跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.87) 您好!臺灣時間:2025/02/09 10:31
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:翁廷瑋
研究生(外文):Ting-Wei Weng
論文名稱:以電腦斷層攝影影像資料於區分EGFR+及EGFR-肺腺癌病人
論文名稱(外文):Distinguish EGFR+ and EGFR- Patients in Lung adenocarcinoma using CT Images
指導教授:鍾翊方
指導教授(外文):I-Fang Chung
學位類別:碩士
校院名稱:國立陽明大學
系所名稱:生物醫學資訊研究所
學門:生命科學學門
學類:生物化學學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:中文
論文頁數:49
中文關鍵詞:電腦斷層攝影影像
外文關鍵詞:CT Images
相關次數:
  • 被引用被引用:0
  • 點閱點閱:187
  • 評分評分:
  • 下載下載:6
  • 收藏至我的研究室書目清單書目收藏:0
肺癌可簡單分成兩大類,分別是小細胞型肺癌以及非小細胞型肺癌。多數的人得到的是非小細胞癌,它又可能是鱗狀、扁平的上皮癌等不同種類,而肺腺癌是其中最常見的一種。肺腺癌的病患治療方式包含手術摘除腫瘤、化學治療以及標靶藥物治療,本論文主要討論為標靶藥物治療的患者。標靶藥物治療可抑制癌細胞繼續成長,或盡量使其萎縮,並不能讓腫瘤消失,因此不能擅自停藥,否則很容易復發。但並非所有罹患肺腺癌的患者都適合標靶藥物治療,需確認癌細胞有表皮生長因子(Epidermal Growth Factor Receptor, EGFR)突變,並施以標靶藥物的治療,才能達到治療的效果。目前各大醫院須透過切片方式來獲得檢驗結果,但切片面臨的困難點有:因肺功能差,可能導致氣胸、肺炎或死亡、等待檢驗結果時間長以及侵入式對於患者有所負擔。因此本篇研究希望透過非侵入式的方式也就是醫學影像,來確認癌細胞是否突變。因此,我們設計了一個分類機制,其中包含以下三個部分:(1) 抽取各種影像特徵值 (2)選擇有用的特徵以及(3)設計完成該診斷系統。我們收集了94筆數據,其中包含(a)14位病患突變為點落於exon19;(b)31位病患突變為點落於exon21;(c)12位病患突變位點為exon18或exon20;(d)31位病患未突變;(e)6位病患為多個突變位點。
目前實驗結果表明,我們使用灰階共生矩陣(Gray-level Co-occurrence Matrix, GLCM)以及鄰近灰階差異矩陣(Neighborhood Gray-Tone Difference Matrix , NGTDM)來進行特徵抽取,每個群組間的分類,都具有影響性之特徵值,且分類效果高達80%的成功率。此外,透過這些特徵值,我們可以解釋出不同基因型態在影像上的差異性。
希望提出的策略能透過更多特徵值,讓EGFR(+)及EGFR(-)的分類效果更好,分類機制更為完善。爾後,我們預期收集更多的患者影像數據,產生更多不同類型的特徵值,以及引入不同的特徵選擇方法,透過分類器來挖掘更多有用的影像特徵值。
The efficacy of targeted therapy for lung adenocarcinoma (LA) patients has a strong correlation with the mutation statuses of epidermal growth factor receptor (EGFR) gene. Some studies have adopted computed tomography (CT) scans to identify useful imaging features for prognostic prediction or distinguishing the EGFR mutation statuses of LA patients. The aim of this study is to investigate what CT imaging features are good for classifying EGFR mutation subtypes of LA patients. Hence, we designed an in silico analysis pipeline containing the following three parts: (1) extraction of various imaging features; (2) selection of useful imaging features; (3) design of a diagnostic system. Here we collected 94 sets of CT data from LA patients including (a) 14 patients with exon 19 in-frame deletion of EGFR; (b) 31 patients with exon 21 L858R point of EGFR; (c) 12 patients with mutations located in exons 18~21 of EGFR but not in cases (a) and (b); (d) 31 patients without mutants in exons 18~21 of EGFR; (e) 6 patients with exons 19 and 21 of EGFR. Currently, experimental results show that our proposed strategy can select useful CT imaging features and yield effectively discriminatory power to distinguish some EGFR mutation subtypes. In the future, we plan to dig out more useful/powerful imaging features by collecting more patient data, producing more CT imaging features, and introducing different feature selection approaches/classifiers.

中文摘要 i
ABSTRACT iii
目錄 v
圖目錄 vi
表目錄 vii
第一章 背景與緒論 1
1.1 肺癌介紹 1
1.2 小細胞肺癌與非小細胞肺癌 3
1.3 肺腺癌介紹 4
1.4 表皮生長因子受體(Epidermal growth factor receptor, EGFR)介紹 5
1.5 肺腺癌標靶藥物介紹 6
1.6 電腦斷層掃描影像介紹 9
1.7 紋理分析 10
1.8 研究動機與目的 12
第二章 文獻回顧 13
第三章 材料與方法 15
3.1 材料來源 15
3.2 分析流程 15
3.3 紋理分析 17
3.3.1 資料前處理 19
3.3.1.1 VOI選取 19
3.3.1.2 方向性 20
3.3.2 灰階共生矩陣 21
3.2.3 鄰近灰階差異矩陣 25
3.4 紋理特徵選取 28
3.4.1 minimum Redundancy Maximum Relevance feature selection 28
3.5 分類機制 30
3.5.1 支持向量機 30
3.5.2 一次性交叉驗證 32
第四章 結果與討論 33
4.1 EGFR+與EGFR-差異性 33
4.1.1 exon other與EGFR(-) 34
4.1.2 exon 19, exon21與EGFR(-) 38
4.1.3 exon 19, exon21與exon other 41
第五章 結果與未來展望 45
參考文獻 47
1. Siegel, R., D. Naishadham, and A. Jemal, Cancer statistics, 2012. CA Cancer J Clin, 2012. 62(1): p. 10-29.

