Momentum- and Resilient-Based Level Set for Medical Image Segmentation

Abstract

In this chapter, the authors present the technique of medical image segmentation which means to partition an image into non-overlapping regions based on intensity. The active contour is one of the most successful level set methods for segmentation and it is widely applicable in various image processing applications including medical image segmentation. Biomedical image segmentation and analysis plays an important role in medical science and healthcare. This chapter proposes a momentum term and resilient propagation-based gradient descent method which will remove the sensitivity of local minima of gradient descent. Proposed method is applicable in case of diseases like retinal, diabetic, and glaucoma, etc. Medical image segmentation via momentum and resilient propagation based gradient descent method can be optimized and effectively used. Extensive experiments have been performed over medical images to test the ability of the system. The proposed method is able to present the segmented medical image with clear and smooth boundary also it is simple to design and implementation.