CT-based radiomics can identify physiological modifications of bone structure related to subjects' age and sex.
Computed tomography
Lumbar vertebrae
Radiomics
Tissue characterization
Trabecular bone structure
Journal
La Radiologia medica
ISSN: 1826-6983
Titre abrégé: Radiol Med
Pays: Italy
ID NLM: 0177625
Informations de publication
Date de publication:
Jun 2023
Jun 2023
Historique:
received:
07
11
2022
accepted:
26
04
2023
medline:
15
6
2023
pubmed:
6
5
2023
entrez:
5
5
2023
Statut:
ppublish
Résumé
Radiomics of vertebral bone structure is a promising technique for identification of osteoporosis. We aimed at assessing the accuracy of machine learning in identifying physiological changes related to subjects' sex and age through analysis of radiomics features from CT images of lumbar vertebrae, and define its generalizability across different scanners. We annotated spherical volumes-of-interest (VOIs) in the center of the vertebral body for each lumbar vertebra in 233 subjects who had undergone lumbar CT for back pain on 3 different scanners, and we evaluated radiomics features from each VOI. Subjects with history of bone metabolism disorders, cancer, and vertebral fractures were excluded. We performed machine learning classification and regression models to identify subjects' sex and age respectively, and we computed a voting model which combined predictions. The model was trained on 173 subjects and tested on an internal validation dataset of 60. Radiomics was able to identify subjects' sex within single CT scanner (ROC AUC: up to 0.9714), with lower performance on the combined dataset of the 3 scanners (ROC AUC: 0.5545). Higher consistency among different scanners was found in identification of subjects' age (R2 0.568 on all scanners, MAD 7.232 years), with highest results on a single CT scanner (R2 0.667, MAD 3.296 years). Radiomics features are able to extract biometric data from lumbar trabecular bone, and determine bone modifications related to subjects' sex and age with great accuracy. However, acquisition from different CT scanners reduces the accuracy of the analysis.
Identifiants
pubmed: 37147473
doi: 10.1007/s11547-023-01641-6
pii: 10.1007/s11547-023-01641-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
744-754Informations de copyright
© 2023. Italian Society of Medical Radiology.
Références
Baum T, Gräbeldinger M, Räth C et al (2014) Trabecular bone structure analysis of the spine using clinical MDCT: can it predict vertebral bone strength? J Bone Miner Metab 32:56–64. https://doi.org/10.1007/s00774-013-0465-6
doi: 10.1007/s00774-013-0465-6
pubmed: 23604586
Hemmatian H, Bakker AD, Klein-Nulend J, Van Lenthe H, G, (1914) Aging, Osteocytes, and Mechanotransduction. Curr Osteoporos Rep. https://doi.org/10.1007/s11914-017-0402-z
doi: 10.1007/s11914-017-0402-z
Russo CR, Lauretani F, Bandinelli S et al (2003) Aging bone in men and women: beyond changes in bone mineral density. Osteoporos Int 14:531–538. https://doi.org/10.1007/s00198-002-1322-y
doi: 10.1007/s00198-002-1322-y
pubmed: 12827220
Yu A, Huang M, Wang L et al (2023) Age and gender differences in vertebral bone marrow adipose tissue and bone mineral density based on MRI and quantitative CT. Eur J Radiol 159:110669. https://doi.org/10.1016/j.ejrad.2022.110669
doi: 10.1016/j.ejrad.2022.110669
pubmed: 36608598
Kanis JA, Cooper C, Rizzoli R, Reginster J-Y (2019) European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporos Int 30:3–44. https://doi.org/10.1007/s00198-018-4704-5
doi: 10.1007/s00198-018-4704-5
pubmed: 30324412
Tamimi I, Cortes ARG, Sánchez-Siles J-M et al (2020) Composition and characteristics of trabecular bone in osteoporosis and osteoarthritis. Bone 140:115558. https://doi.org/10.1016/j.bone.2020.115558
