研究生: |
詹翔崴 HSIANG-WEI CHAN |
---|---|
論文名稱: |
基於人工智慧之腦腫瘤病理影像自動分類系統:結合特徵萃取及資料平衡之研究 Automatic classification system of brain tumor pathological images based on artificial intelligence:combining feature extraction and data balance |
指導教授: |
黃騰毅
Teng-Yi Huang |
口試委員: |
黃騰毅
Teng-Yi Huang 林益如 Yi-Ru Lin 蔡尚岳 Shang-Yueh Tsai 莊子肇 Tzu-Chao Chuang |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2021 |
畢業學年度: | 109 |
語文別: | 中文 |
論文頁數: | 43 |
中文關鍵詞: | 人工智慧 、腦腫瘤病理影像 、特徵萃取 、資料平衡 、自動分類 |
外文關鍵詞: | Artificial intelligence, Brain tumor pathological images, Feature extraction, Data balance, Automatic classification |
相關次數: | 點閱:198 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
現代醫學中,細胞腫瘤為一種複雜的疾病,而腫瘤細胞的切片影像則能為醫生提供腫瘤內各類型的細胞組成以及分布概況,並可透過此影象對病患做初步的病症判讀。本研究結合機器學習及人工智慧的方式,設計一套腦腫瘤類型的分類系統,透過自動化的處理對腦腫瘤的切片影像進行自動分類。然而機器學習的設計方法也有其受限之處,在現實環境中,臨床病患的個人資料不易取得,而不同來源的資料也有品質不一的問題,在這種情況下所訓練出的模型可能會造成預測結果偏頗或是不佳的狀況,因此本研究中使用了不同的影像處理及訓練方法使訓練出的模型能在資料受限的狀況下有穩定的判別能力,此外,我們設計了三種實驗探討系統中各項方法對於預測結果的影響。
Cellular tumors are a complex disease, and the histological slides of tumor cells allow doctors to observe the composition and distribution of various types of cells in the tumor, and make initial diagnosis of the disease through this image. Advancements in digital microscopy enables digitization of histology slides and histopathology diagnosis combined with image analysis is an emerging application of machine-learning techniques. In this study, we designed a classification system for brain tumor slides, aiming to automatically classify brain tumor types. However, the design method of machine learning also has its limitations. The quality of data from different sources is also different. The model obtained by data-driven methods may be influenced by data quality and then produce inaccurate results. In this study, we performed three experiments to explore the influence of machine-learning methods and developed a fully automatic system for histopathology diagnosis.
1. Javier, R.T. and J.S. Butel, The history of tumor virology. Cancer research, 2008. 68(19): p. 7693-7706.
2. Whiteside, T., The tumor microenvironment and its role in promoting tumor growth. Oncogene, 2008. 27(45): p. 5904-5912.
3. Zacharaki, E.I., et al., Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine, 2009. 62(6): p. 1609-1618.
4. Bondy, M.L., et al., Brain tumor epidemiology: consensus from the Brain Tumor Epidemiology Consortium. Cancer, 2008. 113(S7): p. 1953-1968.
5. Louis, D.N., et al., The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Acta neuropathologica, 2016. 131(6): p. 803-820.
6. Moise, D. and S. Madhusoodanan, Psychiatric symptoms associated with brain tumors: a clinical enigma. CNS Spectr, 2006. 11(1): p. 28-31.
7. El-Dahshan, E.-S.A., et al., Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm. Expert systems with Applications, 2014. 41(11): p. 5526-5545.
8. Akram, M.U. and A. Usman. Computer aided system for brain tumor detection and segmentation. in International conference on Computer networks and information technology. 2011. IEEE.
9. Reinhardt, H., H. Meyer, and E. Amrein, A computer-assisted device for the intraoperative CT-correlated localization of brain tumors. European surgical research, 1988. 20(1): p. 51-58.
10. Horobin, R.W., Histochemistry: an explanatory outline of histochemistry and biophysical staining. 2014: Elsevier.
11. Chan, H.-W., Y.-T. Weng, and T.-Y. Huang. Automatic Classification of Brain Tumor Types with the MRI Scans and Histopathology Images. in International MICCAI Brainlesion Workshop. 2019. Springer.
12. Mohri, M., A. Rostamizadeh, and A. Talwalkar, Foundations of machine learning. 2018: MIT press.
13. Krizhevsky, A., I. Sutskever, and G.E. Hinton, Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012. 25: p. 1097-1105.
14. Deng, J., et al. Imagenet: A large-scale hierarchical image database. in 2009 IEEE conference on computer vision and pattern recognition. 2009. Ieee.
15. He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
16. Huang, G., et al. Densely connected convolutional networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
17. Howard, A.G., et al., Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
18. Zoph, B., et al. Learning transferable architectures for scalable image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
19. Zoph, B. and Q.V. Le, Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578, 2016.
20. Kanungo, T., et al., An efficient k-means clustering algorithm: Analysis and implementation. IEEE transactions on pattern analysis and machine intelligence, 2002. 24(7): p. 881-892.
21. Quinlan, J.R., Induction of decision trees. Machine learning, 1986. 1(1): p. 81-106.