Abstract
Neural networks are a computational paradigm model of the human brain that has become popular in recent years. We have tried to address the problem of Glioma by creating a more accurate classifier which can act as an expert assistant to medical practitioners. Brain stem gliomas are now recognized as a heterogenous group of tumors. In this study proposed a prediction of Glioma in MR images using weight optimized neural network. Magnetic Resonance (MR) images are affected by rician noise which limits the accuracy of any quantitative measurements from the data. A recently proposed filter for rician noise removal is analyzed and adapted to reduce this noise in MR images. This parametric filter, named Non-Local Means (NLM), is highly dependent on setting its parameters. Experimental results reveal the efficacy of the adduced methodology as compared to the related work.
Highlights
These grades reflect the growth potential and aggressiveness of the tumor.Magnetic Resonance Imaging (MRI) has been often the medical imaging method of choice when the soft tissue delineation is necessary
The human brain MRI suffers from rician noise
We proposed a classification of MR image using the genetic optimized neural network, imposed with sequential forward selection and k-Nearest Neighbor (k-NN) classifier
Summary
These grades reflect the growth potential and aggressiveness of the tumor. Magnetic Resonance Imaging (MRI) has been often the medical imaging method of choice when the soft tissue delineation is necessary. Unlike previous denoise methods that rely on the local regularity assumption, the NLM exploits the spatial correlation in the entire image for noise removal It can adjust each pixel value with a weighted average of other pixels whose neighborhood has a similar geometrical configuration. Explained the construction methodologies of moment invariant functions which can be used to give distinctive brain images for accurate predictive classification of brain tumor. The adduced work provides a framework for prediction of Glioma in MR image weight optimized neural network.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
