Segmentation of ovarian follicles using geometric properties, texture descriptions, and boundary information

The size and number of follicles present within an ovary may be used as an indicator of fertility in women.Ultrasound is the imaging modality of choice for obtaining information on the follicles as it is inexpensive and readily available. A method of segmenting the follicles and ovary and producing accurate 2D and 3D representa- tions would be of great benefit to a large segment of the population. However, the nature of ultrasound imagesmeans that standard approaches to segmentation based on image gradients or detecting regions of homogeneous grey-level alone are inadequate. A semi-automatic method of segmentation which combines a texture based classification for initial segmen-tation with deformable models to provide descriptions of individual objects is extended by imposing geometricconstraints on the relationships between the individual objects present within an image. Since we are interested in segmenting the individual objects over a 3D spatial stack we use the results from one