Rician noise reduction by combining mathematical morphological operators through genetic programming

摘要

We propose a genetic programming (GP)-based approach for noise reduction from magnetic resonance imaging (MRI). An optimal composite morphological supervised filter (F_(ocmsf)) is developed through a certain number of generations by combining gray-scale mathematical morphological (MM) operators under a fitness criterion. The proposed method does not need any prior information about the noise variance. The improved performance of the developed filter is investigated using simulated and real MRI datasets. Comparative analysis demonstrates the superiority of the proposed GP-based scheme over the existing approaches.