(52.201.27.211) 您好!臺灣時間:2019/03/23 20:22
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
本論文永久網址: 
line
研究生:吳玉洺
研究生(外文):Yuh-Ming Wu
論文名稱:使用紅外線熱影像之乳癌分類評估
論文名稱(外文):The Assessment of Breast Cancer Classification by Using Infrared Thermal Images
指導教授:蔡育秀蔡育秀引用關係
指導教授(外文):Tsai Yuh-Show
學位類別:碩士
校院名稱:中原大學
系所名稱:醫學工程研究所
學門:工程學門
學類:綜合工程學類
論文出版年:2008
畢業學年度:96
語文別:中文
論文頁數:72
中文關鍵詞:決策樹乳癌紅外線熱影像倒傳遞類神經網路
外文關鍵詞:Breast cancerThermogramDecision treeNeuron network
相關次數:
  • 被引用被引用:2
  • 點閱點閱:298
  • 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:2
紅外線熱影像可用於評估關節炎、疼痛、心臟血管手術及乳癌輔助診斷等方面之應用。乳癌篩檢為乳癌防治之基本策略,紅外線熱影像如可作為乳癌篩檢之工具,可藉由其低成本、及無輻射傷害的特性造福大眾。在早期之乳房紅外線影像研究,一般均是以影像的模式進行研判,但是以影像模式進行研判之方式較無法擬定一個客觀的標準,近年來亦有一些研究將影像進行數值統計分析及類神經網路之分類應用,本研究擬在探討合併使用過去研究的特徵及新增不同的統計特徵,使用類神經網路及決策樹之分類研究,祈能達到輔助診斷之需求。
本研究蒐集,乳癌診斷為正常者有107名、良性腫瘤者有104名、惡性腫瘤有138名樣本之乳房熱影像及診斷資料。在特徵方面取正面乳房紅外線熱影像,以手動分割之方式區分出兩個橢圓,乳房影像區塊及乳頭位置,進行溫度特徵統計。統計特徵包含最高溫度、平均溫度、左右乳房最高溫度差、平均溫度差、溫度分佈標準差、偏態係數、峰態係數、亂度、變化梯度等17個特徵。將合格的受試者特徵樣本以診斷進行分組,再以各組樣本之三分之二的特徵及診斷進行決策樹及倒傳遞類神經網路訓練及驗證,最後再以剩餘的三分之ㄧ樣本進行最終測試。決策樹測試結果正確率(Accuracy)為 0.546至0.718不等;倒傳遞類神經網路測試結果正確率(Accuracy)為0.587至0.644不等。
由於預測效能結果並不理想,說明在17個溫度統計參數再加以倒傳遞類神經網路或決策樹之分類無法做出有效的分類。檢討主要的原因是在不同診斷族群的特徵值,有著嚴重重疊的情形,致使在分類上使用線性或非線性的分類方法,均無法將不同族群予以有效的分類,而得到令人滿意的結果。本研究以紅外線攝影儀及電腦運算能力的持續進步為基礎進行,以所使用的特徵參數預測乳癌或非乳癌之正確率、靈敏度、特異度,在評估作為單獨適用的診斷工具上並未達到診斷的基本要求,對於正常及腫瘤之熱影像分佈在特徵上之表現,無法明確的切割兩者之差異。此一結果限制它在將來作為乳癌之診斷工具的用途,它只能作為X光乳房攝影及其他診斷工具的輔助,仍無法提作為可靠的篩檢方式,至於合併其他診斷工具使用,對於乳癌診斷之幫助仍有待後續研究之驗證。
Infrared Thermography can be used as a tool for the evaluation of arthritis, pain modeling, and cardiac surgery. It also can be used for breast cancer evaluation. In the past, making use of thermography to evaluate the condition of beast cancer was mainly done by visual inspection. Besides, nowadays there is an increase in putting temperature statistical features and classified it by neuron network to evaluate the breast cancer by thermography. The study used some unique features from other studies, and classified them to breast cancer positive and negative groups by backpropgation neuron network and decision tree techniques, hopefully to build some classify model for to help the diagnosis of breast cancer.
