A unified patch based method for brain tumor detection using features fusion. (January 2020)

• Record Type: Journal Article
• Authors: Sharif, Muhammad; Amin, Javaria; Nisar, Muhammad Wasif; Anjum, Muhammad Almas; Muhammad, Nazeer; Ali Shad, Shafqat
• Is Part Of: Cognitive systems research. Volume 59(2020)
• Page Start: 273
• Page End: 286
• Publication Date: 2020-01
• Subjects: MRI -- FLAIR -- LBP -- HOG -- GEO; Cognition -- Periodicals; Cognitive engineering (System design) -- Periodicals; Artificial intelligence -- Periodicals; 153.05
• DOI: 10.1016/j.cogsys.2019.10.001
• Languages: English
• ISSNs: 1389-0417

Abstract

Abstract: The manuscript authenticates the effectiveness of fusing texture and geometrical (GEO) features in magnetic resonance imaging (MRI) for tumor classification. The presented technique is evaluated on two MRI including T2 and FLAIR. The tumor region is enhanced using fast non-local mean (FNLM) method with 4 × 4 patch size. Otsu algorithm is used for tumor segmentation. Moreover, multiple features are extracted for example local binary pattern (LBP), histogram of oriented gradients (HOG) and GEO (area, circularity, filled area, and perimeter) across each segmented image. These acquired features are merged into a single dimensional vector for prediction. In the end, the fused vector is used with multiple classifiers which proved that features fusion provides good results as compared with individual features.