Analysis of a novel MRI Based Brain Tumour Classification Using Probabilistic Neural Network (PNN)

This is the authors' abstract. We don't add key points for this paper.

Now-a-days the most horrendous curse to mankind is cancer. But if we can detect the tumour at an early stage, at least we can make an attempt to cure it. MRI is perhaps the most popular non-invasive imaging diagnostic technique which does not use any radio-active energy harmful for body tissue. Pre-processing of MRI images helps the detection method to eliminate computational complexity. The redundant pixels of an image can be removed by DCT. Feature values can reveal certain properties of an image. GLCM (Gray Level Co-occurrence Matrix) is an efficient way to extract the feature values. These feature values can be used as the input of a PNN structure. PNN is widely used in classification and pattern recognition problems. The prototype designed has desired accuracy, specificity and sensitivity.