Automatic Nasal Tumor Detection by grey prediction and Fuzzy C-Means clustering

The dynamic magnetic resonance images (DMRI) is one of the major tools for distinguishing nasal tumors in recent years. The purpose of this research is to detect and enhance the tumor region in DMRI automatically by using grey prediction and Fuzzy C-means. The main detecting process is divided into two stages. At the first stage, the pixels that have specific trends and are affected by contrast agents with specific level will be filtered according to the developing coefficient and control coefficient of grey prediction. At the second stage, the tumor area would be detected by using Fuzzy C-means clustering technique to distinguish the differences between normal tissue and tumor. Owing to the work of the first stage, the second stage reduces the calculation dramatically and enhances the result of tumor detection. Six sets of DMRI images are tested by the proposed system. The average of sensitivity, accuracy, and specificity are 0.9856, 0.7857, and 0.7049, respectively. The decreasing percentages of processing pixels are 1.59%~5.59% after the first stage and 0.77%~3.52% after second stage. The detection system has already examined on different MR image sequences. The experimental results are robust and correct.