Automatic measurement of fetal head structures using ultrasound

Routine ultrasound exam in the second and third trimesters of pregnancy involves manually measuring fetal head and brain structures in 2-D scans. The procedure requires a sonographer to find the standardized visualization planes with a probe and manually place measurement of calipers on the structure of interest. The process is tedious, time consuming and introduces user variability into the measurements. This paper proposes an automatic fetal head and brain(AFHB) system for automatically measuring anatomical structures from 3-D ultrasound volumes. Input image is preprocessed and filtered. Hybrid mean filter is used in order to perform filtering, though there are different types of filters available, hybrid mean filter is commonly used in medical applications because it preserves edges and boundaries. Segmentation is performed by gray level thersholding and threshold value is chosen based on k-mean clustering algorithm. Feature extraction is done to mark and measure OFD, BPD&HC. The feature here are texture (brain structures) which include lateral ventricle, cisterna magna and cerebellm. The accuracy of the AFHB system is within inter-user variability and the running time is fast, which meets the requirements for clinical use.