- 學位論文
探測乳房腫瘤硬度最佳下壓深度之研究
Study of the Optimal Indentation Depth in Breast Tumor Hardness Exploration
摘要
乳癌是女性最常發生的惡性腫瘤之一，近年乳癌更名列女性十大癌症之中，然而乳房腫瘤良惡性的篩檢在乳癌防治上佔了很重要的角色。臨床上區分乳房腫瘤為良性或惡性，主要的判斷是根據腫瘤的位置、大小、形狀和硬度等資訊一般而言腫瘤之硬度比與腫瘤之類型關聯性高，因此可能可以把腫瘤與乳房內軟組織的相對硬度，作為判斷良性惡性之主要依據。利用下壓與橫推方向之兩軸力量感測器進行矽膠乳房模型探測實驗並評估其效能，找出具有描述腫瘤特性之力量特徵值。本文利用觸覺靈敏度方法，分析探討出應用於不同腫瘤特性之最佳探測深度，進而採用探測力學模型推算出腫瘤與周圍組織的硬度比。本文利用了21種樣本做驗證結果顯示在最佳探測策略條件下，對於不同硬度之腫瘤有很好的區分能力，且對於大、小、深、淺之腫瘤同樣有不錯的預測能力。
並列摘要
The breast cancer is one which of malignant tumors that the women occur most frequently. The breast cancer ranked in women's ten major cancers in recent years. And examine of breast tumor has taken very important role in the breast cancer prevented and cured. The differentiation between the benign and malignant tumors clinically depends on the location、size、shape and hardness. Therefore, the relative hardness between the breast tumor and the surrounding soft tissues might be used to tell whether the tumor is malignant or benign. In this study, we designed and made the model of artificial 3D silicon of soft tissue that is more approximate then true breast. Use one axis force sense for exploration experiment and assess its efficiency, and find out the characteristics of breast tumor has been described. Based on the sensitivity of tactile perception information, and discuss the optimal exploration depth for different inclusion properties to use neural-fuzzy network for forecast stiffness ratio of tumor with soft tissue. In this study, we used one axis force feature for input of neural-fuzzy network and 21 data sets for validation. The optimal exploration strategy Results depict that prediction accuracy can be achieved very well for inclusion properties, such as big, small, deep and shallow tumor.