의료 영상을 위한 군집화 기반 SNR 자동 분석기법

In signal processing, the signal-to-noise ratio (SNR) is a conventional method for measuring the robustness performance of a system. In medical imaging, accurate SNR measurement is important to determine which system is adequate for diagnosis of particular disease. In this paper, we propose an exact and efficient method for calculating the SNR value of medical imaging samples. This technique is based on the k-means clustering algorithm and tested with real magnetic resonance (MR) images of the human brain. According to our experimental results, the proposed approach is effective for measuring SNR and localizing the region of interest (ROI) of a given medical image.