Computer assisted measurement of cervical length from transvaginal ultrasound images

We describe an image processing algorithm that identifies the anatomic landmarks of the cervix on a transvaginal ultrasound image and determines the standard cervical length. The system is composed of four stages: The first stage is adaptive speckle suppression using variable length sticks algorithm. The second stage is the location of the internal cervical opening or 'os' using a region-based segmentation. The third stage is delineation of the cervical canal. The fourth stage uses gray level summation patterns and prior knowledge to first localize the tissue boundary of the external cervix. A template is then used to determine the specific location of the external os. The cervical length is determined and calculated to image scale. For validation, 101 cervical ultrasound images were selected from a series of 37 examinations performed on 17 patients over an 8-month period. Repeated measurements of cervical length using the computer assisted method were compared with those of two experienced sonographers. The mean coefficient of variation for serial measurements was 1.1% for the computer assisted method and averaged 4.7% for the manual method. In a pairwise comparison, the mean cervical length for the computer method was not different from the mean manual cervical length.