Skip to main content

Advertisement

Log in

Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

The subarachnoid space (SAS) lies between the arachnoid membrane and the pia mater of the human brain, normally filled with cerebrospinal fluid (CSF). Subarachnoid hemorrhage (SAH) is a serious complication of neurological disease that can have high mortality and high risk of disability. Computed tomography (CT) head scans are often used for diagnosing SAH which may be difficult when the hemorrhage is small or subtle. A computer-aided diagnosis system from CT images is thus developed to augment image interpretation.

Methods

Supervised learning using the probability of distance features of several landmarks was employed to recognize SAS. For each CT image, the SAS was approximated in four steps: (1) Landmarks including brain boundary, midsagittal plane (MSP), anterior and posterior intersection points of brain boundary with the MSP, and superior point of the brain were extracted. (2) Distances to all the landmarks were calculated for every pixel in the CT image, and combined to construct a high-dimensional feature vector. (3) Using head CT images with manually delineated SAS as training dataset, the prior probabilities of distances for pixels within SAS and non-SAS were computed. (4) Any pixel of a head CT scan in the testing dataset was classified as an SAS or non-SAS pixel in a Bayesian decision framework based on its distance features.

Results

The proposed method was validated on clinical head CT images by comparison with manual segmentation. The results showed that the automated method is consistent with the gold standard. Compared with elastic registration based on grayscale information, the proposed method was less affected by grayscale variation between normal controls and patients. Compared with manual delineation, the average spatial overlap, relative overlap, and similarity index were, respectively, 89, 63, and 76% for the automatic SAS approximation of the 69 head CT scans tested. The proposed method was tested for SAH detection and yielded a sensitivity of 100% and a specificity of 92%.

Conclusion

Automated SAH detection with high sensitivity was shown feasible in a prototype computer-aided diagnosis system. The proposed method may be extended for computer-aided diagnosis of several CSF-related diseases relevant to SAS abnormalities.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Gray H (2008) Gray’s anatomy: the anatomical basis of clinical practice, 40th edn. Churchill-Livingstone, Elsevier, Amsterdam

  2. Van Gijn J, Kerr RS, Rinkel GJE (2007) Subarachnoid haemorrhage. Lancet 369: 306–318

    Article  PubMed  Google Scholar 

  3. Reiner BI, Siegel EL, Hooper FJ et al (2001) Radiologist productivity in the interpretation of CT scans: a comparison of PACS with conventional film images. AJR 176: 861–864

    PubMed  CAS  Google Scholar 

  4. Edlow JA, Malek AM, Ogilvy CS (2008) Aneurysmal subarachnoid hemorrhage: update for emergency physicians. J Emerg Med 34: 237–251

    Article  PubMed  Google Scholar 

  5. Zijdenbos AP, Dawant BM (1994) Brain segmentation and white matter lesion detection in MR images. Crit Rev Biomed Eng 22: 401–465

    PubMed  CAS  Google Scholar 

  6. Lee JD, Su HR, Cheng PE et al (2009) MR Image segmentation using a power transformation approach. IEEE Trans Med Imaging 28: 894–905

    Article  PubMed  Google Scholar 

  7. Cline HE, Lorensen WE, Kikinis R et al (1990) Three-dimensional segmentation of MR images of the head using probability and connectivity. J Comput Assist Tomogr 14: 1037–1045

    Article  PubMed  CAS  Google Scholar 

  8. Schönmeyer R, Prvulovic D, Rotarska-Jagiela A et al (2006) Automated segmentation of lateral ventricles from human and primate magnetic resonance images using cognition network technology. Magn Reson Imaging 24: 1377–1387

    Article  PubMed  Google Scholar 

  9. Schnack HG, Hulshoff HE, Baare WF et al (2001) Automatic segmentation of the ventricular system from MR images of the human brain. Neuroimage 14: 95–104