The study had its beginning in collecting breast thermoghrapy images. At that time, the total cases of the collection were 422. There were 107 cases diagnosed normal,104 cases diagnosed benign, and 138 cases diagnosed malignant. And the rest cases were about bad images, breast mastectomy, and insufficient diagnosis information and had been excluded. In addition, according to the research, the 17 extracted features were based on the different temperature distribution statistics of the two breasts. The classified work was proceeding by backpropagation neuron network and decision tree techniques. The 2/3 eligible samples were separated for training set, and the remaining samples were kept for the final performance test. The decision tree test accuracies are between 0.546 and 0.718. The backprojection neuron network test accuracies are between 0.597 and 0.644.
The study was proceeding on the basis of high speed computer calculation and new infrared camera technology. But the result is still not satisfactory for the breast cancer diagnosis. The main reasons are that the features of normal and malignant tumor are overlapped, and the features of benign tumors are distributed amid normal and malignant groups. These reasons limited the possibility of thermography as a screen tool for breast cancer. However, under the trend of breast cancer multi modality diagnosis strategy, the application of combining thermography with other diagnostic modality still needs for further assessment.
目 錄
摘要 …………………………………………………………………………Ⅰ
英文摘要 ……………………………………………………………………Ⅱ
誌謝 …………………………………………………………………………Ⅲ
目錄 …………………………………………………………………………Ⅳ
圖目錄 ………………………………………………………………………Ⅵ
表目錄 ………………………………………………………………………Ⅶ
第一章 緒論
1.1 研究背景 ……………………………………………………………1
1.2 乳癌之篩檢及診斷 …………………………………………………2
1.3 國內外研究情況 ……………………………………………………4
1.4 研究目的 ……………………………………………………………7
1.5 論文架構………………………………………………………………8
第二章 理論基礎
2.1 紅外線測量人體溫度之理論基礎……………………………………9
2.2 人體之溫度分布 ……………………………………………………11
第三章 研究設備材料與實驗方法
3.1 材料 …………………………………………………………………13
3.2 方法 …………………………………………………………………14
3.2.1 乳房靜態紅外線熱影像攝影 ……………………………………14
3.2.2 乳房圈選及乳頭位置標定 ………………………………………15
3.2.3 溫度分佈特徵 ……………………………………………………16
3.2.4 溫度特徵值統計 …………………………………………………19
3.2.5 類神經網路分類訓練驗證及測試方法 …………………………19
3.2.6決策樹之分類訓練及測試方法 …………………………………25
3.2.7 分類測試之效能參數 ……………………………………………28
第四章 結果與討論
4.1 結果 …………………………………………………………………31
4.1.1 溫度特徵值統計 …………………………………………………31
4.1.2 倒傳遞類神經網路分類驗證及測試結果 ………………………32
4.1.3 決策樹分類驗證及測試結果 ……………………………………35
4.2 討論 …………………………………………………………………41
4.2.1 乳房最高溫與對側對稱位置溫差之參數最具分類意 …………41
4.2.2 良性腫瘤族群不易歸類 …………………………………………44
4.2.3分類辨識效能不佳之總結 ………………………………………46
4.2.4 與他相關研究結果比較 …………………………………………47
4.2.5 腫瘤大小與腫瘤分類效能之關係 ………………………………53
4.2.6乳癌分類預測的應用 ……………………………………………54
第五章 結論…………………………………………………………………55
參考文獻 ……………………………………………………………………56
附錄A 三種診斷族群之17個特徵統計長條圖 …………………………59
附錄B 目視檢查分析 ……………………………………………………62
圖 目 錄
圖 2-1 Wein定理在不同溫度下之表現 …………………………………10
圖 2-2 在波長範圍內之能量積分 ………………………………………10
圖 3-1 ATIR-M301紅外線攝影儀及影像工作站照 …………………13
圖 3-2 醫用紅外線影像攝影軟體M30-APP-V2.0 ………………………15
圖 3-3 乳房區域圈選及乳頭標定之作業介面 …………………………16
圖 3-4 類神經網路產生及測試方式之流程 ……………………………24
圖 3-5 決策樹分類之特徵參數選取流程圖 ……………………………27
圖 3-6 決策樹分類最終決策樹建構及測試流程圖 ……………………28
圖 4-1 NB-M分組之決策樹結構 …………………………………………37
