Advertisement

Neuroradiology

, Volume 37, Issue 2, pp 89–93 | Cite as

Use of a neural network and a multiple regression model to predict histologic grade of astrocytoma from MRI appearances

  • P. S. Christy
  • O. Tervonen
  • B. W. Scheithauer
  • G. S. Forbes
Diagnostic Neuroradiology

Abstract

Several MRI features of supratentorial astrocytomas are associated with high histologic grade by statistically significant p values. We sought to apply this information prospectively to a group of astrocytomas in the prediction of tumor grade. We used 10 MRI features of fibrillary astrocytomas from 52 patient studies to develop neural network and multiple linear regression models for practical use in predicting tumor grade. The models were tested prospectively on MR images from 29 patient studies. The performance of the models was compared against that of a radiologist. Neural network accuracy was 61% in distinguishing between low and high grade tumors. Multiple linear regression achieved an accuracy of 59%. Assessment of the images by a radiologist yielded 57% accuracy. We conclude that while certain MRI parameters may be statistically related to astrocytoma histologic grade, neural network and linear regression models cannot reliably use them to predict tumor grade.

Key words

Astrocytoma Neural network Magnetic resonance imaging Brain neoplasms 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dean BL, Drayer BP, Bird CR, Flom RA, Hodak JA, Coons SW, Carey RG (1990) Gliomas: classification with MR imaging. Radiology 174: 411–415Google Scholar
  2. 2.
    Kelly PJ, Daumas-Duport C, Scheithauer BW, Kall BA, Kispert DB (1987) Stereotactic histologic correlations of computed tomography- and magnetic resonance imagingdefined abnormalities in patients with glial neoplasms. Mayo Clin Proc 62: 450–459Google Scholar
  3. 3.
    Tervonen O, Forbes GS, Scheithauer BW, Dietz MJ (1992) Diffuse “fibrillary” astrocytomas: correlation of MRI features with histopathologic parameters and tumor grade. Neuroradiology 34: 173–178Google Scholar
  4. 4.
    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: explorations in the microstructures of cognition, vol 1. MTT Press, Cambridge, pp 675–695Google Scholar
  5. 5.
    Kleihues P, Burger PC, Scheithauer BW (1991) World Health Organization classification of tumors of the central nervous system. Springer, New YorkGoogle Scholar
  6. 6.
    Daumas-Duport C, Monsaigneon V, Blond S, Munari C, Musolino A, Chodkiewicz JP, Missir O (1987) Serial stereotactic biopsies and CT scan in gliomas: correlative study in 100 astrocytomas, oligoastrocytomas and oligodendrocytomas. J Neuro-Oncol 4: 317–328Google Scholar
  7. 7.
    Gross GW, Boone JM, Greco-Hunt V, Greenberg B (1990) Neural networks in radiologic diagnosis II: interpretation of neonatal chest radiographs. Invest Radiol 25: 1017–1023Google Scholar
  8. 8.
    Asada N, Doi K, MacMahon H, et al (1990) Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: pilot study. Radiology 177: 857–860Google Scholar

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  • P. S. Christy
    • 1
  • O. Tervonen
    • 1
  • B. W. Scheithauer
    • 1
  • G. S. Forbes
    • 1
  1. 1.Mayo ClinicRochesterUSA

Personalised recommendations