Fusion based Glioma brain tumor detection and segmentation using ANFIS classification

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Biomedical Engineering

Background:

• Glioma brain tumor detection is challenging due to indistinct tumor boundaries in medical images.
• Accurate segmentation is crucial for diagnosis and treatment planning.

Purpose of the Study:

• To develop and evaluate an automated method for detecting and segmenting Glioma brain tumors.
• To enhance the accuracy of brain tumor detection using advanced image processing and machine learning techniques.

Main Methods:

• Non-Sub sampled Contourlet Transform (NSCT) was employed for brain image enhancement.
• Texture features were extracted from enhanced images and classified using Adaptive Neuro Fuzzy Inference System (ANFIS).
• Morphological functions were utilized for tumor region segmentation.

Main Results:

• The proposed method demonstrated effectiveness in enhancing brain images for tumor detection.
• The ANFIS classifier achieved successful classification of normal versus Glioma brain images.
• Tumor regions were accurately segmented using the developed methodology.

Conclusions:

• The integrated approach of NSCT, ANFIS, and morphological functions offers a robust solution for Glioma brain tumor detection.
• This methodology shows promise for improving the accuracy and efficiency of brain tumor diagnosis.