Abstract
Purpose
We present a cross-modality and fully automatic pipeline for labeling of intervertebral discs and vertebrae in volumetric data of the lumbar and thoracolumbar spine. The main goal is to provide an algorithm that is applicable to a wide range of different sequences and acquisition protocols, like T1- and T2- weighted MR scans, MR Dixon data, and CT scans. This requires that the learned models generalize without retraining to modalities and scans with unseen image contrasts.
Methods
We address this challenge by automatically localizing the sacral region combining local entropy-optimized texture models with convolutional neural networks. For subsequent labeling, local three-disc entropy models are matched iteratively to the spinal column. Every model-matched position is further refined by an intensity-based template-matching approach, based solely on the reduced intensity scale provided by the entropy models.
Results
We evaluated our method on 161 publicly available scans, acquired on various scanners. We showed that our method can deal with a wide range of different MR protocols as well as with CT data. We achieved a sacrum detection rate of 93.6%. Mean center accuracies ranged from 2.5 ± 1.5 to 5.7 ± 3.8 mm for the different sets of scans.
Conclusion
We present a novel spine labeling framework that is applicable to a highly heterogeneous set of scans without retraining of the method. Our approach achieves high sacrum localization accuracy and shows promising labeling results. To the best of our knowledge, an algorithm able to deal with such a diverse set of MR and CT scans has not yet been presented in the literature.
Similar content being viewed by others
References
Agur AMR, Dalley AF (2012) Grant’s atlas of anatomy, 13th edn. Lippincott Williams & Wilkins, Philadelphia
Alomari R, Corso J, Chaudhary V (2011) Labeling of lumbar discs using both pixel- and object-level features with a two-level probabilistic model. IEEE Trans Med Imaging 30(1):1–10
Alomari RS, Ghosh S, Koh J, Chaudhary V (2015) Vertebral column localization, labeling, and segmentation. Spinal Imaging Image Anal Springer 18:193–229
Cai Y, Osman S, Sharma M, Landis M, Li S (2015) Multi-modality vertebra recognition in arbitrary views using 3D deformable hierarchical model. IEEE Trans Med Imaging 34(8):1676–1693
Cai Y, Landis M, Laidley DT, Kornecki A, Lum A, Li S (2016) Multi-modal vertebrae recognition using transformed deep convolution network. Comput Med Imaging Graph 51:11–19
Chen C, Belavy D, Zheng G (2014) 3D Intervertebral disc localization and segmentation from MR images by data-driven regression and classification. In: Machine learning in medical imaging, vol 8679, Springer, pp 50–58
Chen C, Belavy D, Yu W, Chu C, Armbrecht G, Bansmann M, Felsenberg D, Zheng G (2015a) Localization and segmentation of 3D intervertebral discs in MR images by data driven estimation. IEEE Trans Med Imaging 34(8):1719–1729
Chen H, Shen C, Qin J, Ni D, Shi L, Cheng JC, Heng PA (2015b) Automatic localization and identification of vertebrae in spine CT via a joint learning model with deep neural networks. In: Proceedings of MICCAI, Springer, vol 9349, pp 515–522
Chen H, Dou Q, Wang X, Qin J, Cheng JCY, Heng PA (2016) 3D Fully convolutional networks for intervertebral disc localization and segmentation. In: Proceedings of international conference on medical imaging and augmented reality, vol 9805, Springer, pp 375–382
Chu C, Belavy DL, Armbrecht G, Bansmann M, Felsenberg D, Zheng G (2015) Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method. PLoS ONE 10(11):e0143,327
Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models—their training and application. Comput Vis Image Underst 61(1):38–59
Daenzer S, Freitag S, von Sachsen S, Steinke H, Groll M, Meixensberger J, Leimert M (2014) VolHOG: a volumetric object recognition approach based on bivariate histograms of oriented gradients for vertebra detection in cervical spine MRI. Med Phys 41(8):082,305
Dieleman S, Schlüter J, Raffel C, Olson E, Sønderby SK, Nouri D, Maturana D, Thoma M, Battenberg E, Kelly J, Fauw JD, Heilman M, de Almeida DM, McFee B, Weideman H, Takács G, de Rivaz P, Crall J, Sanders G, Rasul K, Liu C, French G, Degrave J (2015) Lasagne: First release. https://doi.org/10.5281/zenodo.27878
Forsberg D, Sjöblom E, Sunshine JL (2017) Detection and labeling of vertebrae in MR images using deep learning with clinical annotations as training data. J Dig Imaging 30(4):406–412
Gilad I, Nissan M (1985) Sagittal evaluation of elemental geometrical dimensions of human vertebrae. J Anat 143:115–120
Glocker B, Feulner J, Criminisi A, Haynor DR, Konukoglu E (2012) Automatic localization and identification of vertebrae in arbitrary field-of-view CT scans. In: Proceedings of MICCAI, vol 7512, Springer, pp 590–598
Glocker B, Zikic D, Konukoglu E, Haynor DR, Criminisi A (2013) Vertebrae localization in pathological spine CT via dense classification from sparse annotations. In: Proceedings of MICCAI, vol 8150, Springer, pp 262–270
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, http://www.deeplearningbook.org
Heinrich MP, Oktay O (2016) Accurate intervertebral disc localisation and segmentation in MRI using vantage point hough forests and multi-atlas fusion. In: Computational methods and clinical applications for spine imaging, Springer, pp 77–84