2. Wahbah, M., et al., Changing trends in the distribution of the histologic types of lung cancer: a review of 4,439 cases. Ann Diagn Pathol, 2007. 11(2): p. 89-96.

3. Groome, P.A., et al., The IASLC Lung Cancer Staging Project: validation of the proposals for revision of the T, N, and M descriptors and consequent stage groupings in the forthcoming (seventh) edition of the TNM classification of malignant tumours. J Thorac Oncol, 2007. 2(8): p. 694-705.

4. Mountain, C.F., The evolution of the surgical treatment of lung cancer. Chest Surg Clin N Am, 2000. 10(1): p. 83-104.

5. Mountain, C.F., Staging classification of lung cancer. A critical evaluation. Clin Chest Med, 2002. 23(1): p. 103-21.

6. Ringner, M. and J. Staaf, Consensus of gene expression phenotypes and prognostic risk predictors in primary lung adenocarcinoma. Oncotarget, 2016. 7(33): p. 52957-52973.

7. Chong, C.R. and P.A. Janne, The quest to overcome resistance to EGFR-targeted therapies in cancer. Nat Med, 2013. 19(11): p. 1389-400.

8. Tetsu, O., et al., Drug Resistance to EGFR Inhibitors in Lung Cancer. Chemotherapy, 2016. 61(5): p. 223-35.

9. Lo, H.W., EGFR-targeted therapy in malignant glioma: novel aspects and mechanisms of drug resistance. Curr Mol Pharmacol, 2010. 3(1): p. 37-52.

10. Chan, S.K., W.J. Gullick, and M.E. Hill, Mutations of the epidermal growth factor receptor in non-small cell lung cancer -- search and destroy. Eur J Cancer, 2006. 42(1): p. 17-23.

11. Shigematsu, H. and A.F. Gazdar, Somatic mutations of epidermal growth factor receptor signaling pathway in lung cancers. Int J Cancer, 2006. 118(2): p. 257-62.

12. Sharma, S.V., et al., Epidermal growth factor receptor mutations in lung cancer. Nat Rev Cancer, 2007. 7(3): p. 169-81.

13. Yun, C.H., et al., Structures of lung cancer-derived EGFR mutants and inhibitor complexes: mechanism of activation and insights into differential inhibitor sensitivity. Cancer Cell, 2007. 11(3): p. 217-27.

14. Fang, S. and Z. Wang, EGFR mutations as a prognostic and predictive marker in non-small-cell lung cancer. Drug Des Devel Ther, 2014. 8: p. 1595-611.

15. Morgensztern, D., et al., Molecularly targeted therapies in non-small-cell lung cancer annual update 2014. J Thorac Oncol, 2015. 10(1 Suppl 1): p. S1-63.

16. Depeursinge, A., et al., Lung texture classification using locally-oriented Riesz components. Med Image Comput Comput Assist Interv, 2011. 14(Pt 3): p. 231-8.

17. Ganeshan, B., et al., Tumour heterogeneity in oesophageal cancer assessed by CT texture analysis: preliminary evidence of an association with tumour metabolism, stage, and survival. Clin Radiol, 2012. 67(2): p. 157-64.

18. Cunliffe, A.R., et al., Lung texture in serial thoracic CT scans: assessment of change introduced by image registration. Med Phys, 2012. 39(8): p. 4679-90.

19. Mansoor, A., et al., Segmentation and Image Analysis of Abnormal Lungs at CT: Current Approaches, Challenges, and Future Trends. Radiographics, 2015. 35(4): p. 1056-76.

20. El-Baz, A., et al., Computer-aided diagnosis systems for lung cancer: challenges and methodologies. Int J Biomed Imaging, 2013. 2013: p. 942353.

21. Heim, B., et al., Magnetic resonance imaging for the diagnosis of Parkinson's disease. J Neural Transm (Vienna), 2017. 124(8): p. 915-964.

22. Ozkan, E., et al., CT Gray-Level Texture Analysis as a Quantitative Imaging Biomarker of Epidermal Growth Factor Receptor Mutation Status in Adenocarcinoma of the Lung. AJR Am J Roentgenol, 2015. 205(5): p. 1016-25.

23. Hu, W., et al., Characterization of collagen fibers by means of texture analysis of second harmonic generation images using orientation-dependent gray level co-occurrence matrix method. J Biomed Opt, 2012. 17(2): p. 026007.

24. Mahmood, U., et al., Investigating the Robustness Neighborhood Gray Tone Difference Matrix and Gray Level Co-occurrence Matrix Radiomic Features on Clinical Computed Tomography Systems Using Anthropomorphic Phantoms: Evidence From a Multivendor Study. J Comput Assist Tomogr, 2017.

25. Karacavus, S., et al., Can Laws Be a Potential PET Image Texture Analysis Approach for Evaluation of Tumor Heterogeneity and Histopathological Characteristics in NSCLC? J Digit Imaging, 2017.

26. Sogawa, K., et al., Neurogenic and Myogenic Diseases: Quantitative Texture Analysis of Muscle US Data for Differentiation. Radiology, 2017. 283(2): p. 492-498.

27. Ergen, B. and M. Baykara, Texture based feature extraction methods for content based medical image retrieval systems. Biomed Mater Eng, 2014. 24(6): p. 3055-62.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top