ABSTRACT
In this paper, an iterative implement of level set methodology has been proposed for the precise segmentation of normal and abnormal tissues in magnetic resonance imaging (MRI) brain images. In this segmentation, the normal tissues such as WM (white matter), GM (grey matter), and CSF (cerebrospinal fluid) with other regions of human head such as skull, marrow, and muscles skin are segmented and abnormal tissues such as haemorrhage, oedema, and tumour can be segmented if any. The segmentation is done by using iterative three region level set method based on the condition sharp peak greater than three. The iterative segmented component generates a hierarchical structure for correct segmentation. The performance of the segmentation method is estimated by different metrics such as accuracy, similarity index, and relative error. The performance of segmentation method is examined using a defined set of MRI brain.
ACKNOWLEDGEMENTS
It is my privilege to thank Dr Pradip Saha MD in Radiology from NRS Medical College. He is currently working as radiologist at M N Roy Diagnostic Center, Kolkata, India. He supported for reference image creation, guided, and given us the valuable suggestions to complete this paper, and to enrich my knowledge.
DISCLOSURE STATEMENT
No potential conflict of interest was reported by the authors.
Additional information
Notes on contributors
![](/cms/asset/aab7816f-493e-4425-aa33-57ec101dfb9d/tijr_a_1331757_uf0001_oc.jpg)
Sudipta Roy
Sudipta Roy submitted his PhD degree (Computer Science and Engineering) in the field of image processing Department of Computer Science and Engineering, University of Calcutta (C.U), Kolkata, India. He is author of over 30 papers in national and international journals (SCI index) and conferences including IEEE, Springer, Elsevier, etc. Currently, he is working as an assistant professor in the Department of Computer Science and Engineering, U.V.Patel College of Engineering, Ganpat University, Kherva, Mehsana, Gujarat, India.
E-mail: [email protected]
![](/cms/asset/5edd2e85-040a-4f1e-9b7d-f70ba4e588c6/tijr_a_1331757_uf0002_oc.jpg)
Debnath Bhattacharyya
Debnath Bhattacharyya received his PhD degree (Tech, Computer Science and Engineering) from University of Calcutta. Currently, he is a professor with IT Department of Computer Science and Engineering, Vignan University. He has published 145 research papers in international journals and conferences and four text books for computer science.
E-mail: [email protected]
![](/cms/asset/e5bedc4d-e9ad-4d02-9ddc-c7b8fa5c8487/tijr_a_1331757_uf0003_oc.jpg)
Samir Kumar Bandyopadhyay
Samir Kumar Bandyopadhyay, B.E., M.Tech., Ph. D (Computer Science and Engineering), C.Engg., D.Engg., FIE, FIETE, Sr. Member IEEE, currently, Professor of Computer Science & Engineering, University of Calcutta, Kolkata, India. Visiting Faculty, Dept. of Comp. Sc., Southern Illinois University, USA, MIT, California Institute of Technology, etc. He is Chairman, Science & Engineering Research Support Society (SERSC, Indian Part), Fellow of Computer Society of India, Sectional President of ICT of Indian Science Congress Association, 2008–2009, Senior Member of IEEE, Member of ACM, Fellow of Institution of Engineers (India), Fellow of Institution of Electronics and Tele Communication Engineers, India. He has published 300 research papers in International & Indian Journals and 5 leading text books for Computer Science and Engineering.
E-mail: [email protected]
![](/cms/asset/d0f2104a-c1e6-41d5-9029-a8a859a5d4d3/tijr_a_1331757_uf0004_oc.jpg)
Tai-Hoon Kim
Tai-Hoon Kim received BE and ME degrees from Sungkyunkwan University in Korea and PhD degree from University of Bristol in UK and University of Tasmania in Australia. Now, he is working for Department of Convergence Security, Sungshin W. University, Korea. His main research areas are security engineering for IT products, IT systems, development processes, and operational environments. He has published 300 research papers in international journals and conferences. He is editor of Elsevier, Springer, and many more journals.
E-mail: [email protected]