Finite element models with automatic computed tomography bone segmentation for failure load computation.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
17 Jul 2024
17 Jul 2024
Historique:
received:
21
12
2023
accepted:
05
07
2024
medline:
18
7
2024
pubmed:
18
7
2024
entrez:
17
7
2024
Statut:
epublish
Résumé
Bone segmentation is an important step to perform biomechanical failure load simulations on in-vivo CT data of patients with bone metastasis, as it is a mandatory operation to obtain meshes needed for numerical simulations. Segmentation can be a tedious and time consuming task when done manually, and expert segmentations are subject to intra- and inter-operator variability. Deep learning methods are increasingly employed to automatically carry out image segmentation tasks. These networks usually need to be trained on a large image dataset along with the manual segmentations to maximize generalization to new images, but it is not always possible to have access to a multitude of CT-scans with the associated ground truth. It then becomes necessary to use training techniques to make the best use of the limited available data. In this paper, we propose a dedicated pipeline of preprocessing, deep learning based segmentation method and post-processing for in-vivo human femurs and vertebrae segmentation from CT-scans volumes. We experimented with three U-Net architectures and showed that out-of-the-box models enable automatic and high-quality volume segmentation if carefully trained. We compared the failure load simulation results obtained on femurs and vertebrae using either automatic or manual segmentations and studied the sensitivity of the simulations on small variations of the automatic segmentation. The failure loads obtained using automatic segmentations were comparable to those obtained using manual expert segmentations for all the femurs and vertebrae tested, demonstrating the effectiveness of the automated segmentation approach for failure load simulations.
Identifiants
pubmed: 39019937
doi: 10.1038/s41598-024-66934-w
pii: 10.1038/s41598-024-66934-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
16576Subventions
Organisme : LabEx Primes, France
ID : ANR-11-LABX-0063
Organisme : MSDAVENIR
ID : Research Grant
Informations de copyright
© 2024. The Author(s).
Références
Macedo, F. et al. Bone metastases: An overview. Oncol. Rev. 11(1), 321 (2017).
pubmed: 28584570
pmcid: 5444408
Mirels, H. Metastatic disease in long bones a proposed scoring system for diagnosing impending pathologic fractures. Clin. Orthop. Relat. Res. (1976–2007) 249, 256–264 (1989).
Fisher, C. G. et al. A novel classification system for spinal instability in neoplastic disease: An evidence-based approach and expert consensus from the spine oncology study group. Spine 35(22), E1221–E1229 (2010).
doi: 10.1097/BRS.0b013e3181e16ae2
pubmed: 20562730
Damron, T. A. et al. Critical evaluation of Mirels’ rating system for impending pathologic fractures. Clin. Orthop. Relat. Res. ® 415, S201–S207 (2003).
doi: 10.1097/01.blo.0000093842.72468.73
Piccioli, A., Spinelli, M. S. & Maccauro, G. Impending fracture: A difficult diagnosis. Injury 45, S138–S141 (2014).
doi: 10.1016/j.injury.2014.10.038
pubmed: 25457334
Benca, E. et al. The insufficiencies of risk analysis of impending pathological fractures in patients with femoral metastases: A literature review. Bone Rep. 5, 51–56 (2016).
doi: 10.1016/j.bonr.2016.02.003
pubmed: 28326347
pmcid: 4926839
Lenschow, M. et al. Impact of spinal instrumentation on neurological outcome in patients with intermediate spinal instability neoplastic score (SINS). Cancers 14(9), 2193 (2022).
doi: 10.3390/cancers14092193
pubmed: 35565322
pmcid: 9101027
Shi, D. D. et al. Assessing the utility of the spinal instability neoplastic score (SINS) to predict fracture after conventional radiation therapy (RT) for spinal metastases. Pract. Radiat. Oncol. 8(5), e285–e294 (2018).
doi: 10.1016/j.prro.2018.02.001
pubmed: 29703703
Pahr, D. H. & Zysset, P. K. From high-resolution CT data to finite element models: Development of an integrated modular framework. Comput. Methods Biomech. Biomed. Eng. 12(1), 45–57 (2009).
doi: 10.1080/10255840802144105
Sas, A. et al. Nonlinear voxel-based finite element model for strength assessment of healthy and metastatic proximal femurs. Bone Rep. 12, 100263 (2020).
doi: 10.1016/j.bonr.2020.100263
pubmed: 32322609
pmcid: 7163060
Keyak, J. H. et al. Prediction of femoral fracture load using automated finite element modeling. J. Biomech. 31(2), 125–133 (1997).
doi: 10.1016/S0021-9290(97)00123-1
Duchemin, L. et al. An anatomical subject-specific FE-model for hip fracture load prediction. Comput. Methods Biomech. Biomed. Eng. 11(2), 105–111 (2008).
doi: 10.1080/10255840701535965
Eggermont, F. et al. Patient-specific finite element computer models improve fracture risk assessments in cancer patients with femoral bone metastases compared to clinical guidelines. Bone 130, 115101 (2020).
doi: 10.1016/j.bone.2019.115101
pubmed: 31655223
Tanck, E. et al. Pathological fracture prediction in patients with metastatic lesions can be improved with quantitative computed tomography based computer models. Bone 45(4), 777–783 (2009).
