| INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY |
Prev
Next
|
|
|
Magnetic-resonance image segmentation based on improved variable weight multi-resolution Markov random field in undecimated complex wavelet domain |
| Hong Fan(范虹)1,†, Yiman Sun(孙一曼)1, Xiaojuan Zhang(张效娟)2, Chengcheng Zhang(张程程)1, Xiangjun Li(李向军)3, and Yi Wang(王乙)4 |
1 School of Computer Science, Shaanxi Normal University, Xi'an 710062, China;
2 School of Computer Science, Qinghai Normal University, Xining 810003, China;
3 School of Information Engineering, Xi'an University, Xi'an 710065, China;
4 Department of Biomedical Engineering, Cornell University, Ithaca, NY 14853, USA |
|
|
|
|
Abstract To solve the problem that the magnetic resonance (MR) image has weak boundaries, large amount of information, and low signal-to-noise ratio, we propose an image segmentation method based on the multi-resolution Markov random field (MRMRF) model. The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales. The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm, and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation. The results are then segmented by the improved MRMRF model. In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model, it is proposed to introduce variable weight parameters in the segmentation process of each scale. Furthermore, the final segmentation results are optimized. We name this algorithm the variable-weight multi-resolution Markov random field (VWMRMRF). The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness, and can accurately and stably achieve low signal-to-noise ratio, weak boundary MR image segmentation.
|
Received: 21 October 2020
Revised: 14 January 2021
Accepted manuscript online: 01 February 2021
|
|
PACS:
|
87.57.N-
|
(Image analysis)
|
| |
87.61.-c
|
(Magnetic resonance imaging)
|
| |
87.63.lm
|
(Image enhancement)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant No. 11471004), and the Key Research and Development Program of Shaanxi Province, China (Grant No. 2018SF-251). |
Corresponding Authors:
Hong Fan
E-mail: fanhong@snnu.edu.cn
|
Cite this article:
Hong Fan(范虹), Yiman Sun(孙一曼), Xiaojuan Zhang(张效娟), Chengcheng Zhang(张程程), Xiangjun Li(李向军), and Yi Wang(王乙) Magnetic-resonance image segmentation based on improved variable weight multi-resolution Markov random field in undecimated complex wavelet domain 2021 Chin. Phys. B 30 078703
|
[1] Bao S L, Du J and Gao S 2013 Acta Phys. Sin. 62 088701 (in Chinese)
[2] Mann R M, Kuhl C K, Kinkel K and Boetes C 2008 Eur. Radiol. 18 1307
[3] Jeevakala S, Brintha T A and Rangasami R 2018 Biomed. Signal Process. Control 39 117
[4] Panigrahi L, Verma K and Singh B K 2019 Expert Systems with Applications 115 486
[5] Zhang J, Saha A, Zhu Z and Mazurowski M A 2018 IEEE Trans. Med. Imaging 38 435
[6] Ahmadvand A and Daliri M R 2015 Appl. Math. Comput. 256 808
[7] Geman S and Geman D 1984 IEEE Trans. Pattern Analysis and Machine Intelligence 6 721
[8] Azmi R and Norozi N 2011 J. Med. Signals and Sensors 1 156
[9] Ribes S, Didierlaurent D, Decoster N, Gonneau E, Risser L, Feillel V and Caselles O 2014 IEEE Trans. Med. Imaging 33 1986
[10] Goubalan S R, Goussard Y and Maaref H 2016 2016 IEEE International Conference on Image Processing (ICIP) September 25-28, 2016, Phoenix, USA, p. 2653
[11] Lee G G and Chen C H 1996 1996 IEEE Nuclear Science Symposium. Conference Record November 2-9, 1996, Anaheim, USA, p. 1937
[12] Wang L and Liu J 1999 Pattern Recognition Lett. 20 171
[13] Liu G and Guo T 2010 2010 6th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM), September 23-25, 2010, Chengdu, China, p. 1
[14] Tang W, Zhang C and Zou H 2013 Intelligent Computing Theories and Technology July, 2013, Berlin, Heidelberg, p. 56
[15] Hill P, Achim A and Bull D 2012 2012 19th IEEE International Conference on Image Processing September 30-October 3, 2012, Orlando, USA, p. 1205
[16] Selesnick I W, Baraniuk R G and Kingsbury N C 2005 IEEE Signal Process. Mag. 22 123
[17] Kaur G and Vashist S 2017 International Journal of Computer Applications 167 26
[18] Kingsbury N 1999 Philosophical Transactions Mathematical Physical and Engineering Sciences 357 2543
[19] Jain A K 2010 Pattern Recognition Lett. 31 651
[20] Celeux G, Forbes F and Peyrard N 2003 Pattern Recognition 36 131
[21] Fan H, Zhu Y C, Wang F M and Zhang X M 2014 Acta Phys. Sin 63 392 (in Chinese)
[22] Web B 2004 Simulated Brain Database McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill
[23] Turaga D S, Chen Y and Caviedes J 2004 Signal Processing: Image Commun. 19 173
[24] Dice L R 1945 Ecology 26 297
[25] Menze B H, Jakab A, Bauer S et al. 2015 IEEE Trans. Med. Imaging 34 1993
[26] Bakas S, Akbari H, Sotiras A, Bilello M, Rozycki M, Kirby J S, Freymann J B, Farahani K and Davatzikos C 2017 Sci. Data 4 170117
[27] Bakas S, Reyes M, Jakab A et al. 2018 arXiv:1811.02629v3 [cs.CV] |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
