Threshold prediction for segmenting tumour from brain MRI scans

• Published in: International journal of imaging systems and technology Vol. 24; no. 2; pp. 129 - 137
• Main Authors: Beno, M. Marsaline, I. R, Valarmathi, S. M, Swamy, Rajakumar, B. R.
• Format: Journal Article
• Language: English
• Published: Hoboken, NJ Blackwell Publishing Ltd 01.06.2014; Wiley; Wiley Subscription Services, Inc
• Subjects: Algorithmics. Computability. Computer arithmetics; Applied sciences; artificial bee colony; Artificial intelligence; bilateral filter; Biological and medical sciences; Computer science; control theory; systems; Connectionism. Neural networks; Exact sciences and technology; genetic algorithm; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; MRI image; Nervous system; optimal threshold prediction; Pattern recognition. Digital image processing. Computational geometry; Radiodiagnosis. Nmr imagery. Nmr spectrometry; support vector machine; Theoretical computing; tumor detection; Performance evaluation; Artificial life; Grey level image; Methodology; Image processing; Fuzzy neural nets; MRI image; Backpropagation algorithm; Digital filter; Cancerology; Feedforward neural nets; tumor detection; Vector support machine; Tumor; Swarm intelligence; Threshold function; Generic programming; Backpropagation; Neural network; Quadratic programming; Nuclear magnetic resonance imaging; Particle swarm optimization; Radial basis function; Image segmentation; artificial bee colony; support vector machine; optimal threshold prediction; Genetic algorithm; Medical imagery; bilateral filter
• ISSN: 0899-9457; 1098-1098
• DOI: 10.1002/ima.22087

ABSTRACT In recent decades, region growing methods in image segmentation plays a vital role in medical image processing. Nonetheless, the method needs more advancement to cope up with the images of current acquisition devices. This paper attempts to solve the problem of maintaining diversity among wide image specifications by optimizing the threshold. In order to accomplish this, we introduce a hybrid framework of Artificial Bee Colony and Genetic Algorithm in a region growing variant, in which gradient and intensity levels are used for segmentation. Eventually, the proposed work is subjected to classify the tumor and non‐tumor images, followed by the segmentation of tumor region in MRI images. Classification methodologies such as feed forward back propagation neural network, radial basis neural network, support vector machine with quadratic programming and adaptive neuro‐fuzzy inference system are considered for experimental investigation in which support vector machine with quadratic programming is found to be dominant than other methodologies. Proposed region growing method outperforms well on the classified image, when compared with the region growing variant and standard region growing method. The results are demonstrated with the aid of wide set of performance measures. © 2014 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 24, 129–137, 2014