Abstract
Segmenting ultrasonic images is difficult because they consist of many types of noise such as additive and multiplicative noise. Echocardiographic images are greatly affected by speckle noise, which is a type of multiplicative noise. Motion of the heart wall and multi-directional blood flow makes echocardiographic imagery complicated. Closed contour deformable models are the solution to segmenting echocardiographic images. In a conventional approach, segmenting the right boundary of the heart is difficult due to motion and speckle noise. This chapter proposes a technique with a new regularization model to help the curve approach its desired boundary while maintaining its smoothness. The intensity in100formation at different regions in the image also matters for differentiating the boundaries of a curve, therefore we propose a region-based active contour model using intensity information. The speckle density is used for data-fitting energy to find intensity information in local regions. The proposed improved regularization and fitting-based segmentation (IRFS) technique with a new regularization model and fitting function makes it possible for the curve to find its right minima and region. The IRFS technique also improves the capability of the curve to draw the desired boundaries.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Image Processing for Automated Diagnosis of Cardiac Diseases
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.