請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94255完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林永松 | zh_TW |
| dc.contributor.advisor | Frank Yeong-Sung Lin | en |
| dc.contributor.author | 陸翊涔 | zh_TW |
| dc.contributor.author | Yi-Tsen Lu | en |
| dc.date.accessioned | 2024-08-15T16:28:09Z | - |
| dc.date.available | 2024-08-16 | - |
| dc.date.copyright | 2024-08-15 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-08 | - |
| dc.identifier.citation | [1] W.-H. Chow, L. M. Dong, and S. S. Devesa, “Epidemiology and risk factors for kidney cancer,” Nature Reviews Urology, vol. 7, no. 5, pp. 245–257, 2010.
[2] S. Turajlic, C. Swanton, and C. Boshoff, “Kidney cancer: the next decade,” Journal of Experimental Medicine, vol. 215, no. 10, pp. 2477–2479, 2018. [3] F. E. Vera-Badillo, A. J. Templeton, I. Duran, A. Ocana, P. de Gouveia, P. Aneja, J. J. Knox, I. F. Tannock, B. Escudier, and E. Amir, “Systemic therapy for non–clear cell renal cell carcinomas: A systematic review and meta-analysis,” European Urology, vol. 67, no. 4, pp. 740–749, 2015. [4] P. Kapur, S. Setoodeh, E. Araj, J. Yan, V. S. Malladi, J. A. Cadeddu, A. Christie, and J. Brugarolas, “Improving renal tumor biopsy prognostication with BAP1 analyses,” Archives of Pathology & Laboratory Medicine, vol. 146, no. 2, pp. 154–165, 2022. [5] N. Heller, F. Isensee, K. H. Maier-Hein, X. Hou, C. Xie, F. Li, Y. Nan, G. Mu, Z. Lin, M. Han, Q. Song, S. Kihara, Z. Liu, J. C. Paetzold, F. Jia, Z. Li, H. Kim, G. Oh, X. Li, S. Zhao, L. Zhao, Y. He, W. Chen, Q. Zhang, S. Zheng, H. Wang, Y. Wang, Z. Sun, L. Jiang, Z. Liu, Z. Li, S. Nie, H. Gao, X. Xu, D. Yang, N. Kim, P. D. An, M. Lewin, X. Wang, R. Correa, S. Bruns, M. Venable, J. R. Eisenbrey, A. Thanabalan, C. Corrado, J. Mamou, A. Kamen, D. Goldgof, L. O. Hall, O. Gloger, F. Nensa, A. L. Martel, A. Jerebko, R. Manniesing, S. Kondo, K. Okamura, Y. Ma-sutani, Y. Sato, K. Hatano, T. Hayashi, K. Imanaka, M. Oda, Z. Zhou, X. Bai, Q. Wei, Z. Bai, Z. Li, H. Zhang, J. Li, W. Chen, Y. Zheng, Z. Liu, X. Zhang, K. Niu, X. Wang, Z. Zhu, X. Wang, L. Zhou, W. Luo, X. Zhou, R. Yao, Y. Nie, Q. Zhan, S. Wang, Q. Liu, W. Zhong, Y. Li, X. Xue, F. Yang, K. Ren, X. Lu, Y. Liang, Y. Zhang, S. Wu, W. Ma, Z. Zhang, L. Tang, X. Zhou, Q. Wei, W. Liu, T. Zhou, Z. Ye, X. Li, L. Wang, J. Zhang, J. Liu, J. Zhang, Y. Zhang, Y. Zhang, C. Xu, F. Zhang, J. Zhang, B. Li, G. Liu, F. Xie, X. Meng, J. Zhang, D. Shen, X. Liu, F. Liu, H. Liu, L. Chen, X. Tan, B. Zhang, H. Ren, H. Li, Y. Li, M. Li, Y. Yuan, Q. Zhao, Q. Zhang, L. Cui, L. He, J. Li, and C. Chen, “The kits21 challenge.” https://kits-challenge.org/, 2021. Accessed: 2024-06-04. [6] J. J. Hsieh, M. P. Purdue, S. Signoretti, C. Swanton, L. Albiges, M. Schmidinger, D. Y. Heng, J. Larkin, and V. Ficarra, “Renal cell carcinoma,” Nature Reviews Dis-ease Primers, vol. 3, no. 1, pp. 1–19, 2017. [7] R. Goyal, E. Gersbach, X. J. Yang, and S. M. Rohan, “Differential diagnosis of renal tumors with clear cytoplasm: clinical relevance of renal tumor subclassification in the era of targeted therapies and personalized medicine,” Archives of Pathology & Laboratory Medicine, vol. 137, no. 4, pp. 467–480, 2013. [8] S. Chen, N. Zhang, L. Jiang, F. Gao, J. Shao, T. Wang, E. Zhang, H. Yu, X. Wang, and J. Zheng, “Clinical use of a machine learning histopathological image signature in diagnosis and survival prediction of clear cell renal cell carcinoma,” International Journal of Cancer, vol. 148, no. 3, pp. 780–790, 2021. [9] S. A. Fuhrman, L. C. Lasky, and