Fast and robust femur segmentation from computed tomography images for patient-specific hip fracture risk screening

References

• Bjornsson PA, Helgason B, Palsson H, Sigurdsson S, Gudnason V, Ellingsen LM. 2021. Automated femur segmentation from computed tomography images using a deep neural network. In: Gimi B Krol A, editors. Medical imaging 2021: biomedical applications in molecular, structural, and functional imaging; vol. 11600. International Society for Optics and Photonics; SPIE; pp. 324–330. doi:10.1117/12.2581100.
   Google Scholar
• Chang Y, Yuan Y, Guo C, Wang Y, Cheng Y, Tamura S. 2019. Accurate pelvis and femur segmentation in hip CT with a novel patch-based refinement. IEEE J Biomed Health Inform. 23(3):1192–1204. doi:10.1109/JBHI.2018.2834551.
   Google Scholar
• Chen F, Liu J, Zhao Z, Zhu M, Liao H. 2019. 3D feature-enhanced network for automatic femur segmentation. IEEE J Biomed Health Inform. 23(1):243–252. doi:10.1109/JBHI.2017.2785389.
   Google Scholar
• Chengwen C, Bai J, Wu X, Zheng G. 2015. Mascg: multi-atlas segmentation constrained graph method for accurate segmentation of hip CT images. Med Image Anal. 26(1):173–184. doi:10.1016/j.media.2015.08.011.
   Google Scholar
• Dice LR. 1945. Measures of the amount of ecologic association between species. Ecology. 26(3):297–302. doi:10.2307/1932409.
   Google Scholar
• Enns-Bray W, Bahaloo H, Fleps I, Ariza O, Gilchrist S, Widmer R, Guy P, Pálsson H, Ferguson S, Cripton P, et al. 2017. Material mapping strategy to improve the predicted response of the proximal femur to a sideways fall impact. J Mech Behav Biomed Mater. 78:196–205. doi:10.1016/j.jmbbm.2017.10.033.
   Google Scholar
• Enns-Bray W, Bahaloo H, Fleps I, Pauchard Y, Taghizadeh E, Sigurdsson S, Aspelund T, Büchler P, Harris T, Gudnason V, et al. 2019. Biofidelic finite element models for accurately classifying hip fracture in a retrospective clinical study of elderly women from the AGES Reykjavik cohort. Bone. 120:25–37. doi:10.1016/j.bone.2018.09.014.
   Google Scholar
• Fleps I, Enns-Bray W, Baker A, Bahaloo H, Sigurdsson S, Gudnason V, Ferguson S, Pálsson H, Helgason B 2021. FEM-Derived femoral strength is a better predictor of hip fracture risk than aBMD in the AGES Reykjavik study cohort. Under revision in Bone.
   Google Scholar
• Fleps I, Guy P, Ferguson S, Cripton P, Helgason B. 2019. Explicit finite element models accurately predict subject-specific and velocity-dependent kinetics of sideways fall impact. J Bone Mineral Res. 34(10):1837–1850. doi:10.1002/jbmr.3804.
   Google Scholar
• Fleps I, Pálsson H, Baker A, Enns-Bray W, Bahaloo H, Danner M, Singh NB, Taylor WR, Sigurdsson S, Gudnason V, et al. 2022. Finite element derived femoral strength is a better predictor of hip fracture risk than aBMD in the AGES Reykjavik study cohort. Bone. 154:116219. doi: 10.1016/j.bone.2021.116219.
   Google Scholar
• Haleem S, Lutchman L, Mayahi R, Grice J, Parker M. 2008. Mortality following hip fracture: trends and geographical variations over the last 40 years. Injury. 39(10):1157–1163. doi:10.1016/j.injury.2008.03.022.
   Google Scholar
• Harris T, Launer L, Eiriksdottir G, Kjartansson O, Jonsson P, Sigurdsson G, Thorgeirsson G, Aspelund T, Garcia M, Cotch MF, et al. 2007. Age, gene/environment susceptibility-Reykjavik study: multidisciplinary applied phenomics. Am J Epidemiol. 165:1076–1087. doi:10.1093/aje/kwk115.
   Google Scholar
• Hayes W, Myers E, Robinovitch S, Kroonenberg AVD, Courtney A, McMahon T. 1996. Etiology and prevention of age-related hip fractures. Bone. 18(1):77S–86S. doi:10.1016/8756-3282(95)00383-5.
   Google Scholar
• Huo Y, Terry J, Wang J, Nair S, Lasko T, Freedman B, Carr J, Landman B. 2019. Fully automatic liver attenuation estimation combing CNN segmentation and morphological operations. Med Phys. 46(8):3508–3519. doi:10.1002/mp.13675.
