Learning Vector Quantization Neural Networks Improve Accuracy of Transcranial Color-coded Duplex Sonography in Detection of Middle Cerebral Artery Spasm—Preliminary Report

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.

[1]  G Becker,et al.  Transcranial color-coded real-time sonography in adults. , 1990, Stroke.

[2]  W. Sorteberg,et al.  Cerebral vasospasm diagnosis by means of angiography and blood velocity measurements , 2005, Acta Neurochirurgica.

[3]  Martti Juhola,et al.  Evaluation and classification of otoneurological data with new data analysis methods based on machine learning , 2007, Inf. Sci..

[4]  R. Aaslid,et al.  Evaluation of cerebrovascular spasm with transcranial Doppler ultrasound. , 1984, Journal of neurosurgery.

[5]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[6]  Jaroslaw Krejza,et al.  Assessment of Cerebrovascular Pathophysiology , 2003 .

[7]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[8]  J. Krejza,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. , 1999, AJR. American journal of roentgenology.

[9]  G Becker,et al.  [Transcranial color-coded real time sonography in adults. Part 2: Cerebral hemorrhage and tumors]. , 1991, Ultraschall in der Medizin.

[10]  K Schreiber,et al.  Significant reduction in the rate of false-negative cervical smears with neural network-based technology (PAPNET Testing System). , 1997, Human pathology.

[11]  Adnan I Qureshi,et al.  Symptomatic vasospasm diagnosis after subarachnoid hemorrhage: Evaluation of transcranial Doppler ultrasound and cerebral angiography as related to compromised vascular distribution , 2002, Critical care medicine.

[12]  J. Krejza,et al.  A guide to the identification of major cerebral arteries with transcranial color Doppler sonography. , 2000, AJR. American journal of roentgenology.

[13]  Paulo J. G. Lisboa,et al.  The Use of Artificial Neural Networks in Decision Support in Cancer: a Systematic Review , 2005 .

[14]  M. Swiercz,et al.  Intracranial Pressure Processing with Artificial Neural Networks: Prediction of ICP Trends , 2000, Acta Neurochirurgica.

[15]  M. Costanza,et al.  Transcranial Doppler Versus Angiography in Patients With Vasospasm due to a Ruptured Cerebral Aneurysm: A Systematic Review , 2001, Stroke.

[16]  Miroslaw Swiercz,et al.  Accuracy of transcranial color Doppler ultrasonography in the diagnosis of middle cerebral artery spasm determined by receiver operating characteristic analysis. , 2002, Journal of neurosurgery.

[17]  J. Krejza,et al.  Clinical Applications of Transcranial Color‐Coded Duplex Sonography , 2004, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[18]  J S Uebersax,et al.  Modeling approaches for the analysis of observer agreement. , 1992, Investigative radiology.

[19]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[20]  L R Caplan,et al.  Transcranial Doppler Ultrasonography: Year 2000 Update , 2000, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[21]  Chris D. Nugent,et al.  Evaluation of inherent performance of intelligent medical decision support systems: utilising neural networks as an example , 2003, Artif. Intell. Medicine.

[22]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[23]  Zenon Mariak,et al.  Standardization of flow velocities with respect to age and sex improves the accuracy of transcranial color Doppler sonography of middle cerebral artery spasm. , 2003, AJR. American journal of roentgenology.

[24]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[25]  Terrence L. Fine,et al.  Feedforward Neural Network Methodology , 1999, Information Science and Statistics.

[26]  Michael R. Pinsky.  Cerebral blood flow : mechanisms of ischemia, diagnosis and therapy , 2002 .

[27]  Teuvo Kohonen,et al.  Statistical pattern recognition with neural networks , 1988, Neural Networks.