Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Classification of brain compartments and head injury lesions by neural networks applied to MRI

Abstract

An automatic, neural network-based approach was applied to segment normal brain compartments and lesions on MR images. Two supervised networks, backpropagation (BPN) and counterpropagation, and two unsupervised networks, Kohonen learning vector quantizer and analog adaptive resonance theory, were trained on registered T2-weighted and proton density images. The classes of interest were background, gray matter, white matter, cerebrospinal fluid, macrocystic encephalomalacia, gliosis, and “unknown.” A comprehensive feature vector was chosen to discriminate these classes. The BPN combined with feature conditioning, multiple discriminant analysis followed by Hotelling transform, produced the most accurate and consistent classification results. Classifications of normal brain compartments were generally in agreement with expert interpretation of the images. Macrocystic encephalomalacia and gliosis were recognized and, except around the periphery, classified in agreement with the clinician's report used to train the neural network.

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

References

  1. 1.

    Hillman GR, Kent TA, Kaye A, et al (1991) Measurement of brain compartment volumes in MR using composition calculations. J Comput Assist Tomogr 15:640–646

  2. 2.

    Olsen WL, Longo FM, Mills CM, et al (1988) White matter disease in AIDS: findings at MR imaging. Radiology 169: 445–448

  3. 3.

    Raff U, Newman FD (1990) Lesion detection in radiologic images using an autoassociative paradigm. Med Phys 17: 926–928

  4. 4.

    Hall EL, Kruger RP, Dwyer SJ, et al (1971) A survery of preprocessing and feature extraction techniques for radiographic images. IEEE Trans Comput C- 20:1032–1044

  5. 5.

    Kohn MI, Tanna NK, Herman GT, et al (1991) Analysis of brain and cerebrospinal fluid volumes with MR imaging. Radiology 178:115–122

  6. 6.

    Lim KO, Pfefferbaum A (1989) Segmentation of MR brain images into cerebrospinal fluid spaces, white and gray matter. J Comput Assist Tomogr 13:588–593

  7. 7.

    Raya SP (199) Low-level segmentation of 3-D magnetic resonance brain images-a rule-based system. IEEE Trans Med Imaging 9:327–337

  8. 8.

    Amartur SC, Piraino D, Takefuji Y (1992) Optimization neural networks for the segmentation of magnetic resonance images. IEEE Trans Med Imaging 11:215–220

  9. 9.

    Clarke LP, Velthuizen RP, Phuphanich S, et al (1993) MRI: stability of three supervised segmentation techniques. Magn Reson Imaging 11:95–106

  10. 10.

    Hall LO, Bensaid AM, Clarke LP, et al (1992) A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain. IEEE Trans Neural Networks 3:672–682

  11. 11.

    Chimowitz MI, Estes ML, Furlan AJ, et al (1992) Further observations on the pathology of subcortical lesions identified on magnetic resonance imaging. Arch Neurol 49:747–752

  12. 12.

    Just M, Thelen M (1988) Tissue characterization with T1, T2 and proton density values: result in 160 patients with brain tumors. Radiology 169:770–785

  13. 13.

    Parsons T (1987) Voice and speech processing. McGraw-Hill, New York

  14. 14.

    Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York

  15. 15.

    Tou JT, Gonzalez RC (1974) Pattern recognition principles. Addison-Wesley, Boston

  16. 16.

    Gonzalez RC, Wintz P (1989) Digital image processing. Addison-Wesley, Boston

  17. 17.

    Jain AK (1989) Fundamentals of digital image processing. Prentice Hall, London

  18. 18.

    Freeman AF, Skapura DM (1991) Neural networks: algorithms, applications, and programming techniques. Addison-Wesley, Boston

  19. 19.

    Blum A (1991) Neural networks in C++. Wiley, New York

  20. 20.

    Korn GA (1991) Neural network experiments on personal computers and workstations. MIT Press, Cambridge

  21. 21.

    Wasserman PD (1989) Neural computing theory and practice. Van Nostrand Reinhold, New York

  22. 22.

    Tveter DR (1991) Fast-back propagation (computer software)

  23. 23.

    Hecht-Nielsen R (1987) Counterpropagation networks. Appl Optics 26:4979–4984

  24. 24.

    Carpenter GA, Grossberg S (1987) ART2: self-organization of stable category recognition codes for analog input patterns. Appl Optics 26:4919–4930

  25. 25.

    Huang SC, Huang YF (1991) Bounds on the number of hidden neurons in multilayer perceptrons. IEEE Trans Neural Networks 2:47–55

  26. 26.

    Mirchandani G (1989) On hidden nodes for neural nets. IEEE Trans Circ Syst 36:661–664

  27. 27.

    Vannier MW, Butterfield RL, Rickman DL, et al (1987) Multispectral magnetic resonance image analysis. CRC Crit Rev Biomed Eng 15:117–144

Download references

Author information

Correspondence to G. R. Hillman.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Kischell, E.R., Kehtarnavaz, N., Hillman, G.R. et al. Classification of brain compartments and head injury lesions by neural networks applied to MRI. Neuroradiology 37, 535–541 (1995). https://doi.org/10.1007/BF00593713

Download citation

Key words

  • Head injury
  • Magnetic resonance imaging
  • Neural networks