doi: 10.1016/j.bone.2020.115558
pubmed: 32730941
Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762. https://doi.org/10.1038/nrclinonc.2017.141
doi: 10.1038/nrclinonc.2017.141
pubmed: 28975929
Hong JH, Jung J-Y, Jo A et al (2021) Development and validation of a radiomics model for differentiating bone islands and osteoblastic bone metastases at abdominal CT. Radiology 299:626–632. https://doi.org/10.1148/radiol.2021203783
doi: 10.1148/radiol.2021203783
pubmed: 33787335
Staal FCR, van der Reijd DJ, Taghavi M et al (2021) Radiomics for the prediction of treatment outcome and survival in patients with colorectal cancer: a systematic review. Clin Colorectal Cancer 20:52–71. https://doi.org/10.1016/j.clcc.2020.11.001
doi: 10.1016/j.clcc.2020.11.001
pubmed: 33349519
Sun Q, Chen Y, Liang C et al (2021) Biologic pathways underlying prognostic radiomics phenotypes from paired MRI and RNA sequencing in glioblastoma. Radiology 301(3):203281. https://doi.org/10.1148/radiol.2021203281
doi: 10.1148/radiol.2021203281
Hinzpeter R, Baumann L, Guggenberger R et al (2021) Radiomics for detecting prostate cancer bone metastases invisible in CT: a proof-of-concept study. Eur Radiol. https://doi.org/10.1007/s00330-021-08245-6
doi: 10.1007/s00330-021-08245-6
pubmed: 34559264
pmcid: 8831270
He L, Liu Z, Liu C et al (2021) Radiomics based on lumbar spine magnetic resonance imaging to detect osteoporosis. Acad Radiol 28:e165–e171. https://doi.org/10.1016/j.acra.2020.03.046
doi: 10.1016/j.acra.2020.03.046
pubmed: 32386949
Biamonte E, Levi R, Carrone F et al (2022) Artificial intelligence-based radiomics on computed tomography of lumbar spine in subjects with fragility vertebral fractures. J Endocrinol Invest 45:2007–2017. https://doi.org/10.1007/s40618-022-01837-z
doi: 10.1007/s40618-022-01837-z
pubmed: 35751803
Franke K, Gaser C (2019) Ten years of brainage as a neuroimaging biomarker of brain aging: what insights have we gained? Front Neurol 10:789. https://doi.org/10.3389/fneur.2019.00789
doi: 10.3389/fneur.2019.00789
pubmed: 31474922
pmcid: 6702897
Han Y, Wang G (2020) Skeletal bone age prediction based on a deep residual network with spatial transformer. Comput Methods Programs Biomed 197:105754. https://doi.org/10.1016/j.cmpb.2020.105754
doi: 10.1016/j.cmpb.2020.105754
pubmed: 32957059
Zwanenburg A, Vallières M, Abdalah MA et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338. https://doi.org/10.1148/radiol.2020191145
doi: 10.1148/radiol.2020191145
pubmed: 32154773
Fedorov A, Beichel R, Kalpathy-Cramer J et al (2012) 3D Slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging 30:1323–1341. https://doi.org/10.1016/j.mri.2012.05.001
doi: 10.1016/j.mri.2012.05.001
pubmed: 22770690
pmcid: 3466397
van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339
doi: 10.1158/0008-5472.CAN-17-0339
pubmed: 29092951
pmcid: 5672828
Fortin J-P, Cullen N, Sheline YI et al (2018) Harmonization of cortical thickness measurements across scanners and sites. Neuroimage 167:104–120. https://doi.org/10.1016/j.neuroimage.2017.11.024
doi: 10.1016/j.neuroimage.2017.11.024
pubmed: 29155184
Ozaki Y, Tanigaki Y, Watanabe S, Onishi M (2020) Multiobjective tree-structured parzen estimator for computationally expensive optimization problems. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference. ACM, New York, NY, USA, pp 533–541
Hsieh C-I, Zheng K, Lin C et al (2021) Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning. Nat Commun 12:5472. https://doi.org/10.1038/s41467-021-25779-x
doi: 10.1038/s41467-021-25779-x
pubmed: 34531406
pmcid: 8446034
Smets J, Shevroja E, Hügle T et al (2021) Machine Learning Solutions for Osteoporosis—A Review. J Bone Miner Res 36:833–851. https://doi.org/10.1002/jbmr.4292
