A unique unsupervised enhanced intuitionistic fuzzy C-means for MR brain tissue segmentation

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Neuroscience

Background:

• Accurate brain image segmentation is crucial for diagnosing neurological diseases.
• Challenges in brain segmentation include noise, bias fields, and partial volume effects.
• Existing methods require enhancement for precise tissue and tumor identification.

Purpose of the Study:

• To introduce a novel machine learning method, Gaussian-Kernelized Enhanced Intuitionistic Fuzzy-C-Means (GKEIFCM), for improved brain image segmentation.
• To enhance the Improved Intuitionistic Fuzzy-C-Means Algorithm (IIFCM) using Gaussian kernelized distances for more efficient segmentation.
• To evaluate the efficacy of GKEIFCM in classifying brain tissues and identifying tumors.

Main Methods:

• The proposed GKEIFCM method utilizes Gaussian kernelized distances between pixels.
• This approach enhances the Improved Intuitionistic Fuzzy-C-Means Algorithm (IIFCM).
• The method focuses on simplifying segmentation while reducing computational time and increasing efficiency.

Main Results:

• GKEIFCM demonstrated expertise in tissue and tumor classification and identification.
• The method achieved high performance in terms of Dice, Jaccard-similarity-index, and Accuracy.
• Significant improvements in execution time were observed compared to existing methods.

Conclusions:

• GKEIFCM offers a robust and efficient solution for brain image segmentation.
• The novel method enhances diagnostic capabilities for brain-related diseases.
• GKEIFCM shows significant potential for clinical applications in neuroimaging.