動態磁挀造影是目前鼻咽部位腫瘤的主要輔助診斷工具，在本研究中綜合應用灰色預測、灰色關聯分析，以自動的方式鑑別出腫瘤可能的位置，以供醫務人員參考。由於實際動態磁挀造影的影像變化特性並未完全如理論上所描述，因此本研究將腫瘤的鑑別過程分成兩個階段：第一階段以灰色預測中的發展系數與灰作用量來篩選出具有某種變化特性且受顯影劑影響達到某種程度的影像點；第二階段以灰色關聯分析根據不同組織的變化特性差異，區分出腫瘤組織的位置。由於第一階段已篩選出具特別變化特性的影像點，故可以有效地降低第二階段的計算量與提高腫瘤鑑別的準確度。 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 grey relation analysis. The main detecting process is divided into two stages. At the first stage, the pixels that have specific trend and affect 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 position of tumor will be detected by using grey relation analysis to distinguish the differences between normal tissues and tumors. Owing to the work of the first stage, the second stage will reduce the calculation dramatically and enhance the result of tumor detections.