C. Limas, “Prognostic significance of morphologic parameters in renal cell carcinoma,” The American Journal of Surgical Pathology, vol. 6, no. 7, pp. 655–664, 1982. [10] M. E. Mayerhoefer, A. Materka, G. Langs, I. Häggström, P. Szczypiński, P. Gibbs, and G. Cook, “Introduction to radiomics,” Journal of Nuclear Medicine, vol. 61, no. 4, pp. 488–495, 2020. [11] J. E. Van Timmeren, D. Cester, S. Tanadini-Lang, H. Alkadhi, and B. Baessler, “Ra-diomics in medical imaging—“how-to＂guide and critical reflection,” Insights Into Imaging, vol. 11, no. 1, pp. 1–16, 2020. [12] B. K. Budai, R. Stollmayer, A. D. Rónaszéki, B. Körmendy, Z. Zsombor, L. Palotás, B. Fejér, A. Szendrõi, E. Székely, P. Maurovich-Horvat, et al., “Radiomics analysis of contrast-enhanced ct scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols,” Frontiers in Medicine, vol. 9, p. 974485, 2022. [13] J. J. Van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan, R. G. Beets-Tan, J.-C. Fillion-Robin, S. Pieper, and H. J. Aerts, “Computational radiomics system to decode the radiographic phenotype,” Cancer Research, vol. 77, no. 21, pp. e104–e107, 2017. [14] N. Iqbal, R. Mumtaz, U. Shafi, and S. M. H. Zaidi, “Gray level co-occurrence ma-trix (glcm) texture based crop classification using low altitude remote sensing plat-forms,” PeerJ Computer Science, vol. 7, p. e536, 2021. [15] G. Thibault, B. Fertil, C. Navarro, S. Pereira, P. Cau, N. Levy, J. Sequeira, and J. T. I. Mari, “Gray level size zone matrix application to cell nuclei classification,” Pattern Recognition and Information Processing, pp. 140–145, 2009. [16] M. M. Galloway, “Texture analysis using gray level run lengths,” Computer Graph-ics and Image Processing, vol. 4, no. 2, pp. 172–179, 1975. [17] A. Chu, C. M. Sehgal, and J. F. Greenleaf, “Use of gray value distribution of run lengths for texture analysis,” Pattern Recognition Letters, vol. 11, no. 6, pp. 415–419, 1990. [18] Y. Li, X. Gao, X. Tang, S. Lin, and H. Pang, “Research on automatic classification technology of kidney tumor and normal kidney tissue based on computed tomogra-phy radiomics,” Frontiers in Oncology, vol. 13, p. 1013085, 2023. [19] U. Mahmood, A. P. Apte, J. O. Deasy, C. R. Schmidtlein, and A. Shukla-Dave, “In-vestigating 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,” Journal of Computer Assisted Tomography, vol. 41, no. 6, pp. 995–1001, 2017. [20] M. Khushi, K. Shaukat, T. M. Alam, I. A. Hameed, S. Uddin, S. Luo, X. Yang, and M. C. Reyes, “A comparative performance analysis of data resampling methods on imbalance medical data,” IEEE Access, vol. 9, pp. 109960–109975, 2021. [21] G. E. Batista, R. C. Prati, and M. C. Monard, “A study of the behavior of several methods for balancing machine learning training data,” ACM SIGKDD Explorations Newsletter, vol. 6, no. 1, pp. 20–29, 2004. [22] J. Prusa, T. M. Khoshgoftaar, D. J. Dittman, and A. Napolitano, “Using random undersampling to alleviate class imbalance on tweet sentiment data,” in 2015 IEEE International Conference on Information Reuse and Integration, pp. 197–202, 2015. [23] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “Smote: syn-thetic minority over-sampling technique,” Journal of Artificial Intelligence Re-search, vol. 16, pp. 321–357, 2002. [24] I. Kononenko, “Machine learning for medical diagnosis: History, state of the art and perspective,” Artificial Intelligence in medicine, vol. 23, no. 1, pp. 89–109, 2001. [25] M. P. LaValley, “Logistic regression,” Circulation, vol. 117, no. 18, pp. 2395–2399, 2008. [26] S. Nusinovici, Y. C. Tham, M. Y. C. Yan, D. S. W. Ting, J. Li, C. Sabanayagam, T. Y. Wong, and C.