Automatic fetal measurements in ultrasound using constrained probabilistic boosting tree
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Hi-index | 0.00 |
Measurement of the fetal head circumference and diameters in addition to the femur length is crucial for the estimation of fetal age and growth pattern. Due to the noisy nature of ultrasound images and variation in image acquisition and measurement techniques, manual measurements of these parameters are subject to inter and intra-observer variability. The main objective of this work is to apply morphologically-based algorithms in order to recognize the fetal head contour in the ultrasound image, refine its shape and compensate for different irregularities, then correctly measure its dimensions, thus attaining accuracy and reproducibility of measurements. The automation algorithms utilize morphological operations, Hough transforms, and tracing methods. Measurements performed using the automation algorithms were closely correlated to those obtained manually and have been verified using many cases. Automation algorithms can be further improved to be performed online and can be implemented in the ultrasound machine, thus achieving consistency of fetal measurements.