7 A novel neutrosophic approach-based filtering and Gaussian mixture modeling clustering for CT/MR images

Medical imaging modalities like computed tomography (CT), magnetic resonance (MR) imaging, ultrasound and positron emission tomography have revolutionized modern medicine. The computer-aided algorithms are used for the analysis of medical images for disease diagnosis and treatment planning. Noise is unavoidable in medical images, CT images are corrupted by Gaussian noise and MR images are corrupted by Rician noise. This chapter focuses on a novel neutrosophic approach median filter for the CT/MR images, and denoised image was subjected to Gaussian mixture model segmentation. The neutrosophic domain filtering approach was found to be superior when compared with other filters and was validated in terms of performance metrics for phantom images. The real-time abdomen CT and brain MR images were also used for analysis, and the Gaussian mixture model segmentation results were found to be proficient when coupled with the neutrosophic domain filtering approach.