MRI Brain Tumour Segmentation Using Hybrid Clustering and Classification by Back Propagation Algorithm

Area of Science:

• Medical Imaging
• Computer Vision
• Artificial Intelligence

Background:

• Medical image segmentation is crucial for identifying abnormalities but faces challenges like noise and non-uniform textures.
• Existing segmentation techniques often require improvements in efficiency and speed for clinical applications.

Purpose of the Study:

• To develop an efficient and accurate medical image segmentation method.
• To integrate K-means clustering with spatial Fuzzy C-means for enhanced segmentation performance.
• To enable accurate classification of brain tumor abnormalities in MRI scans.

Main Methods:

• A hybrid image segmentation approach combining K-means and spatial Fuzzy C-means clustering.
• Feature extraction using Discrete Wavelet Transform (DWT) for identifying hidden image information.
• Classification of segmented abnormalities using the Back Propagation Algorithm (BPA).

Main Results:

• The proposed method demonstrates high accuracy and minimal execution time for MRI brain image segmentation.
• The integrated approach leverages the speed of K-means and the accuracy of spatial Fuzzy C-means.
• Successful implementation for segmenting and classifying abnormal regions in MRI brain images, distinguishing between benign and malignant tumors.

Conclusions:

• The hybrid K-means and spatial Fuzzy C-means clustering method offers an efficient and accurate solution for medical image segmentation.
• The integration of DWT and BPA facilitates reliable classification of brain tumor types.
• This technique shows significant potential for improving diagnostic accuracy in neuroimaging.