doi: 10.1002/jbmr.4292
pubmed: 33751686
Fang Y, Li W, Chen X et al (2021) Opportunistic osteoporosis screening in multi-detector CT images using deep convolutional neural networks. Eur Radiol 31:1831–1842. https://doi.org/10.1007/s00330-020-07312-8
doi: 10.1007/s00330-020-07312-8
pubmed: 33001308
Valentinitsch A, Trebeschi S, Kaesmacher J et al (2019) Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures. Osteoporos Int 30:1275–1285. https://doi.org/10.1007/s00198-019-04910-1
doi: 10.1007/s00198-019-04910-1
pubmed: 30830261
pmcid: 6546649
Kawashima Y, Fujita A, Buch K et al (2019) Using texture analysis of head CT images to differentiate osteoporosis from normal bone density. Eur J Radiol 116:212–218. https://doi.org/10.1016/j.ejrad.2019.05.009
doi: 10.1016/j.ejrad.2019.05.009
pubmed: 31153568
Sun W, Liu S, Guo J et al (2021) A CT-based radiomics nomogram for distinguishing between benign and malignant bone tumours. Cancer Imaging 21:20. https://doi.org/10.1186/s40644-021-00387-6
doi: 10.1186/s40644-021-00387-6
pubmed: 33549151
pmcid: 7866630
Dionísio FCF, Oliveira LS, Hernandes MA et al (2020) Manual and semiautomatic segmentation of bone sarcomas on MRI have high similarity. Brazilian J Med Biol Res. https://doi.org/10.1590/1414-431x20198962
doi: 10.1590/1414-431x20198962
Eweje FR, Bao B, Wu J et al (2021) Deep learning for classification of bone lesions on routine MRI. EBioMedicine 68:103402. https://doi.org/10.1016/j.ebiom.2021.103402
doi: 10.1016/j.ebiom.2021.103402
pubmed: 34098339
pmcid: 8190437
Geirhos R, Jacobsen J-H, Michaelis C et al (2020) Shortcut learning in deep neural networks. Nat Mach Intell 2:665–673. https://doi.org/10.1038/s42256-020-00257-z
doi: 10.1038/s42256-020-00257-z
DeGrave AJ, Janizek JD, Lee S-I (2021) AI for radiographic COVID-19 detection selects shortcuts over signal. Nat Mach Intell 3:610–619. https://doi.org/10.1038/s42256-021-00338-7
doi: 10.1038/s42256-021-00338-7
Berenguer R, del Pastor-Juan M, R, Canales-Vázquez J, et al (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288:407–415. https://doi.org/10.1148/radiol.2018172361
doi: 10.1148/radiol.2018172361
pubmed: 29688159
van Hamersvelt RW, Schilham AMR, Engelke K et al (2017) Accuracy of bone mineral density quantification using dual-layer spectral detector CT: a phantom study. Eur Radiol 27:4351–4359. https://doi.org/10.1007/s00330-017-4801-4
doi: 10.1007/s00330-017-4801-4
pubmed: 28374079
pmcid: 5579207
Euler A, Nowak T, Bucher B et al (2021) Assessment of bone mineral density from a computed tomography topogram of photon-counting detector computed tomography—effect of phantom size and tube voltage. Invest Radiol 56:614–620. https://doi.org/10.1097/RLI.0000000000000781
doi: 10.1097/RLI.0000000000000781
pubmed: 33787538
Niu YT, Olszewski ME, Zhang YX et al (2011) Experimental study and optimization of scan parameters that influence radiation dose in temporal bone high-resolution multidetector row CT. Am J Neuroradiol 32:1783–1788. https://doi.org/10.3174/ajnr.A2609
doi: 10.3174/ajnr.A2609
pubmed: 21852373
pmcid: 7966019
Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25:44–56. https://doi.org/10.1038/s41591-018-0300-7
doi: 10.1038/s41591-018-0300-7
pubmed: 30617339
Bogowicz M, Jochems A, Deist TM et al (2020) Privacy-preserving distributed learning of radiomics to predict overall survival and HPV status in head and neck cancer. Sci Rep 10:4542. https://doi.org/10.1038/s41598-020-61297-4
doi: 10.1038/s41598-020-61297-4
pubmed: 32161279
pmcid: 7066122
Murray N, Le M, Ebrahimzadeh O et al (2017) Imaging the spine with dual-energy CT. Curr Radiol Rep 5:9. https://doi.org/10.1007/s40134-017-0236-6
doi: 10.1007/s40134-017-0236-6