Front Inner Page - Volume 4 No.6 December 2017

  • » Back to Index

  • Title

    :

    Enhanced Segmentation Of Brain Tumour Detection Using Cnn Techniques

    Authors

    :

    Sankara Raman1

    Keywords

    :

    Magnetic Resonance Imaging (MRI), KG (knowledge-guided) method, Brian Tumour, k NN classifier, Graph cuts.

    Issue Date

    :

    December 2017

    Abstract

    :

    As the Magnetic Resonance Imaging (MRI) technique is the most popular non-invasive technique, the imaging of biological structures by MRI imaging is a common investigating procedure in these days. Due to this reason, the automatic processing of such images is getting the most attention. Nowadays, the issue of automatic segmentation and analysis of brain tumours are becoming a major area of research. It is the first step in surgical and therapy planning. And the very first step of the automatic analysis of brain tumour is its detection and subsequent segmentation. The difficulty of the tumour segmentation is in its shape variability in each case. The automatic segmentation of brain tumours is still a challenging problem, even though several different and interesting fully- or semi-automatic algorithms have been proposed in recent years. There are many existing algorithms which are classified as semi and fully-automatic methods that are region and contour-based methods. Existing system encodes the knowledge of the pixel intensity and spatial relationships in the images to create a fully automated segmentation system known as the KG (knowledge-guided) method. In this paper, the system proposes a novel semi-automatic segmentation method based on population and individual statistical information to segment brain tumours in magnetic resonance (MR) images. The probability of each pixel belonging to the foreground (tumour) and the back ground is estimated by the k NN classifier under the learned optimal distance metrics. A new cost function for segmentation is constructed through these probabilities and is optimized using graph cuts.

    Page(s)

    :

    1-11

    ISSN

    :

    2347- 4734

    Source

    :

    Vol. 4, No.6, December 2017

    Download

    :


  • » Back index