An improved brain MR image binarization method as a preprocessing for abnormality detection and features extraction

• Published in: Frontiers of Computer Science Vol. 11; no. 4; pp. 717 - 727
• Main Authors: ROY, Sudipta, BHATTACHARYYA, Debnath, BANDYOPADHYAY, Samir Kumar, KIM, Tai-Hoon
• Format: Journal Article
• Language: English
• Published: Beijing Higher Education Press 01-08-2017; Springer Nature B.V
• Subjects: accuracy estimation; Algorithms; Brain; Cancer; Computer Science; Entropy; Error reduction; image binarization; image preprocessing; Iterative methods; Magnetic resonance imaging; Methods; MRI of brain; performance analysis; Preprocessing; Research Article; segmentation; thresholding; 二值化方法; 大脑; 异常检测; 特征提取; 磁共振图像; 磁共振成像; 预处理方法; 黑色背景; image binarization; thresholding; entropy; segmentation; accuracy estimation; image preprocessing; MRI of brain; performance analysis
• ISSN: 2095-2228; 2095-2236
• DOI: 10.1007/s11704-016-5129-y

This paper propose a computerized method of magnetic resonance imaging (MRI) of brain binarization for the uses of preprocessing of features extraction and brain abnormality identification. One of the main problems of MRI binarization is that many pixels of brain part cannot be correctly binarized due to extensive black background or large variation in contrast between background and foreground of MRI. We have proposed a binarization that uses mean, variance, standard deviation and entropy to determine a threshold value followed by a non-gamut enhancement which can overcome the binarization problem of brain component. The proposed binarization technique is extensively tested with a variety of MRI and generates good binarization with improved accuracy and reduced error. A comparison is carried out among the obtained outcome with this innovative method with respect to other well-known methods.