跳到主要內容

臺灣博碩士論文加值系統

(34.204.180.223) 您好!臺灣時間:2021/07/31 17:05
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:蘇心悅
研究生(外文):Su, Hsinyueeh
論文名稱:應用傅立葉轉換對超音波脂肪肝影像進行雜訊處理暨定量分析
論文名稱(外文):Quantification Of Fatty Liver Sonography After Denoising By Fourier Transform Approach
指導教授:陳泰賓陳泰賓引用關係
指導教授(外文):Chen, Taibeen
口試委員:杜維昌陳泰賓黃詠暉
口試委員(外文):Du, WeichangChen, TaibeenHuang, Yunghui
口試日期:2012-06-01
學位類別:碩士
校院名稱:義守大學
系所名稱:資訊工程學系碩士在職專班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:48
中文關鍵詞:超音波影像脂肪肝傅立葉轉換定量分析
外文關鍵詞:Ultrasound ImageFatty LiverFourier TransformQuantitative Analysis
相關次數:
  • 被引用被引用:1
  • 點閱點閱:1218
  • 評分評分:
  • 下載下載:70
  • 收藏至我的研究室書目清單書目收藏:0
超音波造影是目前脂肪肝主要的診斷方法之一;具有非侵入性、無輻射線、低成本、操作靈活等優點,使之成為診斷脂肪肝的首選工具。但其缺點為易受回音波散射干擾,不僅影像解析度變差,同時影像上會出現雜訊斑點 (speckle noise) ,增加影像診斷判讀之困難性。本研究之目的為運用傅立葉轉換處理影像之雜訊,提高影像定量分析之準確性。本研究收集正常、輕、中與重度脂肪肝影像,利用影像處理與分類模型,建立脂肪肝超音波影像之定量分析。分析流程包括: (1)影像前處理,利用傅立葉轉換去除影像雜訊;(2)圈選ROI (region of interest) ,取得影像特徵;(3)進行定量分析,藉以比較及界定有利於判讀的影像參數。
此研究針對經傅立葉轉換處理之超音波脂肪肝影像,分析出關鍵的影像參數,有效提升超音波影像之診斷能力;建立脂肪肝功能定量模型,提高定量分析之準確度。
Ultrasound imaging is the most common method to diagnose fatty liver disease. Meanwhile, ultrasound is non-invasive, free of radiation dose, lower cost and handy operation. However, image resolution of ultrasound has been affected by scatter noise, speckle noise and none linear attenuation. The purpose of this study is to increase the accuracy of image and then improve quantitative analysis by reducing the noise on Fourier domain (space). This study was applied retrospectively to collect normal, mild, moderate and severe fatty liver images. The steps of flow-chart were involved denoising by Fourier transform approach, selection of region of interest for extracting features from images, and quantitative analysis to evaluate the performance of image feature. The presented method was improve sensitivity, specificity, accuracy, positive predicted value, negative predicted value, and Kapa statistics then those of original image. The most experimental samples need included in this study for the purpose of stability, feasibility, and sufficiency in future works.
謝誌I
中文摘要II
Abstract III
目錄IV
表目錄V
圖目錄VI
第一章 緒論1
1.1 前言1
1.2 超音波造影原理2
1.3 研究目的5
第二章 文獻探討6
2.1 脂肪肝的致病機轉6
2.2 脂肪肝的成因及徵狀7
2.3 脂肪肝的診斷8
2.4 文獻回顧9
第三章 研究方法與步驟11
3.1 研究流程11
3.2 研究資料收集12
3.2.1 造影條件12
3.2.2 脂肪肝影像13
3.2.3 影像斑點雜訊13
3.3 研究方法14
3.3.1 傅立葉轉換14
3.3.2 感興趣區域的選取17
3.3.3 雜訊閾值設定19
3.3.4 萃取影像特徵19
3.4 影像資料分析方法19
3.4.1 影像特徵分析與統計分類方法19
3.4.2 影像定量分析方法22
3.4.3 影像特徵效度評估方法22
第四章 結果27
4.1 去除影像雜訊27
4.2 影像定量分析30
4.3 影像特徵效度分析32
第五章 結論與討論34
5.1 結論34
5.2 討論35
5.3 未來研究方向36
參考文獻37
表目錄
表一、生物組織的聲速、聲阻抗及衰減係數4
表二、Test方法與Gold Standard之2x2列聯表,用以說明Sensitivity、Specificity、Positive Predicted Value (PPV) 、Negative Predicted Value (NPV) 、Accuracy、以及Kappa之計算方式23
表三、一般AUC數值的判別規則26
表四、影像特徵為平均值之AUC與P-value及其Relative Performance29
表五、影像特徵為標準差之AUC與P-value及其Relative Performance30
表六、影像特徵平均值定量分析結果31
表七、影像特徵標準差定量分析結果32
表八、分類模型之效度評估33
圖目錄
圖一、99及98年主要癌症死亡人數占率1
圖二、(a)為正常肝之外觀;(b)脂肪變性;(c)脂肪肝之外觀2
圖三、(a)縱波示意圖;(b)橫波示意圖3
圖四、研究流程圖11
圖五、右肝第五分葉(S5)影像13
圖六、右肝第六分葉(S6)影像13
圖七、(a)相互干擾。模擬兩個波源或散射子(白點),當振幅增加至兩波峰交會時,發射或反射波產生橢圓形斑點雜訊;(b)為不規則的干擾模式,是由更多位置發生散射效應而產生隨機斑點雜訊14
圖八、相位角示意圖15
圖九、空間域(spatial-domain)資料16
圖十、頻率域(frequency-domain)資料16
圖十一、(a)原始影像、(b)去除額外影像訊息之肝臟影像17
圖十二、經傅立葉轉換後利用設定不同閾值去除高頻雜訊之肝臟影像18
圖十三、顯示三組不同位置與不同半徑之3個ROI;作用於原始影像(左)與經傅立葉轉換之影像(右)18
圖十四、比較經傅立葉轉換前後,其影像特徵為平均值之ROC曲線27
圖十五、比較經傅立葉轉換前後,其影像特徵為標準差之ROC曲線28
[1]Aha, D., Tolerating Noisy, Irrelevant, and Novel Attributes in Instance-Based Learning Algorithms. International Journal of Man-Machine Studies, 1992;36(2):267-287.
