(3.235.191.87) 您好!臺灣時間:2021/05/13 05:06
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:::

我願授權國圖
: 
twitterline
研究生:洪恩慧
研究生(外文):En-Huei Hong
論文名稱:乳房腫瘤超音波影像之電腦輔助診斷:幾近不受系統對比度設定影響之影像特徵擷取
論文名稱(外文):Computer-Aided Diagnosis of Breast Lesions on Sonograms with Extraction of Nearly Contrast-Independent Image Features
指導教授:陳中明陳中明引用關係
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:醫學工程學研究所
學門:工程學門
學類:綜合工程學類
論文種類:學術論文
論文出版年:2004
畢業學年度:92
語文別:中文
論文頁數:61
中文關鍵詞:特徵值迴歸分析函數分類對比度獨立超音波影像電腦輔助診斷乳房腫瘤影像分析
外文關鍵詞:Breast neoplasmSonogramsComputer Aided DiagnosisImage analysisClassificationLogistic Regression FunctionFeaturesCo
相關次數:
  • 被引用被引用:0
  • 點閱點閱:160
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
使用乳房超音波影像檢查可以顯著的減少昂貴且易引發病患緊張之不必要的組織切片檢查。然而,從乳房超音波影像中歸納出影像特徵來區分良惡性腫瘤的工作卻十分仰賴臨床醫師的判讀。不同的醫師在不同的系統參數設定下其所判讀出來的結果很可能會不同。雖然電腦輔助診斷技術可以減緩此一問題,然而綜觀過去乳房超音波影像電腦輔助診斷的研究卻有一共同問題,即其所常用的區域性影像特徵會隨著超音波影像系統參數的設定改變而改變。為減少此潛在問題,本研究提出Normalization的概念以減少系統參數設定之影響,更嘗試改變影像對比度來進行嚴格的實驗。本研究所提出的電腦輔助診斷系統以幾近不受系統對比度參數設定影響之影像特徵擷取,主要模擬臨床醫師診斷乳房腫瘤的模式來區別乳房超音波影像中的良性與惡性腫瘤,提高正確診斷率以達到早期治療的目的。有別於以往電腦輔助診斷乳房腫瘤之超音波影像的研究,主要在於醫師可依循其專業調整超音波影像系統對比度參數設定且不受限於超音波影像系統的機型,同時以乳房腫瘤外正常組織超音波影像的紋理當作參考指標找出Normalization之標準,優點是降低不同對比度參數設定造成的潛在差別,並正規化輔助診斷系統所轉換出的紋理特徵值。

本研究的實驗材料是由台北榮民總醫院放射部周宜宏醫師所提供,包括91個良性腫瘤的乳房超音波影像和69個惡性腫瘤的乳房超音波影像。本研究以幾近不受對比度參數設定影響所擷取出的區域性影像特徵,分別為Cell-Based特徵、Contrast特徵、Variance特徵、Sliding-Window特徵與Fractal Dimension特徵等,並將影像特徵以Logistic Regression Function以及leave-one-out cross-validation的概念進行特徵選取與分類,選出最佳的特徵值組合,進而將腫瘤區別為良性或惡性。經實驗結果可獲致0.8824�b0.0146的ROC Az值與0.823�b0.016的正確率,雖不比幾何特徵好,但在結合兩者特徵下卻獲致0.967�b0.011的ROC Az值與0.934�b0.018的正確率,經Paired-Sample t Tests證明比單就幾何性特徵的表現顯著高。

經Paired-Sample t Tests的假設證明改變影像對比度所擷取的影像特徵,不論是區域性特徵或結合幾何特徵的實驗之下,ROC值與Accuracy值的表現無顯著差異,表示所提出的影像特徵幾近不受對比度變異之影響。本研究所提出的區域性影像特徵,不僅有補強幾何特徵的作用,更使得乳房腫瘤超音波影像在對比度變異之下的電腦輔助診斷更為強健可靠。
Breast sonography is an effective approach to reducing the number of unnecessary biopsy, which is not only an expensive but also an unpleasant process. Nevertheless, to extract the image features for differentiating the malignant lesions from the benign ones is a task highly depending on the interpretations of medical doctors. Moreover, breast sonologists with different experiences or on different sonographic system settings might have different interpretations of the sonograms. Although these problems may be alleviated by taking advantage of computer-aided diagnosis (CAD) techniques, most previous CAD algorithms suffer a common problem that their textural features may vary with the system settings in general. To remedy this deficiency, we propose to minimize the influence of system setting by incorporating the idea of normalization. This idea is verified by a rigorous simulation study, in which the same images with different contrasts are simulated to test the robustness of the proposed CAD algorithm. Consequently, the uniqueness of the proposed CAD system lies in the nearly contrast-independent images features, which mimic the clinical strategy frequently used by medical doctors in differential diagnosis of benign and malignant breast lesions. Compared with the conventional CAD systems for breast lesions, the proposed CAD system has a salient feature that no constraint is imposed on the contrast settings, which allows the medical doctors to adjust the contrast freely to attain the best views of sonographic breast lesions.
All the sonographic breast images are provided by the Department of Radiology, Division of Ultrasound, Taipei Veterans General Hospital, including 91 benign breast lesions and 69 malignant breast lesions. Several textural image features with nearly contrast-independent are proposed in this study, namely, Cell-Based features, Contrast feature, Variance feature, Sliding-Window features and Fractal dimension features. Feature selection and classification are accomplished by using a logistic regression function based on leave-one-out cross-validation strategy to select the best combinations of features for differentiating benign lesions from malignant ones. The experimental results show that the best performance achieved by using textural features only is 0.882±0.015 and 0.823±0.016 in terms of and classification accuracy, respectively. Although this performance is inferior to that achieved solely by using geometrical features, supported by the results of paired-sample t-tests, a better performance has been attained by combining both types of features, the best of which is 0.967±0.011 and 0.934±0.018 in terms of and classification accuracy, respectively.
With the support of paired-sample t-tests, the results of the simulation studies on the effect of contrast variations show that there is no significant difference between the performance for the original images and that for the images with different contrast degradations. It suggests that the proposed sonographic features, including textural and geometrical features, be nearly contrast-independent. In conclusion, the proposed textural features are not only capable of complementing the performance of geometrical features, but also robust to the potential contrast variation in real practices.
目 錄

