A Novel Approach for Hybrid Image Segmentation GCPSO: FCM Techniques for MRI Brain Tumour Identification and...

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Computational Biology

Background:

• Early detection of brain tumors is crucial for effective diagnosis and treatment planning.
• Magnetic Resonance Imaging (MRI) is a key tool for analyzing brain tissue and identifying abnormalities.
• Existing image processing methods often struggle with preserving original image quality during enhancement.

Purpose of the Study:

• To develop an improved image preprocessing technique for brain MRI scans.
• To enhance the accuracy of brain tumor detection and classification.
• To introduce a novel hybrid segmentation method for superior tumor region identification.

Main Methods:

• Implemented an adaptive bilateral filter utilizing wavelet transform for low-frequency signal sub-bands, controlling spatial and intensity parameters.
• Integrated texture region and block boundary detection to further refine the adaptive bilateral filter.
• Employed a hybrid segmentation approach combining Guaranteed Convergence Particle Swarm Optimization (GCPSO) and Fuzzy C-Mean (FCM) techniques.

Main Results:

• The adaptive bilateral filter demonstrated superior image quality restoration compared to other resolution methods.
• The proposed GCPSO-FCM segmentation method achieved a high accuracy rate of 95.32%.
• Comparative analysis showed the hybrid segmentation method outperformed various existing segmentation techniques.

Conclusions:

• The developed adaptive bilateral filtering and GCPSO-FCM segmentation offer a significant advancement in brain tumor analysis.
• This approach enhances diagnostic accuracy and aids in early-stage detection of brain tumors.
• The study highlights the potential of advanced image processing and AI in neuro-oncology.