[2]Angulo, P., Nonalcoholic Fatty Liver Disease. N Engl J Med, 2002; 346:1221-1231.
[3]Asbjørn Støylen., Basic Ultrasound, Echocardiography and Doppler for Clinicians. NTNU, 2010.
[4]Charatcharoenwitthaya, P., et al., Role of Radiologic Modalities in the Management of Non-Alcoholic Steatohepatitis. Clin Liver Dis, 2007;11(1):37-54.
[5]El-Zayadi, A.R., Heapatic Steatosis: A Benign Disease or A Silent Killer. J Gastroenterol, 2008;14(26):4120-4126.
[6]H-C, H., et al., Adaptive Ultrasonic Speckle Reduction Based on the Slope-Facet Model. Ultrasound Med Biol, 2003;29(8):1161-1175.
[7]J.L. Bentley., Multidimensional Binary Search Trees Used for Associative Searching. Communications of ACM, 1975;18:509-517.
[8]J.Mvogo. Rt al., A Combined Speckle Noise Reduction and Compression of SAR Images Using a Multiwavelet Based Method to Improve Codec Performance. Geoscience and Remote Sensing Symposium, IEEE 2001;1: 103-105.
[9]Lall, C.G., et al., Nonalcoholic Fatty Liver Disease. AJR Am J Roentgenol, 2008;190(4):993-1002.
[10]Loupas, T., et al., An Adaptive Weighted Median Filter for Speckle Suppression in Medical Ultrasonic Images. IEEE Trans. Circuits Syst, 1989;36(1):129-135.
[11]Ma, X., et al., Imaging-based Quantification of Hepatic Fat: Methods and Clinical Applications. Radiographics, 2009;29(5):1253-1277.
[12]Mehta, S.R., et al., Non-Invasive Means of Measuring Hepatic Fat Content. World J Gastroenterol, 2008;14(22):3476-3483.
[13]Mendez-Sanchez, N., et al., Current Concepts in the Pathogenesis of Nonalcoholic Fatty Liver Disease. Liver Int, 2007;27(4):423-433.
[14]Mulhall, B.P., et al., Non-alcoholic Fatty Liver Disease: an overview. J Gastroenterol Hepatic, 2002;17(11):1136-1143.
[15]Schwenzer, N.F., et al., Non-Invasive Assessment and Quantification of Liver Steatosis by Ultrasound, Computed Tomography and Magnetic Resonance. J Hepatol, 2009;51(3):433-445.
[16]S.Sudha. Et al., Speckle Noise Reduction in Ultrasound Images by Wavelet Thresholding Based on Weighted Variance. International Journal of Computer Theory and Engineering, 2009;1(1):1793-8201.
[17]Strauss, S., et al., Interobserver and Intraobserver Variability in the Sonographic Assessment of Fatty Liver. AJR Am J Roentgenol, 2007;189(6):W320-W323.
[18]Thakur A. et al., Image Quality Based Comparative Evaluation of Wavelet Filters in Ultrasound Speckle Reduction. Digital Singnal Process, 2005;15(5):455-465.
[19]T.Ratha Jeyalakshmi and K.Ramar., A Modified Method for Speckle Noise Removal in Ultrasound Medical Images. International Journal of Computer Theory and Engineering, 2010;2(1):1793-8163.
[20]Trahey, G.E., et al., A Quantitative Approach to Speckle Reduction via Frequency Compounding. Ultrason. Imag, 1986;8(3):151-164.
[21]Trahey, G.E., et al., Speckle Pattern Correlation with Lateral Aperture Translation: Experimental Results and Implications for Spatial Compounding. IEEE Trans Ultrason., Ferroelect. Freq. Contr, 1986;33(3):257-264.
[22]Yang, P., et al., Adaptive Weighted Median Filter Using Local Entropy for Ultrasonic Image De-noising. In Proc. Of 3rd Int. Symp. On Image and Signal Process. And Anal, 2003;2:799-803.
[23]Yoshihisa, K., et al., Comparison of CT Methods for Determining the Fat Content of the Liver. AJR, 2007;188:1307-1312.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top