Advertisement

Automatic Vertebrae Localization and Identification by Combining Deep SSAE Contextual Features and Structured Regression Forest

  • Xuchu WangEmail author
  • Suiqiang Zhai
  • Yanmin Niu
Article
  • 28 Downloads

Abstract

Automatic vertebrae localization and identification in medical computed tomography (CT) scans is of great value for computer-aided spine diseases diagnosis. In order to overcome the disadvantages of the approaches employing hand-crafted, low-level features and based on field-of-view priori assumption of spine structure, an automatic method is proposed to localize and identify vertebrae by combining deep stacked sparse autoencoder (SSAE) contextual features and structured regression forest (SRF). The method employs SSAE to learn image deep contextual features instead of hand-crafted ones by building larger-range input samples to improve their contextual discrimination ability. In the localization and identification stage, it incorporates the SRF model to achieve whole spine localization, then screens those vertebrae within the image, thus relieves the assumption that the part of spine in the field of image is visible. In the end, the output distribution of SRF and spine CT scans properties are assembled to develop a two-stage progressive refining strategy, where the mean-shift kernel density estimation and Otsu method instead of Markov random field (MRF) are adopted to reduce model complexity and refine vertebrae localization results. Extensive evaluation was performed on a challenging data set of 98 spine CT scans. Compared with the hidden Markov model and the method based on convolutional neural network (CNN), the proposed approach could effectively and automatically locate and identify spinal targets in CT scans, and achieve higher localization accuracy, low model complexity, and no need for any assumptions about visual field in CT scans.

Keywords

Vertebrae localization Stacked sparse autoencoder (SSAE) Contextual feature Structured regression forest (SRF) Kernel density estimation 

Notes

Acknowledgements

The authors would like to sincerely thank the anonymous reviewers for their valuable comments, suggestions, and enlightenment.

Funding Information

This research was partially supported by the Basic and Frontier Planning of CQ-CSTC (cstc2016jcyjA0317).