圖 4-2 N-BM分組之決策樹結構 …………………………………………39
圖 4-3 N-M分組之決策樹結構 …………………………………………41
圖 4-4 三個特徵項目之族群分布情形 …………………………………45
圖 4-5 依Lesion位置手動選取高溫點與對側乳房之溫度差統計圖…46
圖 4-6 三個不同分區方法溫差累積的分類效能ROC Curve …………49
圖 4-7 二個本研究使用特徵之ROC curve ……………………………50
圖 4-8 各診斷族群的分類預測正確率 …………………………………52
表 目 錄
表 3-1 N-BM分組之分類預測值定義表 …………………………………29
表 3-2 NB-M分組之分類預測值定義表 …………………………………30
表 3-3 N-M分組之分類預測值定義表 …………………………………30
表 4-1 各特徵的三個診斷族群單因子變異數分析 ……………………31
表 4-2 類神經網路NB-M分類驗證及測試結果 ………………………35
表 4-3 類神經網路N-BM分類驗證及測試結果 ………………………35
表 4-4 類神經網路N-M分類驗證及測試結果 …………………………35
表 4-5 決策樹NB-M分組驗證及測試結果………………………………37
表 4-6 決策樹N-BM分組驗證及測試結果………………………………39
表 4-7 決策樹N-M分組驗證及測試結果 ………………………………41
表 4-8 決策樹分類中各項特徵之重要次序排序 ………………………43
表 4-9 以J.F. Head的研究方用本研究的資料進行測試結果比較 …48
表 4-10 三個分區方法之ROC curve積分AUC value …………………49
表 4-11 二個特徵ROC curve積分之AUC value ………………………50
表 4-12 二種決策樹、類神經網路分類效能與JF Head之分類性能比較………………………………………………………………… 51
表 4-13 Sym TD+Nip TD參數分類預測以惡性腫瘤體積分類之預測正確率 …………………………………………………………………53
[1] Hisayoshi Suma, Tadashi Isomura, Taiko Horii, and Toru Sato, "Intraoperative coronary atery imaging with infrared camera in off-pump CBAG," The Annals of Thoracic Surgery, vol. 70, pp. 1741-1742, 2000.
[2] Preston B.Rich, Georage R.Dulabon, Christtle D.Douillet, and Todd M.et.al, "Infrared thermography: a rapid, portable, and accurate techmique to detect experimental pneumothorax," Journal of Surgical Research, vol. 120, no. 2, pp. 163-170, Jan.2004.
[3] C. Herry and M. Frize, "Quantitative assessment of pain-related thermal dysfunction through clinical digital infrared thermal imaging," BioMedical Engineering OnLine, vol. 3, no. 1, p. 19, 2004.
[4] 行政院衛生署, "癌症登記年報,"2004.
[5] 張志隆譯, Peter Pressman, and Yashar Hirshaut, "各種診斷方法," in 乳癌全書Breast Cancer The Complete Guide 源水文化, 2001, pp. 068-115.
[6] US FDA, "FDA Regulation for Thermography on Breast Cancer Diagnosis," 2004.
[7] J. R. Keyserlingk, P. D. Ahlgren, E. Yu, N. Belliveau, and M. Yassa, "Functional infrared imaging of the breast," Engineering in Medicine and Biology Magazine, IEEE, vol. 19, no. 3, pp. 30-41, 2000.
[8] Isard HJ, Becker W, and Shilo R, "Breast Thermography after four years and 10000 studies," AJR, vol. 115, pp. 811-821, Aug.1972.
[9] Gautherie M and Gros CM, "Breast thermography and cancer risk prediction," Cancer, vol. 45, pp. 51-56, Jan.1980.
[10] J. F. Head, Wang F, and R. L. Elliott, "Breast Thermography Is a noninvasive prognostic procedure that predicts tumor growth rate in breast cancer patients," Ann NY Acad Sci, vol. 698, pp. 153-158, 1993.
[11] N. Weidner, J. P. Semple, W. R. Welch, and J. Folkman, "Tumor angiogenesis and metastasis--correlation in invasive breast carcinoma," N Engl J Med, vol. 324, no. 1, pp. 1-8, Jan.1991
[12] M. Anbar, C. Brown, L. Milescu, J. Babalola, and L. Gentner, "The potential of dynamic area telethermometry in assessing breast cancer," Engineering in Medicine and Biology Magazine, IEEE, vol. 19, no. 3, pp. 58-62, 2000.
[13] J.R.Keyserlingk, P.D.Ahlgren, E.Yu, and N.Belliveau, "Infrared Imaging of the Breast: Initial Reappraisal Using High-Resolution Digital Technology in 100 Successive Cases of Stage I and II Breast Cancer," The Breast Journal, vol. 4, no. 4, pp. 245-251, 1998.
