Fusion of Noise and Contrast Enhancement Filters for Efficient Ovarian Cancer RoI Localization
Suthamerthi Elavarasu1, Viji Vinod2
1Suthamerthi Elavarasu, Research Scholar, Department of Computer Applications, Dr. M.G.R. Educational and Research Institute University, Madoravoyal, Chennai (Tamil Nadu), India.
2Viji Vinod, Head, Department Computer Applications, Dr. M.G.R. Educational and Research Institute University, Madoravoyal, Chennai (Tamil Nadu), India.
Manuscript received on 07 December 2018 | Revised Manuscript received on 18 December 2018 | Manuscript published on 30 December 2018 | PP: 114-116 | Volume-8 Issue-2C2, December 2018 | Retrieval Number: 100.1/ijeat.B10251282C218/18©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The emerging trend of artificial intelligence sets new research goal for Computer-Aided Diagnosis (CAD) to provide precise ovarian cancer region to overcome the observational oversights of the radiologists. The CAD system allows automated detection and classification of ovarian cancer affecting region during real-time radiology scanning and potentially helping radiologists to avoid false negative observation of ovarian cancer and facilitate subsequent clinical management of patients to avoid critical conditions. However, the media images are usually subject of affect by Gaussian noise, speckle noise, etc. and contrast variations due to human skin conditions, and so on. So getting good quality medical images from scanning system extremely important task for CAD further process. This paper proposes the fusion of noise and contrast enhancement filter for ovarian cancer medical image quality enhancement for CAD. The proposed approach uses the wiener filter for noise removal and contrast limited adaptive histogram equalization (CLAHE) for contrast enhancement. This proposed approach enhances the ovarian cancer medical images quality and facilitates to localize the region of interest (RoI) of ovarian cancer regions. The proposed method is simulated with real ovarian cancer patient medical images on MATLAB and performance of these filters are compared with image quality parameter Peak Signal-to-Noise Ratio (PSNR).
Keywords: Ovarian Cancer, Noise Filter, Contrast Enhancement Filter, Wiener Filter, Contrast Limited Adaptive Histogram Equalization (CLAHE), Computer Aided Diagnosis (CAD), Machine Learning, Artificial Intelligent (AI).
Scope of the Article: Advanced Computer Networking