References

  1. 1.
    Huang S-H, Chu Y-H, Lai S-H, Novak CL: Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI. IEEE Trans Med Imag 28 (10): 1595–1605, 2009CrossRefGoogle Scholar
  2. 2.
    Ayed IB, Punithakumar K, Minhas R, Joshi R, Garvin GJ: Vertebral body segmentation in MRI via convex relaxation and distribution matching. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2012, pp 520–527Google Scholar
  3. 3.
    Lecron F, Boisvert J, Mahmoudi S, Labelle H, Benjelloun M: Fast 3D spine reconstruction of postoperative patients using a multilevel statistical model.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2012, pp 446–453Google Scholar
  4. 4.
    Yao J, Burns JE, Munoz H, Summers RM: Detection of vertebral body fractures based on cortical shell unwrapping.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2012, pp 509–516Google Scholar
  5. 5.
    Oktay AB, Akgul YS: Localization of the lumbar discs using machine learning and exact probabilistic inference.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2011, pp 158–165Google Scholar
  6. 6.
    Schmidt S, Kappes J, Bergtholdt M, Pekar V, Dries S, Bystrov D, Schnörr C: Spine detection and labeling using a parts-based graphical model.. In: Biennial International Conference on Information Processing in Medical Imaging. Springer, 2007, pp 122–133Google Scholar
  7. 7.
    Ma J, Lu L, Zhan Y, Zhou X, Salganicoff M, Krishnan A: Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2010, pp 19–27Google Scholar
  8. 8.
    Kelm BM, Zhou SK, Suehling M, Zheng Y, Wels M, Comaniciu D: Detection of 3D spinal geometry using iterated marginal space learning.. In: International MICCAI Workshop on Medical Computer Vision. Springer, 2010, pp 96–105Google Scholar
  9. 9.
    Zhan Y, Maneesh D, Harder M, Zhou XS: Robust MR spine detection using hierarchical learning and local articulated model.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2012, pp 141–148Google Scholar
  10. 10.
    Zhan Y, Jian B, Maneesh D, Zhou XS: Cross-modality vertebrae localization and labeling using learning-based approaches.. In: Spinal Imaging and Image Analysis. Springer, 2015, pp 301–322Google Scholar
  11. 11.
    Forsberg D, Sjöblom E, Sunshine JL: Detection and labeling of vertebrae in MR images using deep learning with clinical annotations as training data. J Digit Imaging 30 (4): 1–7, 2017CrossRefGoogle Scholar
  12. 12.
    Klinder T, Ostermann J, Ehm M, Franz A, Kneser R, Lorenz C: Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 13 (3): 471–482, 2009CrossRefGoogle Scholar
  13. 13.
    Rak M, Tonnies KD: A learning-free approach to whole spine vertebra localization in MRI. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. 2016, pp 283–290Google Scholar
  14. 14.
    Glocker B, Feulner J, Criminisi A, Haynor DR, Konukoglu E: Automatic localization and identification of vertebrae in arbitrary field-of-view CT scans.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2012, pp 590–598Google Scholar
  15. 15.
    Glocker B, Zikic D, Konukoglu E, Haynor DR, Criminisi A: Vertebrae localization in pathological spine CT via dense classification from sparse annotations.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2013, pp 262–270Google Scholar
  16. 16.
    Suzani A, Seitel A, Liu Y, Fels S, Rohling RN, Abolmaesumi P: Fast automatic vertebrae detection and localization in pathological CT scans-a deep learning approach.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2015, pp 678–686Google Scholar
  17. 17.
    Chen H, Shen C, Qin J, Ni D, Shi L, Cheng JC, Heng P-A: Automatic localization and identification of vertebrae in spine CT via a joint learning model with deep neural networks.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2015, pp 515–522Google Scholar
  18. 18.
    Yang D, Xiong T, Xu D, Zhou SK, Xu Z, Chen M, Park J, Grbic S, Tran TD, Chin SP, et al: Deep image-to-image recurrent network with shape basis learning for automatic vertebra labeling in large-scale 3DCTvolumes.. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2017, pp 498–506Google Scholar
  19. 19.
    Liao H, Mesfin A, Luo J: Joint vertebrae identification and localization in spinal CT images by combining short-and longrange contextual information. IEEE Transactions on Medical ImagingGoogle Scholar
  20. 20.
    Kontschieder P, Bulo SR, Bischof H, Pelillo M: Structured class-labels in random forests for semantic image labelling. In: International Conference on Computer Vision. 2011, pp 2190–2197Google Scholar
  21. 21.
    Domingos JS, Stebbing RV, Leeson P, Noble JA (2014) Structured random forests for myocardium delineation in 3D echocardiography. Springer International PublishingGoogle Scholar
  22. 22.
    Zhu X, Jia X, Wong KYK: Structured forests for pixel-level hand detection and hand part labelling. Comput Vis Image Underst 141 (C): 95–107, 2015CrossRefGoogle Scholar
  23. 23.
    Dollar P, Zitnick CL Structured forests for fast edge detection. In: IEEE International conference on computer vision, 2014, pp 1841–1848Google Scholar
  24. 24.
    Zhao G, Wang X, Niu Y, Liwen T, Shaoxiang Z: Segmenting brain tissues from chinese visible human dataset by deep-learned features with stacked autoencoder. Biomed Res Int 2016 (6): 1–12, 2016Google Scholar
  25. 25.
    Xu J, Xiang L, Liu Q, Gilmore H, Wu J, Tang J, Madabhushi A: Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Trans Med Imaging 35 (1): 119–130, 2016CrossRefGoogle Scholar
  26. 26.
    Criminisi A, Robertson D, Konukoglu E, Shotton J, Pathak S, White S, Siddiqui K: Regression forests for efficient anatomy detection and localization in computed tomography scans. Medical Image Anal 17 (8): 1293–1303, 2013CrossRefGoogle Scholar
  27. 27.
    Comaniciu D, Meer P: Mean-shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24 (5): 603–619, 2002CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2019

Authors and Affiliations

  1. 1.Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education, College of Optoelectronic EngineeringChongqing UniversityChongqingChina
  2. 2.College of Computer and Information ScienceChongqing Normal UniversityChongqingChina

Personalised recommendations