INTERNATIONAL JOURNA L OF ENGINEERING SCI ENCES & RESEARCH TECHNOLOGY Tumor Identification Using Binary Thresholding in MRI Brain Images
R. Manjula, V. Vidhya Sagar · 2013
Imaging plays a very important role in diagnosis an d treatment planning of brain tumor. Accurate segmentation is critical, especially when tumor mor phological changes remain subt le, irregular and difficult to assess by clinical examination. Traditionally, tumo r segmentation from magnetic resonance imaging data is important but time consuming task which is manually performed by medical experts. Here, automating thi s process allenging task because of high diversity in the app earance of tumor tissues among different patients a nd in many cases it has similarity with normal tissues. M agnetic resonance imaging is an advanced medical imaging technique which provides rich informatio n about human soft tissue anatomy. The automatic tu mor segmentation in MRI tumor poses many challenges with regard to characteristics of an image. Homogeneity criterion meth od is undertaken to analyze and evaluate whether the tumor is malignant or non -malignant.