誌謝 Ⅰ
中文摘要 Ⅱ
英文摘要 Ⅳ
目錄 Ⅵ
圖表目錄 Ⅷ

第一章 前言 1
1.1、介紹 1
1.2、研究動機與目的 2
1.3、論文架構 6
第二章 乳房超音波影像之電腦輔助診斷研究回顧 7
第三章 材料與特徵擷取 10
3.1、材料來源與ROI影像的選取 11
3.2、特徵擷取 14
3.2.1、幾何性特徵擷取 15
3.3、區域性特徵擷取 18
3.3.1、 Cell-Based特徵 18
3.3.1.1、Multi-Scale Gaussian Smoother 19
3.3.1.2、Laplacian Filter 20
3.3.1.3、Gray Scale Dilation 21
3.3.1.4、Watershed Transform 22
3.3.2、 Normalization 30
3.3.3、 Contrast特徵 33
3.3.4、 Sliding-Window特徵 34
3.3.5、 Variance相關特徵 36
3.3.6、 Fractal Dimension特徵 36
3.3.7、 Cell_Max Histogram特徵 40
第四章 特徵值選取與分類 43
4.1、 特徵值選取 43
4.2、 分類方法 44
4.3、 Logistic Regression Function 44
4.4、 Cross-validation 48
第五章 實驗結果與討論 49
5.1、區域性影像特徵實驗結果 49
5.2、結合幾何特徵實驗結果 51
5.3、不受系統對比度(Contrast)設定之實驗結果 53
5.4、討論 55
第六章 結論與展望 57
參考文獻 59
[1]Pisani P, Parkin DM, Ferlay J. Estimates of the worldwide mortality from eighteen major cancers in 1985: Implications for prevention and projections of future burden. Int J Cancer 1993; 55: 891-903.
[2]Bassett LW, Jackson VP, Jahan R, Yao SF, Gold RH. Diagnosis of diseases of the breast. Philadelphia, PA: Saunders, 1997.
[3]Brown ML, Houn F, Sickles EA, Kessler LG. Screening mammography in community practice: positive predictive value of abnormal findings and yield of follow-up diagnostic procedures. AJR 1995; 165: 1373-1377.
[4]Zheng Y, Greenleaf JF, Gisvold JJ. Reduction of breast biospies with a modified self-organizing map. IEEE Trans Neural Networks 1997; 8: 1386-1396.
[5]Fornage BD, Sneige N, Faroux MJ, Andry E. Sonographic appearance and ultrasound-guided fine-needle aspiration biopsy of breast carcinomas smaller than 1cm. J Ultrasound Med 1990; 9: 559-568.
[6]Bassett LW, Ysrael M, Gold RH, Ysrael C. Usefulness of mammography and sonography in women < 35 yrs old. Radiolography 1991; 180:831.
[7]Jackson VP. The role of US in breast imaging. Radiology 1990; 177:305-311.
[8]Fornage BD, Lorigan JG, Andry E. Fibroadenoma of the breast: sonographic appearance. Radiology 1989; 172: 671-675.
[9]Tohno E, Cosgrove DO, Sloane JP. Ultrasound diagnosis of breast diseases. Edinburgh, Scortland:Churchill Livingstone 1994; 50-73.
[10]Stavros AT, Thickman D, Rapp CL, et al. Solid breast nodules: Use of sonography to distinguish between benign and malignant lesions. Radiology 1995; 196:123-134.
[11]Skaane P, Engedal K. Analysis of sonographic features in the differentiation of fibroadenoma and invasive ductal carcinoma. AJR 1998; 170:109-114.
[12]Goldberg V, Manduca A, Ewert DL, Gisvold JJ, Greenleaf JF. Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence. Med Phys 1992; 19: 1475-1481.
[13]Garra BS, Krasner BH, Horii SC, Ascher S, Mun SK, Zeman RK. Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis. Ultrasonic Imaging 1993; 15: 267-285.
[14]Ruggiero C, Bagnoli F, Sacile M, Rescinito CC, Sardanelli F. Automatic recognition of malignant lesions in ultrasound images by artificial neural networks. Proc of the 20th Annual Intl Conf of the IEEE EMBS 1998; 20: 872-875.
[15]Giger ML, Al-Hallaq H, Hui Z, et al. Computerized analysis of lesions in US images of the breast. Acad Radiol 1999; 6: 665-674.
[16]Chen DR, Chang RF, Huang YL. Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology 1999; 213: 407-412.
[17]Chen DR, Chang RF, Huang YL. Breast cancer diagnosis using self-organizing map for sonography. Ultrasound in Med. Biol 2000; 26: 405-411.
[18]Chang RF, Kuo WJ, Chen DR, Huang YL, Lee JH, Chou YH. Computer-aided diagnosis for surgical office based breast ultrasound. Arch Surg 2000; 135: 696-699.
