PROJECT TITLE :

Brain Tumor Detection And Segmentation Using Conditional Random Field - 2017

ABSTRACT:

Medical Image Processing could be a highly difficult field. Medical image techniques are used to mage the inner portions of the human body for medical diagnosis. MR Pictures are widely used in the diagnosis of brain tumor. In this paper, we gift an automatic method to detect and segment the brain tumor regions. The proposed methodology consists of three main steps, initial segmentation, modeling of energy perform and optimize the energy operate. To create our segmentation a lot of reliable we have a tendency to use info gift in the T1 and FLAIR MRI pictures. We use conditional random field(CRF) based frame work to combined the information gift in T1 and FLAIR in probabilistic domain. Main blessings of CRF primarily based frame work is we have a tendency to can mode complex shapes simply and we tend to incorporate the observation of energy function.