Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures.
Aged
Algorithms
Bone Density
/ physiology
Feasibility Studies
Female
Humans
Imaging, Three-Dimensional
/ methods
Incidental Findings
Male
Mass Screening
/ methods
Middle Aged
Osteoporosis
/ diagnostic imaging
Osteoporotic Fractures
/ diagnostic imaging
Radiographic Image Interpretation, Computer-Assisted
/ methods
Retrospective Studies
Spinal Fractures
/ diagnostic imaging
Tomography, X-Ray Computed
/ methods
BMD
Machine learning
Opportunistic screening
Osteoporosis
Quantitative computed tomography
Random forest model
Texture analysis
Vertebral fractures
Journal
Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA
ISSN: 1433-2965
Titre abrégé: Osteoporos Int
Pays: England
ID NLM: 9100105
Informations de publication
Date de publication:
Jun 2019
Jun 2019
Historique:
received:
17
08
2018
accepted:
18
02
2019
pubmed:
5
3
2019
medline:
7
1
2020
entrez:
5
3
2019
Statut:
ppublish
Résumé
Our study proposed an automatic pipeline for opportunistic osteoporosis screening using 3D texture features and regional vBMD using multi-detector CT images. A combination of different local and global texture features outperformed the global vBMD and showed high discriminative power to identify patients with vertebral fractures. Many patients at risk for osteoporosis undergo computed tomography (CT) scans, usable for opportunistic (non-dedicated) screening. We compared the performance of global volumetric bone mineral density (vBMD) with a random forest classifier based on regional vBMD and 3D texture features to separate patients with and without osteoporotic fractures. In total, 154 patients (mean age 64 ± 8.5, male; n = 103) were included in this retrospective single-center analysis, who underwent contrast-enhanced CT for other reasons than osteoporosis screening. Patients were dichotomized regarding prevalent vertebral osteoporotic fractures (noFX, n = 101; FX, n = 53). Vertebral bodies were automatically segmented, and trabecular vBMD was calculated with a dedicated phantom. For 3D texture analysis, we extracted gray-level co-occurrence matrix Haralick features (HAR), histogram of gradients (HoG), local binary patterns (LBP), and wavelets (WL). Fractured vertebrae were excluded for texture-feature and vBMD data extraction. The performance to identify patients with prevalent osteoporotic vertebral fractures was evaluated in a fourfold cross-validation. The random forest classifier showed a high discriminatory power (AUC = 0.88). Parameters of all vertebral levels significantly contributed to this classification. Importantly, the AUC of the proposed algorithm was significantly higher than that of volumetric global BMD alone (AUC = 0.64). The presented classifier combining 3D texture features and regional vBMD including the complete thoracolumbar spine showed high discriminatory power to identify patients with vertebral fractures and had a better diagnostic performance than vBMD alone.
Identifiants
pubmed: 30830261
doi: 10.1007/s00198-019-04910-1
pii: 10.1007/s00198-019-04910-1
pmc: PMC6546649
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1275-1285Subventions
Organisme : H2020 European Research Council
ID : 637164
Références
Center JR, Nguyen TV, Schneider D, Sambrook PN, Eisman JA (1999) Mortality after all major types of osteoporotic fracture in men and women: an observational study. Lancet 353:878–882. https://doi.org/10.1016/S0140-6736(98)09075-8
doi: 10.1016/S0140-6736(98)09075-8
pubmed: 10093980
Kaesmacher J, Schweizer C, Valentinitsch A, Baum T, Rienmüller A, Meyer B, Kirschke JS, Ryang YM (2017) Osteoporosis is the most important risk factor for odontoid fractures in the elderly. J Bone Miner Res 32:1582–1588. https://doi.org/10.1002/jbmr.3120