   Google Scholar
• Ioffe S, Szegedy C. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. ArXiv. abs/1502.03167.
   Google Scholar
• Isensee F, Jäger P, Wasserthal J, Zimmerer D, Petersen J, Kohl S, Schock J, Klein A, Roß T, Wirkert S, et al. 2020. Batchgenerators - a Python framework for data augmentation. https://github.com/MIC-DKFZ/batchgenerators.
   Google Scholar
• Kingma D, Ba J. 2014. Adam: a method for stochastic optimization. International Conference on Learning Representations. https://arxiv.org/pdf/1412.6980.pdf.
   Google Scholar
• LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L. 1990. Handwritten digit recognition with a back-propagation network. Denver (CO): NIPS; pp. 396–404.
   Google Scholar
• Milletari F, Navab N, Ahmadi SA. 2016. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. 10; 565–571.
   Google Scholar
• Müller D, Kramer F. 2019. Miscnn: a framework for medical image segmentation with convolutional neural networks and deep learning. 01. Presented at KiTS19.
   Google Scholar
• Parkkari J, Kannus P, Palvanen M, Natri A, Vainio J, Aho H, Vuori I, Järvinen M. 1999. Majority of hip fractures occur as a result of a fall and impact on the greater trochanter of the femur: a prospective controlled hip fracture study with 206 consecutive patients. Calcif Tissue Int. 65(3):183–187. doi:10.1007/s002239900679.
   Google Scholar
• Pauchard Y, Fitze T, Browarnik D, Eskandari A, Pauchard I, Enns-Bray W, Pálsson H, Sigurdsson S, Ferguson SJ, Harris TB, et al. 2016. Interactive graph-cut segmentation for fast creation of finite element models from clinical CT data for hip fracture prediction. Comput Methods Biomech Biomed Engin. 20(3):342.
   Google Scholar
• Ronneberger O, Fischer P, Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical image computing and computer-assisted intervention (MICCAI); (LNCS; vol. 9351). Springer; pp. 234–241. arXiv:1505.04597 [cs.CV]).
   Google Scholar
• Schuit S, van der Klift M, Weel A, de Laet C, Burger H, Seeman E, Hofman A, Uitterlinden A, van Leeuwen J, Pols H. 2004. Fracture incidence and association with bone mineral density in elderly men and women: the rotterdam study. Bone. 34(1):195–202. doi:10.1016/j.bone.2003.10.001.
   Google Scholar
• Shao M, Han S, Carass A, Li X, Blitz A, Shin J, Prince J, Ellingsen L. 2019. Brain ventricle parcellation using a deep neural network: application to patients with ventriculomegaly. NeuroImage. 23:101871. doi:10.1016/j.nicl.2019.101871.
   Google Scholar
• Stone K, Seeley D, Lui L, Cauley J, Ensrud K, Browner W, Nevitt M, Cummings S. 2003. Bmd at multiple sites and risk of fracture of multiple types: long-term results from the study of osteoporotic fractures. J Bone Miner Res. 18(11):1947–1954. doi:10.1359/jbmr.2003.18.11.1947.
   Google Scholar
• UN. 2015. World population ageing 2015. UN: Department of Economic and Social Affairs, Population Division. (ST/ESA/SER.A/368).
   Google Scholar
• Wainwright S, Marshall L, Ensrud K, Cauley J, Black D, Hillier T, Hochberg M, Vogt M, Orwoll E, of Osteoporotic Fractures Research Group S. 2005. Hip fracture in women without osteoporosis. J Clin Endocrinol Metab. 90(5):2787–2793. doi:10.1210/jc.2004-1568.
   Google Scholar
• Wang H, Yushkevich PA. 2013. Multi-Atlas segmentation without registration: a supervoxel-based approach. In: Mori K, Sakuma I, Sato Y, Barillot C Navab N, editors. Medical image computing and computer-assisted intervention – MICCAI 2013. Berlin, Heidelberg: Springer Berlin Heidelberg; pp. 535–542.
   Google Scholar
• Younes L, Nakajima Y, Saito T. 2019. Fully automatic segmentation of the femur from 3D-CT images using primitive shape recognition and statistical shape models. Int J Comput Assist Radiol Surg. 9(2):189–196. doi:10.1007/s11548-013-0950-3.
   Google Scholar
• Zhao C, Keyak JH, Tang J, Kaneko TS, Khosla S, Amin S, Atkinson E, Zhao L, Serou M, Zhang C, et al. 2020. A deep learning-based method for automatic segmentation of proximal femur from quantitative computed tomography images. ArXiv. abs/2006.05513.
   Google Scholar