[14] Q. Hairong, W. E. Snyder, J. F. Head, and R. L. Elliott, "Detecting breast cancer from infrared images by asymmetry analysis,", 2 ed 2000, pp. 1227-1228.
[15] Jonathan F.Head, Charles A.Lipari, Fen Wang, and Robert L.Elliot, "Image analysis of digital infrared images of the breasts from a first generation infrared imaging system," 1997, pp. 681-684.
[16] Y.R.Parisky, A.Sardi, R.Hamm, K.Hughes, L.Esserman, S.Rust, and K.Callahan, "Efficacy if Computerized Infrared Imaging Analysis to Evaluate Mammographically Suspicious Lesions," AJR, vol. 180, pp. 263-269, Jan.2003.
[17] E.Y.K Ng and E.C.Kee, "Advanced Technique in Breast Thermography Analysis ," Proceeding of the 2005 IEEE Engineering in medicine and Biology 27th Annual Conference, vol. 1, pp. 710-713, Sept.2005.
[18] Manu Mital and E.P.Scott, "Thermal Detection of Embedded Tumors Using Infrared Imaging," Journal of Biomechamical Enginering, vol. 129, pp. 33-39, Jan.2007.
[19] Terry M Button, Haifng Li, and Richard Weiss et al., "Dynamic infrared imaging for the detection of malignancy," Physics in Medicine and Biology, 2004.
[20] M. I. C. H. ANBAR, "Assessment of Physiologic and Pathologic Radiative Heat Dissipation Using Dynamic Infrared Imaging," Ann NY Acad Sci, vol. 972, no. 1, pp. 111-118, Oct.2002.
[21] M. Anbar, L. Milescu, A. Naumov, C. Brown, T. Button, C. Carly, and K. AlDulaimi, "Detection of cancerous breasts by dynamic area telethermometry," Engineering in Medicine and Biology Magazine, IEEE, vol. 20, no. 5, pp. 80-91, 2001.
[22] William C.Amalu, "Nondestructive Testing of the Human Breast: The Validity of Dyanmic Stress Testing in Medical Infrared Breast Imaging," Proceeding of the 2004 IEEE Engineering in medicine and Biology 26th Annual Conference, vol. 2, pp. 1174-1177, Sept.2004.
[23] Jonathan F.Head, Fen Wang, Charles A.Lipari, and Robert L.Elliot, "The Important Role of Infrared Imaging in Breast Cancer," IEEE Engineering in Medicine and Biology, 2000.
[24] Phani Teja Kurugant and Hairong Qi, "Asymmetry Aalysis in Breast Cancer Detection Using Thermal Infrared Imaging," 2002, pp. 1155-1156.
[25] G.Gaussorgues and S.Chomet, "Thermal Emission by Matter," in Infrared Thermography Chapman & Hall, 1994, pp. 11-60.
[26] B. F. Jones, "A reappraisal of the use of infrared thermal image analysis in medicine," Medical Imaging, IEEE Transactions on, vol. 17, no. 6, pp. 1019-1027, 1998.
[27] J Steketee, "Spectral Emissivity of Skin and Pericardium," Phys. Med. Biol., vol. 18, no. 5, pp. 686-694, 1973.
[28] Toshiro Yahara, Toshihiro Koga, Shougo Yoshida, Shino Nakagwa, and Hiroko Degughi, "Relationship Between Microvessel Density and Thermographic Hot Areas in Breast Cancer," Surgery Today, pp. 33243-33248, 2003.
[29] Y. Chen, W. Thompson, R. Semenciw, and Y. Mao, "Epidemiology of Contralateral Breast Cancer," Cancer Epidemiol Biomarkers Prev, vol. 8, no. 10, pp. 855-861, Oct.1999.
[30] J. Henry Patrick Leis, "Managing the remaining breast," Cancer, vol. 46, pp. 1026-1030, 1980.
[31] Hans-Olov, "Age at first primary as a determinant of the incident of bilateral breast cancer," Cancer, vol. 55, pp. 643-647, 1985.
[32] L. Lou, X. L. Cong, G. F. Yu, J. C. Li, and Y. X. Ma, "US findings of bilateral primary breast cancer: Retrospective study," European Journal of Radiology, vol. In Press, Corrected Proof.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