Skip to main content

Advertisement

SpringerLink
Log in

A Deep Learning Approach for Automated Bone Removal from Computed Tomography Angiography of the Brain

  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

Advanced visualization techniques such as maximum intensity projection (MIP) and volume rendering (VR) are useful for evaluating neurovascular anatomy on CT angiography (CTA) of the brain; however, interference from surrounding osseous anatomy is common. Existing methods for removing bone from CTA images are limited in scope and/or accuracy, particularly at the skull base. We present a new brain CTA bone removal tool, which addresses many of these limitations. A deep convolutional neural network was designed and trained for bone removal using 72 brain CTAs. The model was tested on 15 CTAs from the same data source and 17 CTAs from an independent external dataset. Bone removal accuracy was assessed quantitatively, by comparing automated segmentation results to manual segmentations, and qualitatively by evaluating VR visualization of the carotid siphons compared to an existing method for automated bone removal. Average Dice overlap between automated and manual segmentations from the internal and external test datasets were 0.986 and 0.979 respectively. This was superior compared to a publicly available noncontrast head CT bone removal algorithm which had a Dice overlap of 0.947 (internal dataset) and 0.938 (external dataset). Our algorithm yielded better VR visualization of the carotid siphons than the publicly available bone removal tool in 14 out of 15 CTAs (93%, chi-square statistic of 22.5, p-value of < 0.00001) from the internal test dataset and 15 out of 17 CTAs (88%, chi-square statistic of 23.1, p-value of < 0.00001) from the external test dataset. Bone removal allowed subjectively superior MIP and VR visualization of vascular anatomy/pathology. The proposed brain CTA bone removal algorithm is rapid, accurate, and allows superior visualization of vascular anatomy and pathology compared to other available techniques and was validated on an independent external dataset.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Abbreviations

3D :

Three dimensional

CTA :

Computed tomography angiography

DICOM :

Digital Imaging and Communications in Medicine

DSA :

Digital subtraction angiography

MIP :

Maximum intensity projection

MRI :

Magnetic resonance imaging

VR :

Volume rendering

References

  1. Caton Jr. MT, Wiggins WF, Nunez D. Three-Dimensional Cinematic Rendering to Optimize Visualization of Cerebrovascular Anatomy and Disease in CT Angiography. Journal of Neuroimaging 2020;30:286–96.

    Article  PubMed  Google Scholar 

  2. Korogi Y, Takahashi M, Katada K, et al. Intracranial aneurysms: detection with three-dimensional CT angiography with volume rendering--comparison with conventional angiographic and surgical findings. Radiology 1999;211:497–506.

    Article  CAS  PubMed  Google Scholar 

  3. White PM, Teasdale EM, Wardlaw JM, et al. Intracranial aneurysms: CT angiography and MR angiography for detection prospective blinded comparison in a large patient cohort. Radiology 2001;219:739–49.

    Article  CAS  PubMed  Google Scholar 

  4. Fishman EK, Ney DR, Heath DG, et al. Volume Rendering versus Maximum Intensity Projection in CT Angiography: What Works Best, When, and Why. RadioGraphics 2006;26:905–22.

    Article  PubMed  Google Scholar 

  5. Perandini S, Faccioli N, Zaccarella A, et al. The diagnostic contribution of CT volumetric rendering techniques in routine practice. Indian J Radiol Imaging 2010;20:92–7.

    Article  PubMed  PubMed Central  Google Scholar 

  6. Chen W, Yang Y, Xing W, et al. Applications of multislice CT angiography in the surgical clipping and endovascular coiling of intracranial aneurysms. J Biomed Res 2010;24:467–73.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Broder J, Preston R. Chapter 1 - Imaging the Head and Brain. In: Broder J, ed. Diagnostic Imaging for the Emergency Physician. Saint Louis: W.B. Saunders; 2011:1–45.

    Google Scholar 

  8. Bello HR, Graves JA, Rohatgi S, et al. Skull Base–related Lesions at Routine Head CT from the Emergency Department: Pearls, Pitfalls, and Lessons Learned. RadioGraphics 2019;39:1161–82.

    Article  PubMed  Google Scholar 

  9. Anderson GB, Ashforth R, Steinke DE, et al. CT Angiography for the Detection and Characterization of Carotid Artery Bifurcation Disease. Stroke 2000;31:2168–74.

    Article  CAS  PubMed  Google Scholar 

  10. Mayer PL, Awad IA, Todor R, et al. Misdiagnosis of Symptomatic Cerebral Aneurysm. Stroke 1996;27:1558–63.

    Article  CAS  PubMed  Google Scholar 

  11. Lu L, Zhang LJ, Poon CS, et al. Digital subtraction CT angiography for detection of intracranial aneurysms: comparison with three-dimensional digital subtraction angiography. Radiology 2012;262:605–12.

    Article  PubMed  Google Scholar 

  12. Watanabe Y, Uotani K, Nakazawa T, et al. Dual-energy direct bone removal CT angiography for evaluation of intracranial aneurysm or stenosis: comparison with conventional digital subtraction angiography. Eur Radiol 2009;19:1019–24.

    Article  PubMed  Google Scholar 

  13. Postma AA, Das M, Stadler AAR, et al. Dual-Energy CT: What the Neuroradiologist Should Know. Curr Radiol Rep 2015;3:16.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Sommer WH, Johnson TR, Becker CR, et al. The value of dual-energy bone removal in maximum intensity projections of lower extremity computed tomography angiography. Invest Radiol 2009;44:285–92.

