Filtering and segmentation of a uterine fibroid with an ultrasound images

Abstract

Image segmentation is important tasks in medical image analysis. The challenges in medical image segmentation arise due to poor image contrast and artifacts that result in missing or diffuse organ/tissue boundaries. The segmentation of an ultrasound image is a difficult task as it suffers from speckle noise. The main aim of this work is to segment the fibroid in the uterus. Uterine fibroid is the most common benign tumour of the female in the world. Uterine Fibroid segmentation in patient is the challenging task manually. Exactly extracting the fibroid in the uterus is the challenging task because of size, location and low contrast boundaries. Instead of doing the segmentation manually, this work proposes a new method for segmenting the fibroid in the uterus. The performance of this method is also commendable.