-Y. Cheng, “Logistic regression was as good as machine learning for predicting major chronic diseases,” Journal of Clinical Epidemiology, vol. 122, pp. 56–69, 2020. [27] A. J. Myles, R. N. Feudale, Y. Liu, N. A. Woody, and S. D. Brown, “An introduction to decision tree modeling,” Journal of Chemometrics: A Journal of the Chemomet-rics Society, vol. 18, no. 6, pp. 275–285, 2004. [28] D. Lavanya and K. U. Rani, “Performance evaluation of decision tree classifiers on medical datasets,” International Journal of Computer Applications, vol. 26, no. 4, pp. 1–4, 2011. [29] Y. Liu, Y. Wang, and J. Zhang, “New machine learning algorithm: Random for-est,” in Information Computing and Applications: Third International Conference, ICICA 2012, Chengde, China, September 14-16, 2012. Proceedings 3, pp. 246–252, Springer, 2012. [30] F. Yang, H.-z. Wang, H. Mi, C.-d. Lin, and W.-w. Cai, “Using random forest for re-liable classification and cost-sensitive learning for medical diagnosis,” BMC Bioin-formatics, vol. 10, no. 1, pp. 1–14, 2009. [31] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785–794, 2016. [32] A. Ogunleye and Q.-G. Wang, “Xgboost model for chronic kidney disease diagno-sis,” IEEE/ACM transactions on computational biology and bioinformatics, vol. 17, no. 6, pp. 2131–2140, 2019. [33] S. Suthaharan and S. Suthaharan, “Support vector machine,” pp. 207–235, 2016. [34] Y. Weng, C. Wu, Q. Jiang, W. Guo, and C. Wang, “Application of support vector ma-chines in medical data,” in 2016 4th International Conference on Cloud Computing and Intelligence Systems (CCIS), pp. 200–204, IEEE, 2016. [35] J. Zupan, “Introduction to artificial neural network (ann) methods: What they are and how to use them,” Acta Chimica Slovenica, vol. 41, no. 3, p. 327, 1994. [36] D. J. Sargent, “Comparison of artificial neural networks with other statistical ap-proaches: Results from medical data sets,” Cancer: Interdisciplinary International Journal of the American Cancer Society, vol. 91, no. S8, pp. 1636–1642, 2001. [37] P. Community, “Pyradiomics documentation,” 2024. Accessed: 2024-07-03. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94255 | - |
| dc.description.abstract | 本研究聚焦於腎細胞癌，特別是其主要類別腎亮細胞癌（Clear Cell Renal Cell Carcinoma, ccRCC），此為腎臟癌的主要發病原因。傳統上，醫生診斷腎細胞癌需要判斷腫瘤的良惡性及其具體類型，這通常依賴於醫療影像及組織切片等方法。然而，這些方法不僅耗時且有時結果不夠精確。本研究的重要性在於提出一種結合影像組學和臨床數據的新方法，以模擬醫生的診斷流程並進行改良，使用2021年腎腫瘤分割（KiTS21）公開資料集中的電腦斷層掃描（CT）影像，進行腎臟及腫瘤特徵的精確擷取。研究首先將進行腫瘤良惡性的分類，然後進一步區分ccRCC與非ccRCC腫瘤類型。透過這種兩階段分類法，本研究不僅旨在提升診斷的準確性和速度，同時也期望減少依賴侵入性生物切片的需求，從而減輕病人的負擔。在應用場景方面，此技術可直接應用於臨床診斷，協助醫生迅速且準確地判斷腎腫瘤的類型，進而制定更適合的治療方案。此外，這一技術的發展和完善也將推動個人化醫療的進程，使醫療資源能更有效地被利用。綜合上述，本研究的成果將對腎臟癌的診斷和治療產生深遠的影響，為醫療領域帶來顯著的進步。 | zh_TW |
| dc.description.abstract | This study zeroes in on Renal Cell Carcinoma (RCC), with a specific focus on its primary subtype, Clear Cell Renal Cell Carcinoma (ccRCC), a leading cause of kidney cancer. Traditionally, physicians diagnose RCC by determining the tumor's malignancy and specific type, often relying on medical imaging and tissue biopsy. However, these methods are not only time-consuming but sometimes yield less accurate results. The significance of this research lies in its proposition of a novel method that amalgamates radiomics with clinical data to refine and simulate the physician's diagnostic process. Utilizing Computed Tomography (CT) images from 2021 Kidney Tumor Segmentation datasets (KiTS21), the