SEGMENTATION OF BRAIN TUMOR TISSUES IN MR IMAGES USING MULTIRESOLUTION TRANSFORMS AND RANDOM FOREST CLASSIFIER WITH ADABOOST TECHNIQUE

Citations Over Time

Abstract

Segmentation of brain tissues and classification in Magnetic Resonance Imaging (MRI) is crucial process for clinical applications. Manual process is a tedious and time consuming task for large amount of data. Automatic method eliminates the need of manual interaction and has received more attention. In this work, a new machine learning algorithm is proposed by combining Random forest algorithm with Modified Adaboost algorithm to segment the tumor from the MRI Brain tissues. Artifacts in imaging introduce distortions which may confuse tissues segmentation. These undesired needs to be eliminated for correct segmentation. Due to the complex structure, Brain tumor tissue texture is formulated using fractal based techniques. Then the fractal and intensity features are given as the input to the random forest classifier and modified Adaboost random forest classifier. The MRI BRATS2013 dataset is used for analysing the performance of the proposed method. Simulation results proved that the hybrid method of modified Adaboost random forest classifier achieves higher accuracy compared to the conventional random forest classifier for tumor segmentation.

Related Papers

• → A Precise Breast Cancer Detection Approach Using Ensemble of Random Forest with AdaBoost(2019)20 cited
• → An Improved Coronary Heart Disease Predictive System Using Random Forest(2021)2 cited
• → Guided Random Forest in the RRF Package(2013)61 cited
• → Comparing random forest and AdaBoost with resampling for modeling imbalanced late payment tuition fee data(2022)
• → Prediction and Characteristic Exploration of Military Specialized High School Trainee Selection Using Machine Learning(2023)