請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74436完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 曾雪峰(Snow H. Tseng) | |
| dc.contributor.author | Ting-An Kuo | en |
| dc.contributor.author | 郭庭安 | zh_TW |
| dc.date.accessioned | 2021-06-17T08:35:41Z | - |
| dc.date.available | 2020-08-15 | |
| dc.date.copyright | 2019-08-15 | |
| dc.date.issued | 2019 | |
| dc.date.submitted | 2019-08-09 | |
| dc.identifier.citation | [1] D. Huang et al., 'Optical coherence tomography,' Science, vol. 254, no. 5035, pp. 1178-1181, 1991.
[2] Y. LeCun, Y. Bengio, and G. Hinton, 'Deep learning,' Nature, vol. 521, no. 7553, p. 436, 2015. [3] J. Schmidhuber, 'Deep learning in neural networks: An overview,' Neural Netw., vol. 61, pp. 85-117, 2015. [4] G. Litjens et al., 'A survey on deep learning in medical image analysis,' Med. Image Anal., vol. 42, pp. 60-88, 2017. [5] K. Doi, 'Computer-aided diagnosis in medical imaging: historical review, current status and future potential,' Computerized medical imaging and graphics, vol. 31, no. 4-5, pp. 198-211, 2007. [6] J. M. Schmitt, 'Optical coherence tomography (OCT): a review,' IEEE Journal of selected topics in quantum electronics, vol. 5, no. 4, pp. 1205-1215, 1999. [7] A. F. Fercher, 'In vivo optical coherence tomography,' Am J Ophthalmol, vol. 116, pp. 113-114, 1993. [8] J. Welzel, E. Lankenau, R. Birngruber, and R. Engelhardt, 'Optical coherence tomography of the human skin,' Journal of the American Academy of Dermatology, vol. 37, no. 6, pp. 958-963, 1997. [9] C.-C. Tsai et al., 'Full-depth epidermis tomography using a Mirau-based full-field optical coherence tomography,' Biomedical optics express, vol. 5, no. 9, pp. 3001-3010, 2014. [10] 陳昱彤, '全域式光學同調斷層掃描術用於動物眼睛模型之特性分析,' 碩士, 光電工程學研究所, 國立臺灣大學, 台北市, 2018. [11] V. Nair and G. E. Hinton, 'Rectified linear units improve restricted boltzmann machines,' in Proceedings of the 27th international conference on machine learning (ICML-10), pp. 807-814. 2010. [12] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' in Advances in neural information processing systems, pp. 1097-1105. 2012. [13] L. Bottou, 'Large-scale machine learning with stochastic gradient descent,' in Proceedings of COMPSTAT'2010: Springer, pp. 177-186, 2010. [14] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, 'Learning representations by back-propagating errors,' Cognitive modeling, vol. 5, no. 3, p. 1, 1988. [15] K. Simonyan and A. Zisserman, 'Very deep convolutional networks for large-scale image recognition,' arXiv preprint arXiv:1409.1556, 2014. [16] C. Szegedy et al., 'Going deeper with convolutions,' in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9. 2015. [17] K. He, X. Zhang, S. Ren, and J. Sun, 'Deep residual learning for image recognition,' in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. 2016. [18] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, 'Dropout: a simple way to prevent neural networks from overfitting,' The journal of machine learning research, vol. 15, no. 1, pp. 1929-1958, 2014. [19] M. Lin, Q. Chen, and S. Yan, 'Network in network,' arXiv preprint arXiv:1312.4400, 2013. [20] M. Abadi et al., 'Tensorflow: A system for large-scale machine learning,' in 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), pp. 265-283. 2016. [21] S. Aksoy and R. M. Haralick, 'Feature normalization and likelihood-based similarity measures for image retrieval,' Pattern Recognit. Lett., vol. 22, no. 5, pp. 563-582, 2001. [22] S. Ioffe and C. Szegedy, 'Batch normalization: Accelerating deep network training by reducing internal covariate shift,' arXiv preprint arXiv:1502.03167, 2015. [23] D. P. Kingma and J. Ba, 'Adam: A method for stochastic optimization,' arXiv preprint arXiv:1412.6980, 2014. [24] K. He, X. Zhang, S. Ren, and J. Sun, 'Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,' in Proceedings of the IEEE international conference on computer vision, pp. 1026-1034. 