Open AccessAdopting Texture Features to Detect and Recognize Brain Tumors in Magnetic Resonance Images
Author(s) -
Aya S Derea,
Heba Kh. Abbas,
Anwar H. Al-Saleh,
Haidar J. Mohamad
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/757/1/012029
Subject(s) - histogram , artificial intelligence , magnetic resonance imaging , segmentation , computer science , pattern recognition (psychology) , computer vision , texture (cosmology) , process (computing) , region of interest , image segmentation , image (mathematics) , radiology , medicine , operating system
The detection and recognition of tumor have a very important role in many applications of medical imaging. The use of computer in this process required high accuracy as it relates to human life especially that the error rate should be as low as possible. In this paper, Magnetic Resonance Imaging (MRI) images are tested using image processing (segmentation-based threshold) and supervised classification (minimum distance) to detect the region of interest. The location of the tumor is located using histogram algorithm with run length features. The geometric measurements calculated to identify tumors dimensions, location, volume and area. The results were highly efficient and highly accurate to determine the location and dimensions of the tumor.