An optimized SVM based possibilistic fuzzy c-means clustering algorithm for tumor segmentation
- PDF / 9,617,882 Bytes
- 29 Pages / 439.642 x 666.49 pts Page_size
- 27 Downloads / 238 Views
An optimized SVM based possibilistic fuzzy c-means clustering algorithm for tumor segmentation Sreedhar Kollem1,4
· Katta Ramalinga Reddy2 · Duggirala Srinivasa Rao3
Received: 30 April 2020 / Revised: 17 August 2020 / Accepted: 20 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract To design an efficient partial differential equation-based total variation method for denoising and possibilistic fuzzy c-means clustering algorithm for segmentation and these methods presented the more detailed information of the MRI medical images compared to traditional methods. In this article, the pipeline of the proposed method described by two modules like pre-processing and segmentation. In pre-processing, noisy image is decomposed using nonsubsampled contourlet transform and it contains highpass contourlet coefficient (i.e., noisy coefficient) is removed by the threshold method as well. After reconstruction, the primary denoised image is enhanced by an improved partial differential equation-based total variation method in terms of image details like edges, boundaries, etc. In segmentation, the enhanced primary denoised image is segmented by an improved possibilistic fuzzy cmeans clustering algorithm that avoids limitations in possibilistic c-means, fuzzy c-means, and K-means clustering. Next, a support vector machine classifier is utilized to identify brain tissues into gray matter, white matter, cerebrospinal fluid, and tumor part. The parameters were optimally selected by a grey wolf optimization algorithm for the classification of brain tissues. The performance of the proposed method is computed with reference to peak signal-to-noise ratio, mean square error, structural similarity index, sensitivity, specificity, and accuracy. The experimental results claimed that the proposed method is better than the traditional methods. Keywords Nonsubsampled contourlet transform · Partial differential equations · Possibilistic fuzzy C-means clustering · Support vector machine · Grey wolf optimization
Sreedhar Kollem
[email protected] 1
Department of ECE, School of Engineering, SR University, Warangal 506371, Telangana, India
2
Department of ETM, G. Narayanamma Institute of Technology and Science, Hyderabad 500104, Telangana, India
3
Department of ECE, JNTUH College of Engineering, Kukatpally, Hyderabad 500085, Telangana, India
4
Research Scholar, Department of ECE, JNTUH University, Hyderabad 500085, Telangana, India
Multimedia Tools and Applications
1 Introduction In this section, the authors have presented several methods that address the denoising and segmentation areas of MRI medical images. The outline of the different methods is described as follows: Kollem et al. [17] have presented a method that enhances noisy medical images through a threshold method, a modified transformation-based gamma correction method and an improved fourth-order partial differential equation method. In denoising results, some of the enhanced images are seen as noisy by the wrong choice of tetromi
Data Loading...
