AN AUTOMATED INTELLIGENT DIAGNOSTIC SYSTEM FOR THE INTERPRETATION OF UMBILICAL ARTERY DOPPLER VELOCIMETRY

The objective is to develop an automated intelligent diagnostic system for the interpretation of umbilical artery velocity waveforms. An ult rasound instrument with pulsed-wave Doppler is connected to a microcom puter by means of a frame grabber. After data acquisition, umbilical D oppler velocimetry is handled as a pattern recognition (feature extrac tion and classification) and decision-making problem. Automated image processing (enhancement, smoothing/thresholding and edge detection) an d analysis are used for feature extraction, Six waveform indices obtai ned by feature extraction are used as input layer to vector quantizati on which classifies waveforms into six groups. A clinical decision is assigned to each group by the medical expert. Our system is trained by 278 and 380 waveform images of 94 normal and 157 high risk pregnancie s, respectively. The system was tested with 193 and 61 images of norma l and risky pregnancies; it was demonstrated that sensitivity and spec ificity of the system are 54.1% and 80.3%, respectively.