Author:
Ali Nosiba M.,ElZubair Omnia M.,Hamza Alnazier O.,Elnour Hanan A. M.,Khider Mohamed O.
Abstract
Tumor is an uncontrolled growth of harmful cells within the skull that raises intracranial pressure. In the field of medical research, medical picture classification is critical. Imaging plays a crucial role in the diagnosis of brain tumors. Magnetic resonance imaging is a noninvasive, 3-dimensional imaging technique that produces high-quality images. The interpretation of an image might not be completely precise and require the assistance of a second opinion, variability in diagnosis made by different doctors and even by the same doctor under different circumstances due to job load, observation accuracy for the physician, picture clarity, noise, or the physician's vision or mood. Based on the previously mentioned reasons, we have developed a computer-aided diagnosis system to aid in the identification or detection of benign tumor in brain magnetic resonance imaging scans. In the first stage of this study, image enhancement and correct segmentation processes have been conducted into the images in order to facilitate the system to give an accurate classification of brain tumor type. In the second stage, we investigated several statistical features using a technique called gray-level co-occurrence matrix. The implementation of this technique was done with software called MATLAB (Matrix Laboratory) to determine the best features for diagnosing benign tumors of the brain. Gray-level co-occurrence matrix is second-order statistical analysis that describes spatial relationships and the information about the pixel position that has a similar gray-level value; we have found that some features have a big cutoff range between normal and abnormal tissues. Classification was done using back-propagation artificial neural network. The detection findings and quantitative data analysis show that our suggested system is effective, with a detection accuracy of 99.8%.
Publisher
Ovid Technologies (Wolters Kluwer Health)
Subject
Biomedical Engineering,Medicine (miscellaneous)
Reference7 articles.
1. Brain tumor classification using convolutional neural networks;Biomed Pharmacol J,2018
2. Computer aided classification of mammographic masses and normal tissue: linear discriminate in texture feature space;Phys Med Biol,1995
3. Computer-aided detection of benign tumors of the female breast;J Clin Eng,2013
4. Brain tumor extraction from MRI images using MATLAB;Int J Electron Commun Soft Comput Sci Eng,2012
5. Artificial neural network for detection of biological early brain cancer;Int J Comput Appl,2010