Abstract
MRI is the imaging technique most often used to detect brain tumor. A brain tumor is a knot, or mass, of abnormal cells in parts of the brain. Brain tumors can be either malignant or benign and can be located in the tissues of the brain. In this research study, a computerized approach has been presented where MRI gray- scale images were assimilated for the detection of brain tumor. This study suggested a computerized approach that involves improvement at the elementary stage to reduce the gray-scale color variations. Filter operation was used to eliminate undesired noises as much as feasible to accommodate better segmentation. As this study test grayscale images therefore; threshold-based OTSU segmentation was used instead of color segmentation. Finally, specialists in the field of pathology provided feature intelligence that was used to recognize the zone of interests for brain tumor. This study pertained a novel architecture, named Xception, which permitted both elevated presentation, diminished expanse and estimated charge of deep neural networks employing depth wise separable convolution to establish high performance computer aided diagnosis system for brain tumor detection from MRI. Preparatory appraisal for the Xception model employing transfer learning exhibited exceptional performance with immense efficiency and prediction probability. Fascinatingly, prediction probabilities were distinct when various layers were reviewed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.