T1-T2 weighted MR image composition and cataloguing of brain tumor using regularized logistic regression

Abstract

In medical diagnosis, the functional and structural information of the brain as well as the impending abnormal tissues is very crucial and important with an MR image. A collective CAD system that detects and classifies the brain tumor by exploiting the structural information is presented. Magnetic Resonance Imaging (MRI) T1-weighted and T2-weighted images provides suitable variation of contrast between the different soft tissues of the brain which is suitable for detecting the brain tumor. Both the Magnetic Resonance (MR) image sequences are composited using the alpha blending technique. The tumor area in the MR images will be segmented using the Enhanced Watershed Segmentation (EWATS) algorithm. The feature extraction is a means of signifying the raw image data in its abridged form to ease the classification in a better way. An expert classification assistant is tried out to help the physicians to classify the detected MRI brain tumor in an efficient manner. The proposed method uses the Regularized Logistic Regression (RLR) for the efficient cataloguing of brain tumor in which it achieves an effective accuracy rate of 96%, specificity rate of 86% and sensitivity rate of 97%.