Automated ovarian follicle segmentation using region growing

An improved algorithm for ovarian follicle detection in ultrasound images is presented. This fully automated recognition algorithm is composed of three successive steps. First, the initial homogeneous regions are determined. Then, these initial regions are grown. Growing is controlled by the average grey-level and by a newly introduced weighted gradient of the image. In the last step, the regions that are probably follicles are extracted. The algorithm has been tested on 50 ovarian ultrasound images. The recognition rate of follicles was around 88%.