Par with Human Observers for Detection of Radiographically Visible and Occult Fractures of the Scaphoid? Clin Orthop Relat Res. 2020;478(11):2653–2659. https://​doi.​org/​10.​1097/​CORR.​0000000000001318​.CrossRef
26.
go back to reference Tsujimoto R, Maeda J, Abe Y, Arima K, Tomita M, Koseki H, Kaida E, Aoyagi K, Osaki M: Epidemiology of Kienböck’s disease in middle-aged and elderly Japanese women. Orthopedics. 2015;38(1):e14–e18CrossRefPubMed Tsujimoto R, Maeda J, Abe Y, Arima K, Tomita M, Koseki H, Kaida E, Aoyagi K, Osaki M: Epidemiology of Kienböck’s disease in middle-aged and elderly Japanese women. Orthopedics. 2015;38(1):e14–e18CrossRefPubMed
27.
go back to reference van Leeuwen W, Janssen S, ter Meulen D, Ring D: What Is the Radiographic Prevalence of Incidental Kienböck Disease? Clin Orthop Relat Res. 2016;474(3):808–813CrossRefPubMed van Leeuwen W, Janssen S, ter Meulen D, Ring D: What Is the Radiographic Prevalence of Incidental Kienböck Disease? Clin Orthop Relat Res. 2016;474(3):808–813CrossRefPubMed
28.
go back to reference Mennen U, Sithebe H: The incidence of asymptomatic Kienböck’s disease. Journal of Hand Surgery: Eur Vol. 2009;34(3):348–350 Mennen U, Sithebe H: The incidence of asymptomatic Kienböck’s disease. Journal of Hand Surgery: Eur Vol. 2009;34(3):348–350
29.
go back to reference Saroj K Golay, Philippa Rust, David Ring: The Radiological Prevalence of Incidental Kienböck Disease. Arch Bone Jt Surg. 2016;4(3):220–3. Saroj K Golay, Philippa Rust, David Ring: The Radiological Prevalence of Incidental Kienböck Disease. Arch Bone Jt Surg. 2016;4(3):220–3.
Metadata
Title
Detecting Avascular Necrosis of the Lunate from Radiographs Using a Deep-Learning Model
Authors
Krista Wernér
Turkka Anttila
Sina Hulkkonen
Timo Viljakka
Ville Haapamäki
Jorma Ryhänen
Publication date
16-01-2024
Publisher
Springer International Publishing
Published in
Journal of Imaging Informatics in Medicine / Issue 2/2024
Print ISSN: 2948-2925
Electronic ISSN: 2948-2933
DOI
https://doi.org/10.1007/s10278-023-00964-0

Other articles of this Issue 2/2024

Journal of Imaging Informatics in Medicine 2/2024 Go to the issue