Hybrid multiresolution Slantlet transform and fuzzy c-means clustering approach for normal-pathological brain MR...

Area of Science:

• Medical Imaging Analysis
• Signal Processing
• Artificial Intelligence

Background:

• Automated segregation of brain Magnetic Resonance Imaging (MRI) is crucial for diagnosing neurological conditions.
• Traditional methods may lack the precision required for complex image features.
• Existing transforms and clustering techniques have limitations in time-frequency resolution and classification accuracy.

Purpose of the Study:

• To develop and evaluate a novel hybrid automated technique for brain MRI segregation.
• To leverage the enhanced time-frequency resolution of the Slantlet Transform (ST) for improved feature extraction.
• To utilize Fuzzy C-Means (FCM) clustering for accurate classification of segmented brain MR images.

Main Methods:

• Implementation of the Slantlet Transform (ST), an improved orthogonal discrete wavelet transform (DWT), for superior time-frequency resolution.
• Application of Fuzzy C-Means (FCM) clustering on processed feature vectors for efficient classification.
• Development of a hybrid ST-FCM scheme for automated segregation of brain MR images.

Main Results:

• The proposed hybrid ST-FCM technique demonstrated excellent accuracy in characterizing human brain MR images.
• The method effectively segregates brain MR images, distinguishing between normal and pathological cases.
• Benchmark brain MR images were utilized to validate the high performance of the developed automated tool.

Conclusions:

• The hybrid ST-FCM approach offers a robust and accurate method for automated brain MRI segregation.
• The combination of ST's advanced signal processing and FCM's classification capabilities provides a powerful tool for medical image analysis.
• This automated system has the potential to significantly aid in the diagnosis of brain pathologies through precise MRI analysis.