Hojjat SP, Ayed I, Garvin GJ, Punithakumar K (2017) Spine labeling in MRI via regularized distribution matching. Int J Comput Assist Radiol Surg 12(11):1911–1922
Jamaludin A, Lootus M, Kadir T, Zisserman A (2016) Automatic intervertebral discs localization and segmentation: a vertebral approach. Comput Methods Clin Appl Spine Imaging Springer 9402:97–103
Ji X, Zheng G, Liu L, Ni D (2016) Fully automatic localization and segmentation of intervertebral disc from 3D multi-modality MR images by regression forest and CNN. Comput Methods Clin Appl Spine Imaging Springer 10182:92–101
Kelm B, Wels M, Zhou S, Seifert S, Suehling M, Zheng Y, Comaniciu D (2013) Spine detection in CT and MR using iterated marginal space learning. Med Image Anal 17(8):1283–1292
Krizhevsky A (2009) Learning multiple layers of features from tiny images. Tech. rep, University of Toronto
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Li X, Dou Q, Chen H, Fu CW, Heng PA (2016) Multi-scale and modality dropout learning for intervertebral disc localization and segmentation. Comput Methods Clin Appl Spine Imaging Springer 10182:85–91
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JA, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Lootus M, Kadir T, Zisserman A (2014) Vertebrae detection and labelling in lumbar MR images. In: Computational Methods and clinical applications for spine imaging, vol 17, Springer, pp 219–230
Major D, Hladůvka J, Schulze F, Bühler K (2013) Automated landmarking and labeling of fully and partially scanned spinal columns in CT images. Med Image Anal 17(8):1151–1163
Oktay AB, Akgul YS (2013) Simultaneous localization of lumbar vertebrae and intervertebral discs with SVM-based MRF. IEEE Trans Biomed Eng 60(9):2375–2383
Panjabi MM, Takata K, Goel V, Federico D, Oxland T, Duranceau J, Krag M (1991) Thoracic human vertebrae: quantitative three-dimensional anatomy. Spine 16(8):888–901
Panjabi MM, Goel V, Oxland T, Takata K, Duranceau J, Krag M, Price M (1992) Human lumbar vertebrae: quantitative three-dimensional anatomy. Spine 17(3):299–306
Rak M, Tönnies KD (2016) On computerized methods for spine analysis in MRI: a systematic review. Int J Comput Assist Radiol Surg 11(8):1445–1465
Schmidt S, Kappes J, Bergtholdt M, Pekar V, Dries S, Bystrov D, Schnörr C (2007) Spine detection and labeling using a parts-based graphical model. In: Proceedings of international conference on information processing in medical imaging, vol 4584, Springer, pp122–133
Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Štern D, Likar B, Pernuš F, Vrtovec T (2009) Automated detection of spinal centrelines, vertebral bodies and intervertebral discs in CT and MR images of lumbar spine. Phys Med Biol 55(1):247–264
Suzani A, Seitel A, Liu Y, Fels S, Rohling RN, Abolmaesumi P (2015) Fast automatic vertebrae detection and localization in pathological CT scans—a deep learning approach. In: Proceedings of MICCAI vol 9351, Springer, pp 678–686
Vrtovec T, Yao J, Glocker B, Klinder T, Frangi A, Zheng G, Li S (eds) (2015) Computational methods and clinical applications for spine imaging, Springer, chap challenge (automatic intervertebral disc localization and segmentation from 3D T2 MRI data), pp 107–158
Wang Z, Zhen X, Tay K, Osman S, Romano W, Li S (2015) Regression segmentation for M3 spinal images. IEEE Trans Med Imaging 34(8):1640–1648
Wimmer M, Major D, Novikov AA, Bühler K (2016) Local entropy-optimized texture models for semi-automatic spine labeling in various MRI protocols. In: Proceedings of IEEE 13th international symposium on biomedical imaging, IEEE, pp 155–159
Zambal S, Bühler K, Hladůvka J (2008) Entropy-optimized texture models. In: Proceedings of MICCAI, vol 5242, Springer, pp 213–221
Zhan Y, Jian B, Maneesh D, Zhou XS (2015) Cross-modality vertebrae localization and labeling using learning-based approaches. In: Spinal imaging and image analysis, Springer, pp 301–322
Zheng G, Chu C, Belavỳ DL, Ibragimov B, Korez R, Vrtovec T, Hutt H, Everson R, Meakin J, Andrade IL, Glocker B, Chen H, Dou Q, Heng PA, Wang C, Forsberg D, Neubert A, Fripp J, Urschler M, Štern D, Wimmer M, Novikov AA, Cheng H, Armbrecht G, Felsenberg D, Li S (2017) Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: a grand challenge. Med Image Anal 35:327–344
Zukić D, Vlasák A, Egger J, Hořínek D, Nimsky C, Kolb A (2014) Robust detection and segmentation for diagnosis of vertebral diseases using routine MR images. Comput Graph Forum 33(6):190–204
Acknowledgements
Thanks go to our project partner AGFA HealthCare for providing data and valuable input.
Funding
VRVis is funded by BMVIT, BMDW, Styria, SFG, and Vienna Business Agency in the scope of COMET—Competence Centers for Excellent Technologies (854174) which is managed by FFG.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
For this type of study, formal consent is not required.
Informed consent
This article does not contain patient data.
Rights and permissions
About this article
Cite this article
Wimmer, M., Major, D., Novikov, A.A. et al. Fully automatic cross-modality localization and labeling of vertebral bodies and intervertebral discs in 3D spinal images. Int J CARS 13, 1591–1603 (2018). https://doi.org/10.1007/s11548-018-1818-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-018-1818-3