Abstract
To determine the performance of an artificial neural network in transcranial color-coded duplex sonography (TCCS) diagnosis of middle cerebral artery (MCA) spasm. TCCS was prospectively acquired within 2 h prior to routine cerebral angiography in 100 consecutive patients (54M:46F, median age 50 years). Angiographic MCA vasospasm was classified as mild (<25% of vessel caliber reduction), moderate (25–50%), or severe (>50%). A Learning Vector Quantization neural network classified MCA spasm based on TCCS peak-systolic, mean, and end-diastolic velocity data. During a four-class discrimination task, accurate classification by the network ranged from 64.9% to 72.3%, depending on the number of neurons in the Kohonen layer. Accurate classification of vasospasm ranged from 79.6% to 87.6%, with an accuracy of 84.7% to 92.1% for the detection of moderate-to-severe vasospasm. An artificial neural network may increase the accuracy of TCCS in diagnosis of MCA spasm.
Similar content being viewed by others
References
Aaslid, R., Huber, P., & Nornes, H. (1984). Evaluation of cerebrovascular spasm with transcranial Doppler ultrasound. Journal of Neurosurgery, 60, 37–41.
Babikian, V. L., Feldmann, E., Wechsler, L. R., Newell, D., Gomez, C. R., Bogdahn, U., et al. (2000). Transcranial Doppler ultrasonography: Year 2000 update. Journal of Neuroimaging, 10, 101–115.
Babikian, V. L., Gomes, J., & Krejza, J. (2002). Assessment of cerebrovascular pathophysiology. In R. M. Pinsky (Ed.), Cerebral blood flow: mechanisms of ischemia, diagnosis and therapy. Berlin: Springer.
Bishop, C. M. (1997). Neural networks for pattern recognition. Oxford: Oxford University Press.
Bogdahn, U., Becker, G., Winkler, J., Greiner, K., Perez, J., & Meurers, B. (1990). Transcranial color-coded real time sonography in adults. Stroke, 21, 1680–1688.
Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines (and other kernel-based learning methods). Cambridge: Cambridge University Press.
Fine, T. (1999). Feedforward neural network methodology. Berlin: Springer.
Haykin, S. (1999). Neural networks. A comprehensive foundation. New York: Prentice Hall.
Johnson, R. A., & Wichern, D. W. (1992). Applied multivariate statistical analysis. New York: Prentice Hall.
Kohonen, T., Barna, G., & Chrisley, R. (1988). Statistical pattern recognition with neural networks: benchmark studies. In Proc. of the Second IEEE International Conference on Neural Networks. San Diego: SOS Printing.
Koss, L. G., Sherman, M. E., Cohen, M. B., Anes, A. R., Darragh, T. M., Lemos, L. B., et al. (1997). Significant reduction in the rate of false-negative cervical smears with neural network-based technology (PAPNET testing system). Human Pathology, 28, 1196–1203. doi:10.1016/S0046-8177(97)90258-6.
Krejza, J., & Baumgartner, R. W. (2004). Clinical applications of transcranial color-coded duplex sonography. Journal of Neuroimaging, 14, 215–225. doi:10.1177/1051228403259274.
Krejza, J., Mariak, Z., & Lewko, J. (2003). Standardization of flow velocities with respect to age and gender improves accuracy of transcranial color Doppler ultrasonography in the diagnosis of middle cerebral artery spasm. American Journal of Roentgenology, 181, 245–252.
Krejza, J., Mariak, Z., Melhem, E. R., & Bert, R. J. (2000). A guide to the identification of major cerebral arteries with transcranial color Doppler sonography. American Journal of Roentgenology, 174, 1297–1303.
Krejza, J., Mariak, Z., Walecki, J., Szydlik, P., Lewko, J., & Ustymowicz, A. (1999). Transcranial color Doppler sonography of basal cerebral arteries in 182 healthy subjects: age and sex variability and normal reference values for blood flow parameters. American Journal of Roentgenology, 172, 213–218.
Lindegaard, K. F., Nornes, H., Bakke, S. J., Sorteberg, W., & Nakstad, P. (1989). Cerebral vasospasm diagnosis by means of angiography and blood velocity measurements. Acta Neurochirurgica, 100, 12–24. doi:10.1007/BF01405268.
Lisboa, P. J., & Taktak, A. F. G. (2006). The use of artificial neural networks in decision support in cancer: a systematic review. Neural Networks, 19, 408–415. doi:10.1016/j.neunet.2005.10.007.
Lysakowski, C., Walder, B., Costanza, M. C., & Tramer, M. R. (2001). Transcranial Doppler versus angiography in patients with vasospasm due to a ruptured cerebral aneurysm: a systematic review. Stroke, 32, 2292–2298. doi:10.1161/hs1001.097108.
Mariak, Z., Krejza, J., Swiercz, M., Kordecki, K., & Lewko, J. (2002). Accuracy of transcranial color Doppler ultrasonography in the diagnosis of middle cerebral artery spasm determined by receiver operating characteristic analysis. Journal of Neurosurgery, 96, 323–330.
Siermala, M., Juhola, M., Laurikkala, J., Iltanen, K., Kentala, E., & Pyykkö, I. (2007). Evaluation and classification of otoneurological data with new data analysis methods based on machine learning. Information Sciences, 177, 1963–1976. doi:10.1016/j.ins.2006.11.002.
Smith, A. E., Nugent, C. D., & McClean, S. I. (2003). Evaluation of inherent performance of intelligent medical decision support systems: utilising neural networks as an example. Artificial Intelligence in Medicine, 27, 1–27. doi:10.1016/S0933-3657(02)00088-X.
Suarez, J. I., Qureshi, A. I., Yahia, A. B., Parekh, P. D., Tamargo, R. J., Williams, M. A., et al. (2002). Symptomatic vasospasm diagnosis after subarachnoid hemorrhage: evaluation of transcranial Doppler ultrasound and cerebral angiography as related to compromised vascular distribution. Critical Care Medicine, 30, 1348–1355. doi:10.1097/00003246-200206000-00035.
Swiercz, M., Mariak, Z., Krejza, J., Lewko, J., & Szydlik, P. (2000). Intracranial pressure processing with artificial neural networks: prediction of ICP trends. Acta Neurochirurgica, 142, 401–406. doi:10.1007/s007010050449.
Uebersax, J. S. (1992). Modeling approaches for the analysis of observer agreement. Investigative Radiology, 27, 738–743. doi:10.1097/00004424-199209000-00017.
Acknowledgments
Supported by American Heart Association Established Investigator Award grant 044099N—(Krejza J) and Polish State Committee for Scientific Research—grant 3 T11E 027 28 (Swiercz M).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Swiercz, M., Kochanowicz, J., Weigele, J. et al. Learning Vector Quantization Neural Networks Improve Accuracy of Transcranial Color-coded Duplex Sonography in Detection of Middle Cerebral Artery Spasm—Preliminary Report. Neuroinform 6, 279–290 (2008). https://doi.org/10.1007/s12021-008-9023-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12021-008-9023-0