doi: 10.1002/jbmr.3120
pubmed: 28256741
Kanis JA, McCloskey EV, Johansson H, Cooper C, Rizzoli R, Reginster J-Y et al (2013) European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporos Int 24:23–57. https://doi.org/10.1007/s00198-012-2074-y
doi: 10.1007/s00198-012-2074-y
pubmed: 23079689
Cummings SR, Bates D, Black DM (2002) Clinical use of bone densitometry: scientific review. JAMA 288:1889–1897
doi: 10.1001/jama.288.15.1889
pubmed: 12377088
Wang X, Sanyal A, Cawthon PM, Palermo L, Jekir M, Christensen J, Ensrud KE, Cummings SR, Orwoll E, Black DM, for the Osteoporotic Fractures in Men (MrOS) Research Group, Keaveny TM (2012) Prediction of new clinical vertebral fractures in elderly men using finite element analysis of CT scans. J Bone Miner Res 27:808–816. https://doi.org/10.1002/jbmr.1539
doi: 10.1002/jbmr.1539
pubmed: 22190331
pmcid: 3510751
Engelke K (2017) Quantitative computed tomography-current status and new developments. J Clin Densitom 20:309–321. https://doi.org/10.1016/j.jocd.2017.06.017
doi: 10.1016/j.jocd.2017.06.017
pubmed: 28712984
Melton LJ, Riggs BL, Keaveny TM, Achenbach SJ, Kopperdahl D, Camp JJ et al (2010) Relation of vertebral deformities to bone density, structure, and strength. J Bone Miner Res 25:1922–1930. https://doi.org/10.1002/jbmr.150
doi: 10.1002/jbmr.150
pubmed: 20533526
pmcid: 3153401
Issever AS, Link TM, Kentenich M, Rogalla P, Schwieger K, Huber MB, Burghardt AJ, Majumdar S, Diederichs G (2009) Trabecular bone structure analysis in the osteoporotic spine using a clinical in vivo setup for 64-slice MDCT imaging: comparison to microCT imaging and microFE modeling. J Bone Miner Res 24:1628–1637. https://doi.org/10.1359/jbmr.090311
doi: 10.1359/jbmr.090311
pubmed: 19338434
Damilakis J, Adams JE, Guglielmi G, Link TM (2010) Radiation exposure in X-ray-based imaging techniques used in osteoporosis. Eur Radiol 20:2707–2714. https://doi.org/10.1007/s00330-010-1845-0
doi: 10.1007/s00330-010-1845-0
pubmed: 20559834
pmcid: 2948153
Schwaiger BJ, Kopperdahl DL, Nardo L, Facchetti L, Gersing AS, Neumann J, Lee KJ, Keaveny TM, Link TM (2017) Vertebral and femoral bone mineral density and bone strength in prostate cancer patients assessed in phantomless PET/CT examinations. Bone 101:62–69. https://doi.org/10.1016/j.bone.2017.04.008
doi: 10.1016/j.bone.2017.04.008
pubmed: 28442297
pmcid: 5506071
Lee DC, Hoffmann PF, Kopperdahl DL, Keaveny TM (2017) Phantomless calibration of CT scans for measurement of BMD and bone strength-inter-operator reanalysis precision. Bone 103:325–333. https://doi.org/10.1016/j.bone.2017.07.029
doi: 10.1016/j.bone.2017.07.029
pubmed: 28778598
pmcid: 5636218
Genant HK, Wu CY, van Kuijk C, Nevitt MC (1993) Vertebral fracture assessment using a semiquantitative technique. J Bone Miner Res 8:1137–1148. https://doi.org/10.1002/jbmr.5650080915
doi: 10.1002/jbmr.5650080915
pubmed: 8237484
Kaesmacher J, Liebl H, Baum T, Kirschke JS (2017) Bone mineral density estimations from routine multidetector computed tomography: a comparative study of contrast and calibration effects. J Comput Assist Tomogr 41:217–223. https://doi.org/10.1097/RCT.0000000000000518
doi: 10.1097/RCT.0000000000000518
pubmed: 27798444
pmcid: 5359785
Hussein AI, Jackman TM, Morgan SR, Barest GD, Morgan EF (2013) The intravertebral distribution of bone density: correspondence to intervertebral disc health and implications for vertebral strength. Osteoporos Int 24:3021–3030. https://doi.org/10.1007/s00198-013-2417-3
doi: 10.1007/s00198-013-2417-3
pubmed: 23863990
