Classification of SGS-SRAD Denoised MRI Using GWO Optimized SVM

Abstract

Automated accurate categorization of brain magnetic resonance images (MRI) is very important for disease diagnosis and treatment. In this paper, a new methodology for the detection of abnormality in brain MRI is suggested. The scale-invariant feature transform is first employed to extract features of MRI. Principal component analysis is applied to the extracted features and a minimal set of more essential features is obtained. Lastly, the obtained feature set is categorized as healthy or unhealthy using support vector machine (SVM)-based classification. The parameters of SVM, i.e. $C$ and $\sigma$ are optimized using Gray Wolf Optimization. However external noise and patient/organ movement degrade the quality of MRI, which in turn affect the classification accuracy. Therefore, a hybrid of Savitzky–Golay smoothing filter and speckle reducing anisotropic diffusion filter is used for preprocessing of the source image, which efficiently reduces the noise while preserving edges of the image. It is revealed from the results that proposed technique provides a classification accuracy of 99.61%. Thus the suggested technique may effectively diagnose diseases using MRI.

KEYWORDS:

• Gray Wolf Optimization
• Magnetic resonance image
• Principle component analysis
• Scale-invariant feature transform
• SGS-SRAD filter

Additional information

Notes on contributors

Sonal Goyal

Sonal Goyal completed her BTech degree in instrumentation and control engineering from Engineering College, Ajmer, Rajasthan in 2009 and MTech degree in process control from Netaji Subhas Institute of Technology, University of Delhi, in 2012, where she is pursuing her PhD degree. Her research interests include biomedical image processing and artificial intelligent control.

Navdeep Yadav

Navdeep Yadav received his BTech degree in biomedical engineering from C R State College of Engineering, Murthal, Haryana, in 2008 and MTech degree in process control from Netaji Subhas Institute of Technology, University of Delhi in 2010, where he is pursuing his PhD degree. His research interests include image processing and biomedical imaging. Email: [email protected]

Asha Rani

Asha Rani completed her BTech in electrical engineering from National Institute of Technology, Hamirpur in 1998 and MTech in electrical engineering from Indian Institute of Technology, Roorkee, in 2000. She did her PhD from Netaji Subhas Institute of Technology, University of Delhi in 2013. Currently, she is working as a professor in Division of Instrumentation and Control Engineering at Netaji Subhas Institute of Technology, New Delhi. Her interests include process control using intelligent control techniques and biomedical Instrumentation. Email: [email protected]

Vijander Singh

Vijander Singh completed his BTech in electrical engineering from GB Pant University of Agriculture & Technology, Pantnagar in 1995. He completed his MTech and PhD from Indian Institute of Technology, Roorkee, in 2000 and 2007, respectively. He is working as a professor in Division of Instrumentation and Control Engineering, Netaji Subhas Institute of Technology, New Delhi. His research interests include biomedical signal processing, image processing, process control and artificial intelligent control. Email: [email protected]