Gradient-based kernel selection technique for tumour detection and extraction of medical images using graph cut

Abstract

Magnetic resonance imaging is a powerful, ubiquitous imaging technique that provides detailed high-contrast images differentiating soft tissues. The low radio-frequency bias field creates intensity inhomogeneity generating low contrast that often creates difficulty for quantitative and qualitative analyses. Segmentation aids in analysis of changes occurring in brain, where bias effect severely affects performance. The graph-cut (GC) segmentation provides supervised computer-assisted diagnosis and treatment. GC's interactive nature requires manual selection of kernels for initialisation. The shrinkage behaviour of GC creates inaccurate and fallacious extraction. On the basis of these problems, this study proposes gradient-based kernel selection GC method that simultaneously removes shrinkage problem and locates tumour in image, eliminating human interaction with accurate segmentation for even bias field images. The proposed method addresses these problems by emphasising on directive inclination of intensity scales of symmetrical halves of images. The proposed method is evaluated for high-grade glioma and low-grade glioma images with and without bias field. The average performance metrics evaluated for these images depict remarkable improvement in comparison with existing techniques. The proposed technique is validated by applying on real-time dataset of tumour images obtained from State Government Hospital, Shimla, India.