MRI brain scan classification using novel 3-D statistical features

Hasan, A; Meziane, F; Aspin, R; Jalab, HA

Abstract

The paper presents an automated algorithm for detecting and classifying magnetic resonance brain slices into normal and abnormal based on a novel three-dimensional modified grey level co-occurrence matrix approach that is used for extracting texture features from MRI brain scans. This approach is used to analyze and measure asymmetry between the two brain hemispheres, based on the prior-knowledge that the two hemispheres of a healthy brain have approximately a bilateral symmetry. The experimental results demonstrate the efficacy of our proposed algorithm in detecting brain abnormalities with high accuracy and low computational time. The dataset used in the experiment comprises 165 patients with 88 having different brain abnormalities whilst the remaining do not exhibit any detectable pathology. The algorithm was tested using a ten-fold cross-validation technique with 10 repetitions to avoid the result depending on the sample order. The maximum accuracy achieved for the brain tumors detection was 93.3% using a Multi-Layer Perceptron Neural Network..

Citation

Hasan, A., Meziane, F., Aspin, R., & Jalab, H. (2017, March). MRI brain scan classification using novel 3-D statistical features. Presented at The Second International Conference on Internet of Things, Data and Cloud Computing (ICC 2017), University of Cambridge, United Kingdom

• Presentation Conference Type: Other
• Conference Name: The Second International Conference on Internet of Things, Data and Cloud Computing (ICC 2017)
• Conference Location: University of Cambridge, United Kingdom
• Start Date: Mar 22, 2017
• End Date: Mar 23, 2017
• Publication Date: Mar 20, 2017
• Deposit Date: Sep 14, 2017
• Publicly Available Date: Sep 14, 2017
• Publisher URL: http://dx.doi.org/10.1145/3018896.3036381
• Related Public URLs: http://icc-conference.org/
• Additional Information: Additional Information : Proceedings ISBN: 978-1-4503-4774-7; Event Type : Conference