ICSES Transactions on Image Processing and Pattern Recognition
Vol. 5, No. 2, Jun. 2019
Research Directions and Future Trends in Medical Image Segmentation
a PRMCEAM, Amravati, India
b Sama College, IAU, Shoushtar Branch, Shoushtar, Iran
Highlights and Novelties
1- This editorial article discuses the evolution of medical image segmentation techniques.
2- The article ends with the discussion on the future trends and directions in this field.
3- In this article, some approaches are briefly discussed and compared.
4- Deep learning methods have also been included.
In the recent years, medical image analysis has turned to be the center of attention for the researchers and practitioners all over the world as it provides high-fidelity and minimally-invasive means for diagnosis, prognosis, therapy and follow-up procedures. Medical image processing techniques in the literature are concentrated vastly on the important processes of filtering, enhancement and object detection, and a variety of methods proposed to improve the image quality for both visual perception and feature detection where the image segmentation is indeed one of the most attractive yet complicated techniques. In this article, a brief updating on computational advances applied to medical image segmentation is provided along with the discussion of some popular methodologies for related medical image processing techniques.
Deep Learning Image Analysis Image Processing Image Segmentation Medical Imaging
Copyright and Licence
Copyright © International Computer Science and Engineering Society (ICSES). This article is an open-access article distributed under the terms and conditions of the Creative Commons Attribution Non Commercial 4.0 International (CC BY-NC 4.0) license, supported by creativecommons.orgcall_made
Cite this manuscript as
Vikramsingh Parihar, Hamid Reza Boveiri, "Research Directions and Future Trends in Medical Image Segmentation," ICSES Transactions on Image Processing and Pattern Recognition, vol. 5, no. 2, pp. 1-3, Jun. 2019.
For External Scientific Databeses