pmcid: 4465501
Valentinitsch A, Trebeschi S, Alarcón E, Baum T, Kaesmacher J, Zimmer C, Lorenz C, Kirschke JS (2017) Regional analysis of age-related local bone loss in the spine of a healthy population using 3D voxel-based modeling. Bone 103:233–240. https://doi.org/10.1016/j.bone.2017.06.013
doi: 10.1016/j.bone.2017.06.013
pubmed: 28716553
Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C (2009) Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 13:471–482. https://doi.org/10.1016/j.media.2009.02.004
doi: 10.1016/j.media.2009.02.004
pubmed: 19285910
Klein S, Pluim JPW, Staring M, Viergever MA (2008) Adaptive stochastic gradient descent optimisation for image registration. Int J Comput Vis 81:227–239. https://doi.org/10.1007/s11263-008-0168-y
doi: 10.1007/s11263-008-0168-y
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern Syst 3:610–621. https://doi.org/10.1109/TSMC.1973.4309314
doi: 10.1109/TSMC.1973.4309314
Albregtsen F (1995) Statistical texture measures computed from gray level coocurrence matrices. Image Processing Laboratory
Klaser A, Marszalek M, Schmid C. A Spatio-Temporal Descriptor Based on 3D-Gradients. 2008
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987. https://doi.org/10.1109/TPAMI.2002.1017623
doi: 10.1109/TPAMI.2002.1017623
Fehr J, Burkhardt H. 3D rotation invariant local binary patterns.2008. pp. 1–4. doi: https://doi.org/10.1109/ICPR.2008.4761098
Leung T, Malik J (2001) Representing and recognizing the visual appearance of materials using three-dimensional Textons | SpringerLink. Int J Comput Vis 43:29–44
doi: 10.1023/A:1011126920638
Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation- IEEE Xplore Document. IEEE Trans Pattern Anal Machine Intell 11:674–693
doi: 10.1109/34.192463
Akbarizadeh G (2012) A new statistical-based kurtosis wavelet energy feature for texture recognition of SAR images- IEEE Xplore Document. IEEE Trans Geosci Remote Sens 50:4358–4368
doi: 10.1109/TGRS.2012.2194787
Breiman L (2001) Random forests. Mach Learn 45
Verikas A, Gelzinis A, Bacauskiene M (2011) Mining data with random forests: a survey and results of new tests. Pattern Recogn 44:330–349
doi: 10.1016/j.patcog.2010.08.011
Statnikov A, Wang L, Aliferis CF (2008) A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification. BMC Bioinformatics 9:319. https://doi.org/10.1186/1471-2105-9-319
doi: 10.1186/1471-2105-9-319
pubmed: 18647401
pmcid: 2492881
Mueller DK, Kutscherenko A, Bartel H, Vlassenbroek A, Ourednicek P, Erckenbrecht J (2011) Phantom-less QCT BMD system as screening tool for osteoporosis without additional radiation. Eur J Radiol 79:375–381. https://doi.org/10.1016/j.ejrad.2010.02.008
doi: 10.1016/j.ejrad.2010.02.008
pubmed: 20223609
Engelke K, Libanati C, Liu Y, Wang H, Austin M, Fuerst T, Stampa B, Timm W, Genant HK (2009) Quantitative computed tomography (QCT) of the forearm using general purpose spiral whole-body CT scanners: accuracy, precision and comparison with dual-energy X-ray absorptiometry (DXA). Bone 45:110–118. https://doi.org/10.1016/j.bone.2009.03.669
doi: 10.1016/j.bone.2009.03.669
pubmed: 19345291
Mao SS, Li D, Luo Y, Syed YS, Budoff MJ (2016) Application of quantitative computed tomography for assessment of trabecular bone mineral density, microarchitecture and mechanical property. Clin Imaging 40:330–338. https://doi.org/10.1016/j.clinimag.2015.09.016
doi: 10.1016/j.clinimag.2015.09.016
pubmed: 26602163
Brown JK, Timm W, Bodeen G, Chason A, Perry M, Vernacchia F, DeJournett R (2016) Asynchronously calibrated quantitative bone densitometry. J Clin Densitom 20:216–225. https://doi.org/10.1016/j.jocd.2015.11.001
doi: 10.1016/j.jocd.2015.11.001
