Automated Morphometric Analysis of the Hip Joint on MRI from the German National Cohort Study.

Anatomy Application Domain Computer Applications-3D Computer-Aided Diagnosis (CAD) Hip Interventional-MSK MR-Imaging Neural Networks Quantification Segmentation Skeletal-Appendicular Vision

Journal

Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556

Informations de publication

Date de publication:
Sep 2021
Historique:
received: 04 09 2020
revised: 03 05 2021
accepted: 17 05 2021
entrez: 7 10 2021
pubmed: 8 10 2021
medline: 8 10 2021
Statut: epublish

Résumé

To develop and validate an automated morphometric analysis framework for the quantitative analysis of geometric hip joint parameters in MR images from the German National Cohort (GNC) study. A secondary analysis on 40 participants (mean age, 51 years; age range, 30-67 years; 25 women) from the prospective GNC MRI study (2015-2016) was performed. Based on a proton density-weighted three-dimensional fast spin-echo sequence, a morphometric analysis approach was developed, including deep learning-based landmark localization, bone segmentation of the femora and pelvis, and a shape model for annotation transfer. The centrum-collum-diaphyseal, center-edge (CE), three alpha angles, head-neck offset (HNO), and HNO ratio along with the acetabular depth, inclination, and anteversion were derived. Quantitative validation was provided by comparison with average manual assessments of radiologists in a cross-validation format. Paired-sample High agreement in mean Dice similarity coefficients was achieved (average of 97.52% ± 0.46 [standard deviation]). The subsequent morphometric analysis produced results with low mean MAD values, with the highest values of 3.34° (alpha 03:00 o'clock position) and 0.87 mm (HNO) and ICC values ranging between 0.288 (HNO ratio) and 0.858 (CE) compared with manual assessments. These values were in line with interreader agreements, which at most had MAD values of 4.02° (alpha 12:00 o'clock position) and 1.07 mm (HNO) and ICC values ranging between 0.218 (HNO ratio) and 0.777 (CE). Automatic extraction of geometric hip parameters from MRI is feasible using a morphometric analysis approach with deep learning.

Identifiants

DOI: 10.1148/ryai.2021200213 PMID: 34617023 PMC: PMC8489451
pubmed: 34617023
doi: 10.1148/ryai.2021200213
pmc: PMC8489451
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e200213

Informations de copyright

2021 by the Radiological Society of North America, Inc.

Déclaration de conflit d'intérêts

Disclosures of Conflicts of Interest: M.F. Activities related to the present article: institution funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project number 325028047. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. S.S.W. Activities related to the present article: institution funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project number 325028047. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. T.H. disclosed no relevant relationships. M.Z. Activities related to the present article: institution funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project number 325028047. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. M.N. Activities related to the present article: institution received grant from German Research Council (grant number NO GZ: NO 1042/1-1 | SCHI 498/10-1 | YA 28/14-1) Automatisierte Segmentierung und Quantifizierung von geometrischen und strukturellen Parametern anhand von 3D-MRTDatensätzen der Hüftgelenke: Entwicklung zuverlässiger Algorithmen zur Datenanalyse in großen Kohortenstudien (Nationale Kohorte). Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. F.S. disclosed no relevant relationships. B.Y. disclosed no relevant relationships.

Références

Med Image Anal. 2009 Aug;13(4):543-63
pubmed: 19525140
Am J Sports Med. 2019 Oct;47(12):2966-2977
pubmed: 31486679
Ann Biomed Eng. 2010 May;38(5):1752-66
pubmed: 20177779
Eur Radiol. 2017 May;27(5):2011-2023
pubmed: 27578045
Ann Biomed Eng. 2013 Jun;41(6):1162-71
pubmed: 23413103
Skeletal Radiol. 2012 Jul;41(7):811-6
pubmed: 22064982
Skeletal Radiol. 2019 Mar;48(3):429-436
pubmed: 30182297
IEEE Trans Pattern Anal Mach Intell. 2010 Dec;32(12):2262-75
pubmed: 20975122
Sci Rep. 2018 Nov 7;8(1):16485
pubmed: 30405145
PLoS Med. 2015 Mar 31;12(3):e1001779
pubmed: 25826379
J Bone Joint Surg Am. 2010 Oct 20;92(14):2436-44
pubmed: 20962194
J Thorac Imaging. 2020 Nov 1;35(6):389-398
pubmed: 32349056
Magn Reson Med. 2018 Apr;79(4):2379-2391
pubmed: 28733975
Radiology. 2015 Oct;277(1):206-20
pubmed: 25989618
Bone Joint J. 2018 May 1;100-B(5):570-578
pubmed: 29701093
PLoS One. 2018 Oct 9;13(10):e0204961
pubmed: 30300421
Clin Orthop Relat Res. 2015 Jan;473(1):361-9
pubmed: 25261258
J Orthop Surg Res. 2020 May 27;15(1):192
pubmed: 32460899
Can Fam Physician. 2015 Dec;61(12):1055-60
pubmed: 26668284
Clin Orthop Relat Res. 2019 May;477(5):1036-1052
pubmed: 30998632
Radiology. 2006 Sep;240(3):778-85
pubmed: 16857978
Radiology. 2012 Aug;264(2):514-21
pubmed: 22653190
Clin Orthop Relat Res. 2009 Mar;467(3):666-75
pubmed: 19048356
J Hip Preserv Surg. 2015 Oct 22;2(4):392-400
pubmed: 27011864
J Orthop Sci. 2015 May;20(3):498-506
pubmed: 25740729
J Bone Joint Surg Am. 2014 Nov 5;96(21):1776-84
pubmed: 25378504
Phys Med Biol. 2015 Oct 7;60(19):7601-16
pubmed: 26390142
Int J Comput Assist Radiol Surg. 2020 Jan;15(1):109-118
pubmed: 31749053
PLoS One. 2016 Mar 02;11(3):e0149480
pubmed: 26933877
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026

Auteurs

Marc Fischer (M)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).
ORCID: 0000-0001-8892-0079

Sven S Walter (SS)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).
ORCID: 0000-0002-2870-825X

Tobias Hepp (T)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).
ORCID: 0000-0002-5241-9642

Manuela Zimmer (M)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).

Mike Notohamiprodjo (M)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).

Fritz Schick (F)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).
ORCID: 0000-0002-4231-3406

Bin Yang (B)

Institute of Signal Processing and Systems Theory, University of Stuttgart, Pfaffenwaldring 47, 70550 Stuttgart, Germany (M.F., M.Z., B.Y.); Department of Diagnostic and Interventional Radiology, Section on Experimental Radiology, University Hospital Tübingen, Tübingen, Germany (S.S.W., T.H., M.N., F.S.); and Empirical Inference Department, Max Planck Institute for Intelligent Systems, Tübingen, Germany (T.H.).

Classifications MeSH