doi: 10.1016/j.bone.2009.06.009
pubmed: 19539798
Dall’Ara, E. et al. QCT-based finite element models predict human vertebral strength in vitro significantly better than simulated DEXA. Osteoporos. Int. 23, 563–572 (2012).
doi: 10.1007/s00198-011-1568-3
pubmed: 21344244
Yosibash, Z. et al. Hip fracture risk assessment in elderly and diabetic patients: Combining autonomous finite element analysis and machine learning. J. Bone Miner. Res. Off. J. Am. Soc. Bone Miner. Res. 38(6), 876–886 (2020).
doi: 10.1002/jbmr.4805
Bjornsson, P. A. et al. Fast and robust femur segmentation from computed tomography images for patient-specific hip fracture risk screening. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 11(2), 253–265 (2023).
doi: 10.1080/21681163.2022.2068160
Stadelmann, M. A. et al. Conventional finite element models estimate the strength of metastatic human vertebrae despite alterations of the bone’s tissue and structure. Bone 141, 115598 (2020).
doi: 10.1016/j.bone.2020.115598
pubmed: 32829037
pmcid: 9206866
Palanca, M., Cavazzoni, G. & Dall’Ara, E. The role of bone metastases on the mechanical competence of human vertebrae. Bone 173, 116814 (2023).
doi: 10.1016/j.bone.2023.116814
pubmed: 37257631
Imai, K. et al. In vivo assessment of lumbar vertebral strength in elderly women using computed tomography-based nonlinear finite element model. Spine 33(1), 27–32 (2008).
doi: 10.1097/BRS.0b013e31815e3993
pubmed: 18165745
Levillain, A. et al. Inter-operator variability of a finite element model of femurs with and without simulated metastatic defects. In ESB2021, 26th Congress of the European Society of Biomechanics 1 (2021).
Chu, C. et al. MASCG: Multi-atlas segmentation constrained graph method for accurate segmentation of hip CT images. Med. Image Anal. 26(1), 173–184 (2015).
doi: 10.1016/j.media.2015.08.011
pubmed: 26426453
Liang, K. et al. Accurate and automatic 3D segmentation of femur and pelvis from CT images of the hip based on deep learning. J. Imaging Sci. Technol. 65(3), 1–6 (2021).
doi: 10.2352/J.ImagingSci.Technol.2021.65.3.030411
Deng, Y. et al. A deep learning-based approach to automatic proximal femur segmentation in quantitative CT images. Med. Biol. Eng. Comput. 60(5), 1417–1429 (2022).
doi: 10.1007/s11517-022-02529-9
pubmed: 35322343
Chen, F. et al. Three-dimensional feature-enhanced network for automatic femur segmentation. IEEE J. Biomed. Health Inform. 23(1), 243–252 (2017).
doi: 10.1109/JBHI.2017.2785389
pubmed: 29990051
Gardegaront, M. et al. Inter-Laboratory Replicability and Sensitivity Study of a Finite Element Model to Quantify Human Femur Failure Load: Case of Metastases. JMBBM-D-23-01657, submitted Nov 2023.
Klinder, T. et al. Automated model-based vertebra detection, identification, and segmentation in CT images. Med. Image Anal. 13(3), 471–482 (2009).
doi: 10.1016/j.media.2009.02.004
pubmed: 19285910
Forsberg, D. Atlas-based registration for accurate segmentation of thoracic and lumbar vertebrae in CT data. In Recent Advances in Computational Methods and Clinical Applications for Spine Imaging. Lecture Notes in Computational Vision and Biomechanics (eds Yao, J. et al.) 49–59 (Springer International Publishing, 2015).
Sekuboyina, A. et al. VerSe: A vertebrae labelling and segmentation benchmark for multi-detector CT images. Med. Image Anal. 73, 102166 (2021).
doi: 10.1016/j.media.2021.102166
pubmed: 34340104
Allard, V. et al. Comparison of two models to predict vertebral failure loads on the same experimental dataset. In Computer Methods in Biomechanics and Biomedical Engineering in Springer book, accepted.
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015, Proceedings, Part III, Vol. 18 234–241 (Springer, 2015).
Isensee, F. et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021).
doi: 10.1038/s41592-020-01008-z
pubmed: 33288961
Wegrzyn, J. et al. Determinants of the mechanical behavior of human lumbar vertebrae after simulated mild fracture. J. Bone Miner. Res. 26(4), 739–746 (2011).
doi: 10.1002/jbmr.264
pubmed: 20928886
Kopperdahl, D. L., Morgan, E. F. & Keaveny, T. M. Quantitative computed tomography estimates of the mechanical properties of human vertebral trabecular bone. J. Orthop. Res. 20(4), 801–805 (2002).
doi: 10.1016/S0736-0266(01)00185-1
pubmed: 12168670
Rincón-Kohli, L. & Zysset, P. K. Multi-axial mechanical properties of human trabecular bone. Biomech. Model. Mechanobiol. 8, 195–208 (2009).
doi: 10.1007/s10237-008-0128-z
pubmed: 18695984
Wang, X. et al. Prediction of new clinical vertebral fractures in elderly men using finite element analysis of CT scans. J. Bone Miner. Res. 27(4), 808–816 (2012).
doi: 10.1002/jbmr.1539
pubmed: 22190331