Rapid image recognition of body parts scanned in computed tomography datasets

  • Volker Dicken
  • B. Lindow
  • L. Bornemann
  • J. Drexl
  • A. Nikoubashman
  • H.-O. Peitgen
Original Article

Abstract

Aim

Automatic CT dataset classification is important to efficiently create reliable database annotations, especially when large collections of scans must be analyzed.

Method

An automated segmentation and labeling algorithm was developed based on a fast patient segmentation and extraction of statistical density class features from the CT data. The method also delivers classifications of image noise level and patient size. The approach is based on image information only and uses an approximate patient contour detection and statistical features of the density distribution. These are obtained from a slice-wise analysis of the areas filled by various materials related to certain density classes and the spatial spread of each class. The resulting families of curves are subsequently classified using rules derived from knowledge about features of the human anatomy.

Results

The method was successfully applied to more than 5,000 CT datasets. Evaluation was performed via expert visual inspection of screenshots showing classification results and detected characteristic positions along the main body axis. Accuracy per body region was very satisfactory in the trunk (lung/liver >99.5% detection rate, presence of abdomen >97% or pelvis >95.8%) improvements are required for zoomed scans.

Conclusion

The method performed very reliably. A test on 1,860 CT datasets collected from an oncological trial showed that the method is feasible, efficient, and is promising as an automated tool for image post-processing.

Keywords

Classification Computed tomography Anatomy Body region Database Segmentation Content-based image retrieval 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Greenspan H, Goldberger J, Ridel L (2001) A Continuous probabilistic framework for image matching. J Comput Vis Image Underst 84(3): 384–406CrossRefGoogle Scholar
  2. 2.
    Pinhas A, Greenspan H (2004) A continuous and probabilistic framework for medical image representation and categorization. In: Proceedings of SPIE, vol 5371, pp 230–238Google Scholar
  3. 3.
    Lehmann T, Wein B, Keysers D, Kohnen M, Schubert H (2002) A mono-hierarchical multi-axial classification code for medical images in content-based retrieval. In: Proceedings of the 1st IEEE International Symposium on biomedical imaging, pp 313–316Google Scholar
  4. 4.
    Deselaers T, Müller H, Clough P, Ney H, Lehmann TM (2007) The CLEF 2005 automatic medical image annotation task. Int J Comput Vis 74(1): 51–58CrossRefGoogle Scholar
  5. 5.
    Zhou X, Kamiya N, Hara T, Fujita H, Yokoyama R, Kiryu T, Hoshi H (2004) Automated Recognition of Human Structure From Torso CT Images, VIIP. In: International Conference on Visualization, imaging and image processing. Marbella, SpainGoogle Scholar
  6. 6.
    MeVisLab, Software for Medical Image Processing and Visualization. http://www.mevislab.de

Copyright information

© CARS 2010

Authors and Affiliations

  • Volker Dicken
    • 1
  • B. Lindow
    • 1
  • L. Bornemann
    • 1
  • J. Drexl
    • 1
  • A. Nikoubashman
    • 1
  • H.-O. Peitgen
    • 1
  1. 1.Fraunhofer MEVISInstitute for Medical Image ComputingBremenGermany

Personalised recommendations