2015. [25] R. Kohavi, 'A study of cross-validation and bootstrap for accuracy estimation and model selection,' in Ijcai, vol. 14, no. 2: Montreal, Canada, pp. 1137-1145. 1995. [26] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, 'Grad-cam: Visual explanations from deep networks via gradient-based localization,' in Proceedings of the IEEE International Conference on Computer Vision, pp. 618-626. 2017. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74436 | - |
| dc.description.abstract | 在本研究中，我們建立了一個電腦輔助診斷（CAD）工具，提出一種結合深度學習與全域式光學同調斷層掃描（Full-Field Optical Coherence Tomography, FF-OCT）數據中自動診斷皮膚癌之有效方法。本論文採用卷積神經網路（Convolutional Neural Network, CNN） 架構訓練可提取皮膚特徵之分類器以加速檢測鱗狀細胞癌（Squamous Cell Carcinoma, SCC），並利用集成學習提升診斷能力，降低誤判程度。此外，我們已經定量地顯示，本論文所提出之方法經過10次交叉驗證於測試集上獲得78.89%之準確率。結果表明，本研究方法於OCT皮膚癌診斷之可行性。 | zh_TW |
| dc.description.abstract | Here we report an effective approach to automatically diagnose skin cancer in Full-Field Optical Coherence Tomography (FF-OCT). We employ a Convolutional Neural Network (CNN) framework to speed up the detection of Squamous Cell Carcinoma (SCC). In addition, our trained neural network yielded performance of 78.89% accuracy by 10-fold cross-validation. Experimental results demonstrate the effectiveness of the proposed method for the automated diagnosis of skin cancer. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T08:35:41Z (GMT). No. of bitstreams: 1 ntu-108-R06941092-1.pdf: 4602014 bytes, checksum: 570af40ea96024e3754ff779386a9619 (MD5) Previous issue date: 2019 | en |
| dc.description.tableofcontents | 口試委員會審定書 #
Chapter 1 緒論 1 1.1 研究動機與目標 1 1.1.1 研究動機 1 1.1.2 研究目標 2 1.1.3 論文架構 3 1.2 研究背景 4 1.2.1 電腦輔助檢測與診斷 4 1.2.2 光學同調斷層掃描 6 Chapter 2 深度學習 9 2.1 引言 9 2.2 神經元 11 2.2.1 神經元模型 11 2.2.2 激活函數 12 2.2.3 梯度下降法 16 2.3 前饋神經網路 20 2.3.1 前向傳播 20 2.3.2 反向傳播 21 2.4 卷積神經網路 26 2.4.1 引言 26 2.4.2 卷積層 27 2.4.3 池化層 28 2.4.4 完全連接層 29 2.4.5 主流卷積神經網路 30 2.5 使用GPU進行深度學習 36 Chapter 3 研究方法 37 3.1 軟硬體與計算環境設置 37 3.2 數據準備 39 3.3 資料預處理 42 3.3.1 圖像裁剪 42 3.3.2 類別資料處裡 43 3.3.3 數據特徵縮放 44 3.4 深度學習模型 45 3.5 模型超參數配置 47 3.6 降低內存成本 50 3.7 模型評估指標及驗證 51 3.7.1 模型評估指標 51 3.7.2 交叉驗證 54 Chapter 4 實驗結果與分析 57 4.1 數據集 57 4.2 診斷系統下CNN結構之驗證 58 4.2.1 Holdout 驗證 58 4.2.2 K-fold 交叉驗證 61 4.3 可視化之分析探討 63 4.4 模型後端整合優化 67 4.5 三維斷層掃描影像診斷 70 Chapter 5 結論與未來展望 72 5.1 研究結論 72 5.2 未來展望 73 參考文獻 74 | |
| dc.language.iso | zh-TW | |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 電腦輔助診斷 | zh_TW |
| dc.subject | 光學同調斷層掃描 | zh_TW |
| dc.subject | 皮膚癌 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | SCC | en |
| dc.subject | CNN | en |
| dc.subject | OCT | en |
| dc.subject | CAD | en |
| dc.subject | Skin cancer | en |
| dc.subject | Deep learning | en |
| dc.title | 以深度學習分類皮膚癌光學同調斷層掃描影像 | zh_TW |
| dc.title | Deep Learning Based Classification of Skin Cancer Optical Coherence Tomography Images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 107-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 黃升龍(Sheng-Lung Huang),陳宏銘(Homer H. Chen) | |
| dc.subject.keyword | 深度學習,卷積神經網路,光學同調斷層掃描,皮膚癌,電腦輔助診斷, | zh_TW |
| dc.subject.keyword | Deep learning,CNN,OCT,CAD,Skin cancer,SCC, | en |
| dc.relation.page | 76 | |
| dc.identifier.doi | 10.6342/NTU201902797 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2019-08-12 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 光電工程學研究所 | zh_TW |
| 顯示於系所單位： | 光電工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-108-1.pdf 未授權公開取用 | 4.49 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。