pubmed: 26781430
Eckstein F, Lochmüller E-M, Lill CA, Kuhn V, Schneider E, Delling G, Müller R (2002) Bone strength at clinically relevant sites displays substantial heterogeneity and is best predicted from site-specific bone densitometry. J Bone Miner Res 17:162–171. https://doi.org/10.1359/jbmr.2002.17.1.162
doi: 10.1359/jbmr.2002.17.1.162
pubmed: 11771664
Matsumoto T, Ohnishi I, Bessho M, Imai K, Ohashi S, Nakamura K (2009) Prediction of vertebral strength under loading conditions occurring in activities of daily living using a computed tomography-based nonlinear finite element method. Spine 34:1464–1469. https://doi.org/10.1097/BRS.0b013e3181a55636
doi: 10.1097/BRS.0b013e3181a55636
pubmed: 19525837
Dragomir-Daescu D, Salas C, Uthamaraj S, Rossman T (2015) Quantitative computed tomography-based finite element analysis predictions of femoral strength and stiffness depend on computed tomography settings. J Biomech 48:153–161. https://doi.org/10.1016/j.jbiomech.2014.09.016
doi: 10.1016/j.jbiomech.2014.09.016
pubmed: 25442008
McCloskey EV, Odén A, Harvey NC, Leslie WD, Hans D, Johansson H et al (2016) A meta-analysis of trabecular bone score in fracture risk prediction and its relationship to FRAX. J Bone Miner Res 31:940–948. https://doi.org/10.1002/jbmr.2734
doi: 10.1002/jbmr.2734
pubmed: 26498132
Räth C, Monetti R, Bauer J, Sidorenko I, Müller D, Matsuura M, Lochmüller EM, Zysset P, Eckstein F (2008) Strength through structure: visualization and local assessment of the trabecular bone structure. New J Phys 10:125010. https://doi.org/10.1088/1367-2630/10/12/125010
doi: 10.1088/1367-2630/10/12/125010
Valentinitsch A, Patsch JM, Burghardt AJ, Link TM, Majumdar S, Fischer L, Schueller-Weidekamm C, Resch H, Kainberger F, Langs G (2013) Computational identification and quantification of trabecular microarchitecture classes by 3-D texture analysis-based clustering. Bone 54:133–140. https://doi.org/10.1016/j.bone.2012.12.047
doi: 10.1016/j.bone.2012.12.047
pubmed: 23313281
Fischer L, Valentinitsch A, DiFranco MD, Schueller-Weidekamm C, Kienzl D, Resch H et al (2015) High-resolution peripheral quantitative CT imaging: cortical porosity, poor trabecular bone microarchitecture, and low bone strength in lung transplant recipients. Radiology 274:473–481. https://doi.org/10.1148/radiol.14140201
doi: 10.1148/radiol.14140201
pubmed: 25299786
Couronné R, Probst P, Boulesteix AL. Random forest versus logistic regression: a large-scale benchmark experiment. 2017
Kanis JA, Johnell O, Oden A, Johansson H, McCloskey E (2008) FRAX and the assessment of fracture probability in men and women from the UK. Osteoporos Int 19:385–397. https://doi.org/10.1007/s00198-007-0543-5
doi: 10.1007/s00198-007-0543-5
pubmed: 18292978
pmcid: 2267485
Donaldson MG, Palermo L, Schousboe JT, Ensrud KE, Hochberg MC, Cummings SR (2009) FRAX and risk of vertebral fractures: the fracture intervention trial. J Bone Miner Res 24:1793–1799. https://doi.org/10.1359/jbmr.090511
doi: 10.1359/jbmr.090511
pubmed: 19419318
Bouxsein ML, Melton LJ, Riggs BL, Muller J, Atkinson EJ, Oberg AL et al (2006) Age- and sex-specific differences in the factor of risk for vertebral fracture: a population-based study using QCT. J Bone Miner Res 21:1475–1482. https://doi.org/10.1359/jbmr.060606
doi: 10.1359/jbmr.060606
pubmed: 16939406
Hussein AI, Morgan EF (2013) The effect of intravertebral heterogeneity in microstructure on vertebral strength and failure patterns. Osteoporos Int 24:979–989. https://doi.org/10.1007/s00198-012-2039-1
doi: 10.1007/s00198-012-2039-1
pubmed: 22707063
Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley-Interscience