Top

Published in:

01-06-2023 | Computed Tomography | Computed Tomography

CT-based radiomics can identify physiological modifications of bone structure related to subjects’ age and sex

Authors: Riccardo Levi, Federico Garoli, Massimiliano Battaglia, Dario A. A. Rizzo, Maximilliano Mollura, Giovanni Savini, Marco Riva, Massimo Tomei, Alessandro Ortolina, Maurizio Fornari, Saurabh Rohatgi, Giovanni Angelotti, Victor Savevski, Gherardo Mazziotti, Riccardo Barbieri, Marco Grimaldi, Letterio S. Politi

Published in: La radiologia medica | Issue 6/2023

Abstract

Purpose

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.

Materials and methods

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.

Results

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).

Conclusion

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.

Available only for authorised users

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/s00774-013-0465-6CrossRefPubMed

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-zCrossRef

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-yCrossRefPubMed

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.2022.110669CrossRefPubMed

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/s00198-018-4704-5CrossRefPubMed

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.2020.115558CrossRefPubMed

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.2017.141CrossRefPubMed

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.2021203783CrossRefPubMed

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.2020.11.001CrossRefPubMed

10.

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.2021203281CrossRef

11.

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/s00330-021-08245-6CrossRefPubMedPubMedCentral

12.

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.2020.03.046CrossRefPubMed

13.

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-zCrossRefPubMed

14.

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.2019.00789CrossRefPubMedPubMedCentral

15.

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.2020.105754CrossRefPubMed

16.

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.2020191145CrossRefPubMed

17.

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.2012.05.001CrossRefPubMedPubMedCentral

18.

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-17-0339CrossRefPubMedPubMedCentral

19.

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.2017.11.024CrossRefPubMed

20.

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

21.

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-xCrossRefPubMedPubMedCentral

22.

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.4292CrossRefPubMed

23.

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/s00330-020-07312-8CrossRefPubMed

24.

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/s00198-019-04910-1CrossRefPubMedPubMedCentral

25.

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.2019.05.009CrossRefPubMed

26.

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/s40644-021-00387-6CrossRefPubMedPubMedCentral

27.

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/10.1590/1414-431x20198962CrossRef

28.

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.2021.103402CrossRefPubMedPubMedCentral

29.

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-zCrossRef

30.

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/s42256-021-00338-7CrossRef

31.

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.2018172361CrossRefPubMed

32.

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/s00330-017-4801-4CrossRefPubMedPubMedCentral

33.

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.0000000000000781CrossRefPubMed

34.

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.A2609CrossRefPubMedPubMedCentral

35.

Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25:44–56. https://doi.org/10.1038/s41591-018-0300-7CrossRefPubMed

36.

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/s41598-020-61297-4CrossRefPubMedPubMedCentral

37.

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/s40134-017-0236-6CrossRef

Title: CT-based radiomics can identify physiological modifications of bone structure related to subjects’ age and sex
Authors: Riccardo Levi
Federico Garoli
Massimiliano Battaglia
Dario A. A. Rizzo
Maximilliano Mollura
Giovanni Savini
Marco Riva
Massimo Tomei
Alessandro Ortolina
Maurizio Fornari
Saurabh Rohatgi
Giovanni Angelotti
Victor Savevski
Gherardo Mazziotti
Riccardo Barbieri
Marco Grimaldi
Letterio S. Politi
Publication date: 01-06-2023
Publisher: Springer Milan
Keywords: Computed Tomography
Computed Tomography
Osteoporosis
Osteoporosis
Published in: La radiologia medica / Issue 6/2023
Print ISSN: 0033-8362
Electronic ISSN: 1826-6983
DOI: https://doi.org/10.1007/s11547-023-01641-6

Keynote webinar | Spotlight on medication adherence

Springer Medicine

CT-based radiomics can identify physiological modifications of bone structure related to subjects’ age and sex

Abstract

Purpose

Materials and methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Materials and methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 6/2023

Evaluation the benefits of additional radiotherapy for gastric cancer patients after D2 resection using CT based radiomics

Prospective validation of 18F-Fluoroethylcholine as a tracer in PET/MRI for the evaluation of breast lesions and prediction of lymph node status

Explainable AI in radiology: a white paper of the Italian Society of Medical and Interventional Radiology

Prediction of the mitotic index and preoperative risk stratification of gastrointestinal stromal tumors with CT radiomic features

A multiparametric clinic-ultrasomics nomogram for predicting extremity soft-tissue tumor malignancy: a combined retrospective and prospective bicentric study

A radiomics nomogram prediction for survival of patients with “driver gene-negative” lung adenocarcinomas (LUAD)