study accurately extracts kidney and tumor characteristics. It begins with classifying tumors into benign or malignant categories, followed by further differentiation into ccRCC and non-ccRCC types. Through this two-tier classification method, the study aims to enhance the accuracy and speed of diagnosis while also hoping to reduce the dependency on invasive biopsies, thereby alleviating patient distress. In practical scenarios, this technique can be directly applied to clinical diagnostics, aiding physicians in swiftly and precisely determining the type of renal tumor, thereby crafting more suitable treatment strategies. Moreover, the development and refinement of this technology are set to propel the progress of personalized medicine, ensuring more effective utilization of medical resources. In sum, the outcomes of this research are poised to profoundly impact the diagnosis and treatment of kidney cancer, marking a significant stride forward in the medical field. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-15T16:28:09Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-15T16:28:09Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝i
摘要iv Abstract v Contents vii List of Figures xi List of Tables xiii Chapter1 Introduction 1 1.1 Background. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.3 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.4 Clinical Implication . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.5 Contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.6 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . 4 Chapter2 Literature Review 6 2.1 Renal Cell Carcinoma (RCC) . . . . . . . . . . . . . . . . . . . . . 6 2.2 Clear Cell Renal Cell Carcinoma (ccRCC) . . . . . . . . . . . . . . 7 2.3 The Diagnosis of ccRCC . . . . . . . . . . . . . . . . . . . . . . . . 8 2.4 Radiomics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.4.1 Brief Introduction of Radiomics . . . . . . . . . . . . . . . . . . . 9 2.4.2 Radiomics in Kidney Tumor . . . . . . . . . . . . . . . . . . . . . 11 2.4.3 Radiomic Features . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.5 Medical Data Imbalance and Data Augmentation . . . . . . . . . . . 14 2.6 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.7 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 Chapter3 Proposed Methods 23 3.1 Dataset-KiTS21 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.2 Statistic Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.3 Data Preprocessing (Stage1) . . . . . . . . . . . . . . . . . . . . . . 27 3.3.1 3DRadiomicFeaturesExtraction. . . . . . . . . . . . . . . . . . . 28 3.3.2 2DRadiomicFeaturesExtraction. . . . . . . . . . . . . . . . . . . 29 3.3.3 The Feature-Level Fusion. . . . . . . . . . . . . . . . . . . . . . . 32 3.4 Machine Learning for Malignant (Stage2) . . . . . . . . . . . . . . 34 3.4.1 Data Augmentation . . . . . . . . . . . . . . . . . . . . . . . . . . 34 3.4.2 Machine Learning and Model Fusion. . . . . . . . . . . . . . . . . 37 3.5 Machine Learning for ccRCC (Stage3) . . . . . . . . . . . . . . . . 38 3.5.1 Malignant Classifier as a Filter . . . . . . . . . . . . . . . . . . . . 39 3.5.2 Machine Learning Classifier of ccRCC. . . . . . . . . . . . . . . . 39 3.6 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 3.6.1 Performance Metrics . . . . . . . . . . . . . . . . . . . . . . . . . 40 3.6.2 Evaluation Strategy . . . . . . . . . . . . . . . . . . . . . . . . . . 42 3.7 Model Implementation . . . . . . . . . . . . . . . . . . . . . . . . . 