查詢結果分析
相關文獻
- Two-Stage Liver Tissue Classification Through Fractal Geometry
- 影像分析及計算機圖學應用於心臟超音波
- An Ultrasonic Scoring System for Assessing the Severity of Chronic Liver Diseases
- 應用迴歸法於都市邊緣山坡地土地利用變遷之偵測--以臺北市南港區山坡地為例
- Liver Sonography and Histopathology: Correlations in AIDS Patients
- 應用SPOT衛星影像與地理資訊於林地土地利用型綠度分析
- Fetal Heart Tracking in Ultrasound Image Sequences Using Coarse-to-Fine Wavelet
- Scene Analysis System Using a Combined Fuzzy Logic-Based Technique
- 織物組織影像分析前處理之研究
- 使用數位影像處理自動分析梭織物之組織
頁籤選單縮合
題 名 | Two-Stage Liver Tissue Classification Through Fractal Geometry=以影像分析超音波圖片為肝臟組織分類 |
---|---|
作 者 | 吳宗明; 周文修; 陳永昌; | 書刊名 | 中國工程學刊 |
卷 期 | 14:5 1991.09[民80.09] |
頁 次 | 頁519-529 |
分類號 | 415.12 |
關鍵詞 | 分析; 分類; 肝臟; 組織; 超音波; 圖片; 影像; |
語 文 | 英文(English) |
中文摘要 | 利用電腦分析來量化肝臟的超音波影像可幫助醫師做更正確的診斷,以避免因先 入為主的主觀意識而誤判。本篇文章利用碎形幾何的兩個特性來量化及辨識肝臟的超音波影 像,不僅可以辨別出正常與否,亦可分辨出不同種類的疾病。首先,利用碎形幾何中的自我 相似性質求出影像的質密特徵曲線,並以此曲線判斷其正常與否。被判斷成不正常的影像可 利用碎形幾何中的自我仿射性質進一步抽取其徵布朗特徵曲線作為不同疾病的診斷依據。經 由實驗證明,使用我們所提出的方法可快速地做相當正確的診斷。 |
英文摘要 | A fractal analysis procedure for the classification of ultrasonic images of liver tissue is proposed. Based on the two properties of fractals (self-similarity and self-affinity), it is possible to recognize not only normal and abnormal liver tissues but also different kinds of abnormalities. Two-stage procedures are performed in the classification. In the first stage, the mass density feature vectors are estimated by the property of self-similarity, classification of normal and abnormal ultrasonic liver tissures can be obtained from the differences between their mass density feature vectors. In the second stage, based on the property of self-affinity, the fractal Browmian motion model is adopted to represent the imaging surface. By evaluating the fractal Brownian feature vectors in about 27 abnormal ultrasonic liver images, it is found that it is possible to classify different kinds of diseases using the model. Moreover, the measurement of lacunarities can be added to improve the method to classify tissues more accurately. |
本系統中英文摘要資訊取自各篇刊載內容。