Efficiency of Decision tree algorithm for Brain Tumor MRI Images comparing with SVM Algorithm

Abstract

To prove that the efficiency of the Decision Tree algorithm is high compared with SVM algorithm for novel classification of Brain Tumor MRI Images. Materials And Methods: A total of 274 Brain Tumor MRI Images are collected and samples are divided into training dataset <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\boldsymbol{(\mathrm{n}=191[70\%])}$</tex> and test dataset <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\boldsymbol{(\mathrm{n}=8 3\ [30\%])}$</tex> . Novel classification of MRI Images is performed by Decision Tree Algorithm and SVM Algorithm. Results and Discussion: Brain Tumor MRI images are classified to extract the quantitative information by using Decision Tree Algorithm and attained accuracy of 97 % and SVM Algorithm got 89%. Decision Tree Algorithm and SVM Algorithm are statistically significant with the independent sample T-Test value (plt;0.05). The results proved that the Decision Tree Algorithm has better efficiency over the SVM Algorithm in classification of Brain Tumor MRI images.