    Article  PubMed  CAS  Google Scholar 

  10. Yushkevich PA, Piven J, Hazlett HC, Smith RG et al (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. NeuroImage 31: 1116–1128

    Article  PubMed  Google Scholar 

  11. Pitiot A, Delingette H, Thompson PM, Ayache N (2004) Expert knowledge-guided segmentation system for brain MRI. NeuroImage 23(1): S85–S96

    Article  PubMed  Google Scholar 

  12. Walser RL, Ackerman LV (1997) Determination of volume from computerised tomograms: finding the volume of fluidfilled brain cavities. J Comput Assist Tomogr 1: 117–130

    Article  Google Scholar 

  13. Sager WD, Gell G, Ladurner G et al (1978) Calculation of cerebral tissue and cerebrospinal fluid space volumes from computer tomograms. Neuroradiology 16: 176–178

    Article  PubMed  CAS  Google Scholar 

  14. Baldy RE, Brindle GS, Ewusi-Mensah I et al (1986) A fully-automated computer-assisted method of CT brain scan analysis for the measurement of cerebrospinal fluid spaces and brain absorption density. Neuroradiology 28(2): 109–117

    Article  PubMed  CAS  Google Scholar 

  15. Luo F, Evans JW, Linney NC et al (2010) Wavelet-based image registration and segmentation framework for the quantitative evaluation of hydrocephalus. Int J Biomed Imaging 2010: 248393

    Article  PubMed  Google Scholar 

  16. Liu J, Huang S, Ihar V et al (2010) Automatic model-guided segmentation of the the human brain ventricular system from CT images. Acad Radiol 17: 718–726

    Article  PubMed  Google Scholar 

  17. Chen W, Smith R, Ji S-Y et al (2009) Automated ventricular systems segmentation in brain CT images by combining low-level segmentation and high-level template matching. BMC Med Inf Decis Mak 9: S4

    Article  Google Scholar 

  18. Provenzale JM, Hacein-Bey L (2009) CT evaluation of subarachnoid hemorrhage: a practical review for the radiologist interpreting emergency room studies. Emerg Radiol 16(6): 441–451

    Article  PubMed  Google Scholar 

  19. Zhang L, Hu Q, Li Y (2010) Approximating major cerebrospinal fluid space in a distance transformation based Bayesian framework from clinical non-enhanced computed tomography images. In: The 4th international conference on bioinformatics and biomedical engineering (iCBBE 2010), Chengdu, China

  20. Hu Q, Qian G, Aziz A et al (2005) Segmentation of brain from computed tomography head images. In: 27th annual conference of the engineering in medicine and biology society, pp 3375–3378

  21. Hu Q, Nowinski WL (2003) A rapid algorithm for robust and automatic extraction of the midsagittal plane of the human cerebrum from neuroimages based on local symmetry and outlier removal. NeuroImage 20: 2153–2165

    Article  PubMed  Google Scholar 

  22. Neyman J, Pearson ES (1933) On the problem of the most efficient tests of statistical hypothese. Philos Trans Royal Soc Lond Ser A, Containing Papers of a Mathematical or Physical Character 231: 289–337

    Article  Google Scholar 

  23. Altman DG, Bland JM (1994) Diagnostic tests. 1: sensitivity and specificity. BMJ 308(6943): 1552

    Article  PubMed  CAS  Google Scholar 

  24. Jaccard P (1912) The distribution of flora in the alpine zone. New Phytol 11: 37–50

    Article  Google Scholar 

  25. Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302. http://jstor.org/stable/1932409

    Google Scholar 

  26. Li Y, Wu J, Li H et al (2010) Automatic detection of the existence of subarachnoid hemorrhage from clinical CT images. J Med Syst. doi:10.1007/s10916-010-9587-8

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Qing-Mao Hu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Li, YH., Zhang, L., Hu, QM. et al. Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans. Int J CARS 7, 507–516 (2012). https://doi.org/10.1007/s11548-011-0664-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-011-0664-3

Keywords

Navigation