Study And Theoretical Analysis Of Various Segmentation Techniques For Ultrasound Images
Authors: S.Sheelaa, M.Sumathi
Abstract:
Image segmentation is an important and also necessary technique as it facilitates the delineation of anatomical structures and other region of interest in various imaging modalities such as Ultrasound, Computer Tomography… of medical field. Among the several imaging modalities, an Ultrasound technique plays a vital role in medical field because it is non-invasive and mainly radiation used in this modality is not harmful. On the other hand, the image obtained using this modality is distorted due to the several reasons like inherent noise of the equipment, lack of operator knowledge…etc. This makes the complexity in identifying the region of interest. Several segmentation techniques are used to segment the region of interest from the noisy image. This paper explores various segmentation techniques like edge based, threshold based, region based and texture based segmentation.
Keywords
Edge; Region; Threshold; Texture; Segmentation; Ultrasound
Citation: S.Sheelaa, M.Sumathi Study And Theoretical Analysis Of Various Segmentation Techniques For Ultrasound Images doi:10.1016/j.procs.2016.05.128
Available online: 7 June 2016
Copyright: © 2016 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Conclusion
In most automatic pictorial pattern recognition and image analysis, applications, the image segmentation plays an essential role. Each segmentation technique have advantages for example, global thresholding is advantageous in term of speed whereas, edge based segmentation have disadvantage that it require post processing such as edge linking. Similarly, segmentation by watersheds in advantageous as it procedures connected segmentation boundaries and also it provides simple framework for incorporation knowledge based constraints. From this study, it is concluded that depends on the proble domain and image characteristics, the choice of segmentation technique will vary.
