Assessment of the middle cerebral artery spasm with learning vector quantization neural networks

• Autorzy: Świercz M. , Krejza J. , Mariak Z. , Bień M.
• Języki publikacji: EN

Abstrakty

EN

With transcranial color-coded Doppler sonography (TCCS), blood velocity in the middle cerebral (MCA) can be measured and used for diagnosis os spasm in this artery. The interpretation of TCCS results is not straightforward however. In this study blood velocities in the MCA's, obtained in one hundred consecutive patients, were classified with the use of artificial neural networks. The results of cerebral angiography were used as the criteria for evaluation of classification accuracy. The neural networks show very good performance in the two-class separation problem. In moderate-to-severe spasm detection, classification accuracy amounted to 92 % and in the assessment of vasospasm of other grades - 87%. The accuracy was higher than that obtained by the human investigator.

Słowa kluczowe

EN

cerebral vasospasm; neural networks; medical data classification

PL

skurcz naczyń mózgowych; sieć neuronowa; klasyfikacja danych medycznych

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2004
• Tom: Vol. 24, no. 1
• Strony: 3--16
• Opis fizyczny: Bibliogr. 21 poz., tab., wykr.

Twórcy

autor

Świercz M.

• Electrical Faculty, Białystok Technical University, ul. Wiejska 45D, 15-351 Białystok, Poland

autor

Krejza J.

• Departament of Radiology, Medical University of Białystok, ul. M. Curie-Skłodowskiej 24a, 15-276 Białystok, Poland

autor

Mariak Z.

• Departament of Neurosurgery, Medical University of Białystok, ul. M. Curie-Skłodowskiej 24a, 15-276 Białystok, Poland

autor

Bień M.

• Departament of Neurosurgery, Medical University of Białystok, ul. M. Curie-Skłodowskiej 24a, 15-276 Białystok, Poland

Bibliografia

• [1] Aaslid R„ Huber P„ Nornes H.: Evaluation of cerebrovascular spasm with transcranial Doppler ultrasound. Journal of Neurosurgery 1984,60, 37-41.
• [2] Babikian V.L., Feldmann E„ Wechsler L.R., et al.: Transcranial Doppler ultrasonography: year 2000 update. Journal of Neuroimaging 2000, 10, 101-115.
• [3] Baumgartner R.W., Mathis J„ Sturzenegger M., et al.: A validation study on the intraobserver reproducibility of transcranial color-coded duplex sonography velocity measurements. Ultrasound in Medicine & Biology 1994, 20,233-237.
• [4] Bishop C.M.: Neural networks for pattern recognition, Oxford University Press, Oxford 1997.
• [5] Gerhardt W„ Keller H.: Evaluation of test data from clinical studies. Scandinavian Journal of Clinical Laboratory Investigations Suppl. 1985, 5-74.
• [6] Grolimund P., Seiler W., Aaslid R„ et al.: Evaluation of cerebrovascular disease by combined extracranial and transcranial Doppler sonography. Experience in 1,039 patients. Stroke 1987, 18, 1018-1024.
• [7] Haykin S.: Neural networks. A comprehensive foundation, Prentice Hall Inc New York 1999 (2nd ed.).
• [8] Johnson R.A., Wichern D.W.: Applied multivariate statistical analysis, Prentice Hall, Englewood Cliffs, New York 1992.
• [9] Kohonen T, Barna G., and Chrisley R.: Statistical pattern recognition with neural networks: benchmark studies, in: Proc. of the Second IEEE International Conference on Neural Networks, SOS Printing, San Diego 1988.
• [10] Krejza J„ Mariak Z., Walecki J., et al.: 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 1999, 172, 213-218.
• [11] Krejza J., Mariak Z., Melhem E.R., et al.: A guide to identification of major cerebral arteries with transcranial color Doppler sonography. American Journal of Roentgenology 2000, 174, 1297-1303.
• [12] Krejza J., Mariak Z., Lewko J.: Standardization of flow velocities with respect to age and gender improves accuracy of transcranial color Doppler sonography in the diagnosis of middle cerebral artery spasm. American Journal of Roentgenology 2003, in press.
• [13] Łysakowski C., Walder B., Costanza M, Tramčr M.R.: Transcranial Doppler versus angiography in patients with vasospasm due to a ruptured cerebral aneurysm. A systematic review Stroke 2001, 32, 2292-2298.
• [14] Mariak Z., Swiercz M„ Krejza J., et al.: Intracranial pressure processing with artificial neural networks: classification of signal properties. Acta Neurochirurgica (Wien) 2000, 142, 407-412.
• [15] Mariak Z„ Krejza J„ Swiercz M„ et al.: Accuracy of transcranial color Doppler ultrasonography in the diagnosis of middle cerebral artery spasm determined by receiver operating characteristic analysis. Journal of Neurosurgery 2002, 96, 323-330.
• [16] Martin P.J., Evans D.H., Naylor A.R.: Measurement of blood flow velocity in the basal cerebral circulation: advantages of transcranial color-coded sonography over conventional transcranial Doppler. Journal of Clinical Ultrasound 1995, 23, 21-26.
• [17] Papadourakis G.M. (ed.): Proceedings of the 4th International Conference on Neural Networks and Expert Systems in Medicine and Healthcare — NNESMED 2001, Milos Island, Greece, 20-22.06. 2001, Technical Educational Institute of Crete, Heraklion 2001.
• [18] Quaghm S., Barahona R, Andreassen S. (eds.): Artificial Intelligence in Medicine, Proceedings of the 8th Conference on AI in Medicine in Europe - AIME 2001, Cascais, Portugal, 1-4.07.2001, Lecture Notes in Artificial Intelligence (LNAI2101), Springer-Verlag 2001.
• [19] Swiercz M., Mariak Z., Lewko J., et al.: Neural network methodology in detection of emergency states in neurosurgical patients. Medical and Biological Engineering & Computing 1998, 36, 717-722.
• [20] Zweig M.H., Campbell G.: Receiver-operating characteristics (ROC) plots: a fundamental evaluation tool in clinical medicine. Clinical Chemistry 1993, 39, 561-577.
• [21] Neural Computing. A technology handbook for NeuralWorks Professional II/PLUS and NeuralWorks Explorer, NeuralWare, Aspen Technology Inc., Pittsburgh 1998.