SEMIAUTOMATED SEGMENTATION OF OVARIAN FOLLICULAR ULTRASOUND IMAGES USING A KNOWLEDGE-BASED ALGORITHM

The application of a knowledge-based segmentation method to the proble m of automatically detecting the outer follicle wall boundary in ultra sonographic images of ovaries is presented, A combination of computer detection and interactive adjustment was used to define an approximate inner follicle-wall boundary, which was then used by the computer alg orithm as a priori knowledge to automatically find the outer follicle- wall border, The segmentation algorithm was tested on ultrasonographic images of women's ovaries that were imaged in vivo, The semiautomatic segmentations were compared to segmentations by an expert human obser ver in terms of border placement differences and in terms of quantitat ive parameters relevant to the physiologic status of the follicles, Th ese physiological parameters include total and specific signal intensi ty from the follicle and from the follicle wall, The computer-detected outer follicle wall boundaries correlated well with the human observe r-defined wall boundaries, in terms of enclosed follicle area, specifi c and total follicle signal, enclosed wall area, and specific and tota l wall signal, The actual border placement differences were also small , with a maximum placement difference of 1.47 +/- 0.83 mm and a root m ean square (r.m.s.) placement difference of 0.59 +/- 0.28 mm. (C) 1998 World Federation for Ultrasound in Medicine & Biology.