    Article  PubMed  Google Scholar 

  15. Nimble Co LLC. Horos Project. 2018 Feb 7. [Epub ahead of print].

  16. Friedli L, Kloukos D, Kanavakis G, et al. The effect of threshold level on bone segmentation of cranial base structures from CT and CBCT images. Sci Rep 2020;10:7361.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. van Straten M, Schaap M, Dijkshoorn ML, et al. Automated bone removal in CT angiography: Comparison of methods based on single energy and dual energy scans. Medical Physics 2011;38:6128–37.

    Article  PubMed  Google Scholar 

  18. Fu F, Wei J, Zhang M, et al. Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network. Nat Commun 2020;11:4829.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. mPower Clinical Analytics for medical imaging | Nuance. Nuance Communications.

  20. Automated Image Retrieval (AIR) - PACS. UCSF Data Resources.

  21. ITK-SNAP. Paul A. Yushkevich, Joseph Piven, Heather Cody Hazlett, Rachel Gimpel Smith, Sean Ho, James C. Gee, and Guido Gerig. User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. Neuroimage 2006 Jul 1;31(3):1116–28.

  22. Calabrese E, Villanueva-Meyer JE, Cha S. A fully automated artificial intelligence method for non-invasive, imaging-based identification of genetic alterations in glioblastomas. Sci Rep 2020;10:11852.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Calabrese E, Rudie JD, Rauschecker AM, et al. Feasibility of Simulated Postcontrast MRI of Glioblastomas and Lower-Grade Gliomas by Using Three-dimensional Fully Convolutional Neural Networks. Radiology: Artificial Intelligence 2021;3:e200276.

  24. Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings; 2010:249–56.

  25. aqqush. CT_BET: Robust Brain Extraction Tool for CT Head Images. 2022 Oct 20. [Epub ahead of print].

  26. Goren, Nir, Dowrick, Thomas, Avery, James, & Holder, David. UCLH Stroke EIT Dataset - Radiology Data | Zenodo. https://doi.org/10.5281/zenodo.1199398.

  27. Caruana R, Lawrence S, Giles L. Overfitting in neural nets: 14th Annual Neural Information Processing Systems Conference, NIPS 2000. Advances in Neural Information Processing Systems 13 - Proceedings of the 2000 Conference, NIPS 2000 2001. [Epub ahead of print].

  28. Prechelt L. Early Stopping — But When? In: Montavon G, Orr GB, Müller K-R, eds. Neural Networks: Tricks of the Trade: Second Edition. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer; 2012:53–67.

  29. Itri JN, Tappouni RR, McEachern RO, et al. Fundamentals of Diagnostic Error in Imaging. Radiographics 2018;38:1845–65.

    Article  PubMed  Google Scholar 

  30. Bahrami S, Yim CM. Quality Initiatives: Blind Spots at Brain Imaging. RadioGraphics 2009;29:1877–96.

    Article  PubMed  Google Scholar 

  31. Biddle G, Assadsangabi R, Broadhead K, et al. Diagnostic Errors in Cerebrovascular Pathology: Retrospective Analysis of a Neuroradiology Database at a Large Tertiary Academic Medical Center. AJNR Am J Neuroradiol https://doi.org/10.3174/ajnr.A7596.

  32. He L, Li Z. The aneurysm close to the skull base was wiped off by bone subtraction on 3D CTA images. AIP Conference Proceedings 2019;2079:020031.

    Article  Google Scholar 

  33. Budd S, Robinson EC, Kainz B. A survey on active learning and human-in-the-loop deep learning for medical image analysis. Medical Image Analysis 2021;71:102062.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

None.

Funding

Dr. M. Isikbay was supported by a National Institutes of Health (NIBIB) T32 Training Grant, T32EB001631.

Author information

Authors and Affiliations

  1. Department of Radiology and Biomedical Imaging, University of California San Francisco, 505 Parnassus Ave, M-396, San Francisco, CA, 94143, USA

    Masis Isikbay & Evan Calabrese

  2. Cerebrovascular Center, Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, 1450 Madison Ave, New York, NY, 10029, USA

    M. Travis Caton

  3. Department of Radiology, Division of Neuroradiology, Duke University Medical Center, Box 3808 DUMC, Durham, NC, 27710, USA

    Evan Calabrese

  4. Duke Center for Artificial Intelligence in Radiology (DAIR), Duke University Medical Center, Durham, NC, 27710, USA

    Evan Calabrese

  5. Center for Intelligent Imaging, University of California San Francisco, San Francisco, CA, 94143, USA

    Evan Calabrese

Authors
  1. Masis Isikbay
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Travis Caton
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Evan Calabrese
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Masis Isikbay.

Ethics declarations

Presentation Information/Sponsoring Societies

Related work was presented at the 15th Annual Meeting of the American Society of Functional Neuroradiology (ASNFR 2022). The results of this work have been accepted to be presented at the annual meeting of the American Society of Neuroradiology (ASNR 2023).

Conflict of Interest

N/A.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 3801 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Isikbay, M., Caton, M.T. & Calabrese, E. A Deep Learning Approach for Automated Bone Removal from Computed Tomography Angiography of the Brain. J Digit Imaging 36, 964–972 (2023). https://doi.org/10.1007/s10278-023-00788-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-023-00788-y

Keywords

Search

Navigation