Comparative study on ovarian follicle detection using segmentation techniques

Abstract

Image segmentation is one of the most critical tasks in ultrasound image analysis. It simply indicates partitioning the image into different regions which contain similar attributes which may be color, intensity or texture. Ultrasound imaging is the hardest medical imaging modality upon which to perform segmentation. Ultrasound images are difficult to segment due to presence of speckle noise and the boundaries of abnormal regions are also difficult to recognize due to similarity. This paper surveys various image segmentation techniques for the detection of the follicles presents in ovary to recognize and diagnose the various forms of ovulatory failure that can contribute to infertility. Performances of some of the previous works are identified and compared.