[19]Chen DR, Chang RF, Huang YL, Chou YH, Tiu CM, Tsai PP. Texture analysis of breast tumors on sonograms. Seminars in Ultrasound, CT and MRI 2000; 21(4): 308-316.
[20]Kuo WJ, Chang RF, Chen DR, Lee CC. Data mining with decision trees for diagnosis of breast tumor in medical ultrasonic images. Breast Cancer Research and Treatment 2001; 66(1): 51-57.
[21]Kuo WJ, Chang RF, WK Moon, Lee JH, Chen DR. Computer-aided diagnosis of breast tumors with different US systems. Academic Radiology 2002; 9(7): 793-799.
[22]Kuo WJ, Chang RF, Lee CC, Moon WK, Chen DR. Retrieval technique for the diagnosis of solid breast tumors on sonogram. Ultrasound in Medicine and Biology 2002; 28(7): 903-909.
[23]Chen DR, Kuo WJ, Chang RF, WK Moon, Lee JH. Use of the bootstrap technique with small training sets for computer-aided diagnosis in breast ultrasound. Ultrasound in Medicine and Biology 2002; 28(7): 897-902.
[24]Chen DR, Chang RF, Kuo WJ, Chen MC, Huang YL. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. Ultrasound in Medicine and Biology 2002; 28(10): 1301-1310.
[25]Chang RF, Wu WJ, Moon WK, Chou YH, Chen DR. Support vector machines for diagnosis of breast tumors on us images. Academic Radiology 2003; 10(2): 189-197.
[26]Chen DR, Chang RF, Chen WM, Moon WK. Computer aided diagnosis for 3-dimensional breast ultrasonography. Archives of Surgery 2003; 138(3): 296-302.
[27]Hung GS. Multivariate analysis of tumor shape features for ultrasound breast cancer diagnosis. Master Thesis. National Yang-Ming University, 2000.
[28]Chou YH, Tiu CM, Hung GS, Wu SC, Chang TY, Chiang HHK. Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis. Ultrasound in Medicine and Biology 2001; 27(11): 1493-1498.
[29]Chen CM, Chou YH, Han KC, Hung GS, Tiu CM, Chiou HJ, Chiou SY. Computer-aided diagnosis of breast lesions on sonogram using nearly setting-independent features and artificial neural networks. Radiology 2003; 226(2): 504-514.
[30]國立台灣大學醫學工程所 楊銘雄碩士論文
[31]國立台灣大學醫學工程所 韓克忠碩士論文:超音波影像乳房腫瘤之電腦輔助區別診斷.
[32]Chen CM, Chou YH, Han KC, Hung GS, Tiu CM, Chiou HJ, Chiou SY. Computer-aided diagnosis of breast lesions on sonogram using nearly setting-independent features and artificial neural networks. Radiology 2003; 226(2): 504-514.
[33]Vincent L, Soille P. Watershed in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans PAMI 1991; 13(6): 583-597.
[34]Wang D. A multiscale gradient algorithm for image segmentation using watersheds. Pattern Recognition 1997; 30(12): 2043-2052.
[35]Haris K, Efstratiadis SN, Maglaveras N, Katsaggelos AK. Hybrid image segmentation using watersheds and fast region merging. IEEE Trans Image Processing 1998; 7(12): 1684-1699.
[36]Gauch JM. Image segmentation and analysis via multiscale gradient watershed hierarchies. IEEE Trans Image Processing 1999; 8(1): 69-79.
[37]Karaman K, Kutay M, Bozdagi G. An adaptive speckle suppression filter for medical ultrasonic imaging. IEEE Trans. Med. Imaging 1995; 14: 283-292.
[38]Sarkar, N. & Chaudhuri, B.B.- An Efficient Differential Box-Counting Approach to Compute Fractal Dimension of Image. IEEE Trans. on Systems, Man and Cybernetics, 24 (1) Jan. (1994) pp. 115 – 120.
[39]Neter and Kutner and Nachtsheim and Wasserman, ”Applied linear regression models” IRWIN, Third Edition.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