43 Chapter 4 Experiments and Results 44 4.1 Malignant Experiment . . . . . . . . . . . . . . . . . . . . . . . . . 44 4.1.1 Individual Model Training of Malignant with Weighted Model Fu-sion and Series Connect Model . . . . . . . . . . . . . . . . . . . . 45 4.1.1.1 Individual Model Training of Malignant . . . . . . . . 45 4.1.1.2 Sum-Weighting Fusion Model of Malignant Classifier . 48 4.1.1.3 Series Connect Model of Malignant Classifier . . . . . 51 4.1.2 2D Radiomics with Majority Voting Model of Malignant . . . . . . 52 4.1.3 Concatenation of Kidney and Tumor Radiomics in Model Training of Malignant . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 4.1.4 Malignant Classifier Comparison . . . . . . . . . . . . . . . . . . . 57 4.2 ccRCC Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 4.2.1 Filter out Malignant Cases for ccRCC Classifier . . . . . . . . . . . 58 4.2.2 Individual Model Training of ccRCC with Weighted Model Fusion and Series Connect Model . . . . . . . . . . . . . . . . . . . . . . 59 4.2.2.1 Individual Model Training of ccRCC . . . . . . . . . . 60 4.2.2.2 Sum-Weighting Fusion Model of ccRCC Classifier . . 63 4.2.2.3 Series Connect Model of ccRCC Classifier . . . . . . . 66 4.2.3 2D Radiomics with Majority Voting Model of ccRCC . . . . . . . . 67 4.2.4 Concatenation of Kidney and Tumor Radiomics in Model Training of ccRCC . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 70 4.2.5 ccRCC Classifier Comparison . . . . . . . . . . . . . . . . . . . . 71 4.3 The Feature Importance of Radiomics in Malignant and ccRCC . . . 72 4.3.1 Feature Importance in Malignant . . . . . . . . . . . . . . . . . . . 73 4.3.2 Feature Importance in ccRCC . . . . . . . . . . . . . . . . . . . . . 73 4.4 Additional Experiment of Malignant Classifier . . . . . . . . . . . . 74 4.4.1 Classic Benign Type . . . . . . . . . . . . . . . . . . . . . . . . . 75 4.4.2 Data Augmentation of Benign Cases . . . . . . . . . . . . . . . . . 76 4.4.3 The Results and Conclusion of Focusing on Classic Benign Cases . 77 4.5 Additional Experiment of 2D Radiomics Slice Order in Malignant . . 80 4.5.1 The Results and Conclusion of 2D Radiomics Slice Order Malignant 80 Chapter 5 Conclusions 82 5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82 5.2 References Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84 References 86 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 腎臟腫瘤分類 | zh_TW |
| dc.subject | 影像組學 | zh_TW |
| dc.subject | 特徵工程 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | Feature Engineering | en |
| dc.subject | Kidney Tumor Classification | en |
| dc.subject | Radiomics | en |
| dc.subject | Machine Learning | en |
| dc.subject | Clinical Data | en |
| dc.title | 基於人工智慧技術融合影像组學和臨床數據於腎細胞癌子型診斷 | zh_TW |
| dc.title | Integration of Artificial Intelligence Technology with Radiomics and Clinical Data for Subtype Diagnosis of Renal Cell Carcinoma | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 蕭邱漢;呂東武;楊瀅臻 | zh_TW |
| dc.contributor.oralexamcommittee | Chiu-Han Hsiao;Tung-Wu Lu;Ying-Chen Yang | en |
| dc.subject.keyword | 腎臟腫瘤分類,影像組學,特徵工程,機器學習, | zh_TW |
| dc.subject.keyword | Kidney Tumor Classification,Radiomics,Clinical Data,Feature Engineering,Machine Learning, | en |
| dc.relation.page | 91 | - |
| dc.identifier.doi | 10.6342/NTU202403285 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-08-12 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 5.05 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。