Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Biocybernetics and Biomedical Engineering

1 2004

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

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

Świercz M., Krejza J., Mariak Z., Bień M.

Biocybernetics and Biomedical Engineering

2004

Vol. 24, no. 1

3-16

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.