請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80778完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張瑞峰(Rui-Feng Zhang) | |
| dc.contributor.author | Han-Jia Shih | en |
| dc.contributor.author | 施翰嘉 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:16:15Z | - |
| dc.date.available | 2021-11-05 | |
| dc.date.available | 2022-11-24T03:16:15Z | - |
| dc.date.copyright | 2021-11-05 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-10-18 | |
| dc.identifier.citation | [1] C. E. DeSantis et al., 'Breast cancer statistics, 2019,' CA: a cancer journal for clinicians, vol. 69, no. 6, pp. 438-451, 2019. [2] U. Veronesi et al., 'Distribution of axillary node metastases by level of invasion. An analysis of 539 cases,' Cancer, vol. 59, no. 4, pp. 682-687, 1987. [3] U. Veronesi, A. Luini, V. Galimberti, S. Marchini, V. Sacchini, and F. Rilke, 'Extent of metastatic axillary involvement in 1446 cases of breast cancer,' European journal of surgical oncology: the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology, vol. 16, no. 2, pp. 127-133, 1990. [4] C. L. Carter, C. Allen, and D. E. Henson, 'Relation of tumor size, lymph node status, and survival in 24,740 breast cancer cases,' Cancer, vol. 63, no. 1, pp. 181-187, 1989. [5] B. Weigelt, J. L. Peterse, and L. J. Van't Veer, 'Breast cancer metastasis: markers and models,' Nature reviews cancer, vol. 5, no. 8, pp. 591-602, 2005. [6] D. Ivens, A. L. Hoe, T. J. Podd, C. R. Hamilton, I. Taylor, and G. T. Royle, 'Assessment of morbidity from complete axillary dissection,' British journal of cancer, vol. 66, no. 1, pp. 136-138, 1992. [7] J. Yang et al., 'Preoperative prediction of axillary lymph node metastasis in breast cancer using mammography-based radiomics method,' Scientific reports, vol. 9, no. 1, pp. 1-11, 2019. [8] L. Ouldamer, F. Arbion, A. Balagny, F. Fourquet, H. Marret, and G. Body, 'Validation of a breast cancer nomogram for predicting nonsentinel node metastases after minimal sentinel node involvement: validation of the Helsinki breast nomogram,' The Breast, vol. 22, no. 5, pp. 787-792, 2013. [9] J. Cools-Lartigue and S. Meterissian, 'Accuracy of axillary ultrasound in the diagnosis of nodal metastasis in invasive breast cancer: a review,' World journal of surgery, vol. 36, no. 1, pp. 46-54, 2012. [10] X. Zheng et al., 'Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer,' Nature communications, vol. 11, no. 1, pp. 1-9, 2020. [11] J. Nori et al., 'Role of axillary ultrasound examination in the selection of breast cancer patients for sentinel node biopsy,' The American journal of surgery, vol. 193, no. 1, pp. 16-20, 2007. [12] G. R. Kim et al., 'Preoperative axillary US in early-stage breast cancer: potential to prevent unnecessary axillary lymph node dissection,' Radiology, vol. 288, no. 1, pp. 55-63, 2018. [13] I. Ibrahim-Zada, C. S. Grant, K. N. Glazebrook, and J. C. Boughey, 'Preoperative axillary ultrasound in breast cancer: safely avoiding frozen section of sentinel lymph nodes in breast-conserving surgery,' Journal of the American College of Surgeons, vol. 217, no. 1, pp. 7-15, 2013. [14] J.-G. Lee et al., 'Deep learning in medical imaging: general overview,' Korean journal of radiology, vol. 18, no. 4, pp. 570-584, 2017. [15] Z. Liu et al., 'Axillary lymph node metastasis prediction by contrast-enhanced computed tomography images for breast cancer patients based on deep learning,' Computers in Biology and Medicine, vol. 136, p. 104715, 2021. [16] M. Guillemé, V. Masson, L. Rozé, and A. Termier, 'Agnostic local explanation for time series classification,' pp. 432-439: IEEE. [17] M. T. Ribeiro, S. Singh, and C. Guestrin, '' Why should i trust you?' Explaining the predictions of any classifier,' pp. 1135-1144. [18] M. T. Ribeiro, S. Singh, and C. Guestrin, 'Anchors: High-precision model-agnostic explanations,' vol. 32. [19] R. Bellman, 'A Markovian decision process,' Journal of mathematics and mechanics, vol. 6, no. 5, pp. 679-684, 1957. [20] C. J. C. H. Watkins and P. Dayan, 'Q-learning,' Machine learning, vol. 8, no. 3-4, pp. 279-292, 1992. [21] R. S. Sutton, 'Learning to predict by the methods of temporal differences,' Machine learning, vol. 3, no. 1, pp. 9-44, 1988. [22] N. Metropolis and S. Ulam, 'The monte carlo method,' Journal of the American statistical association, vol. 44, no. 247, pp. 335-341, 1949. [23] V. Mnih et al., 'Playing atari with deep reinforcement learning,' arXiv preprint arXiv:1312.5602, 2013. [24] H. Van Hasselt, A. Guez, and D. Silver, 'Deep reinforcement learning with double q-learning,' vol. 30. [25] M. Wunder, M. L. Littman, and M. Babes, 'Classes of multiagent q-learning dynamics with epsilon-greedy exploration.' [26] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' Advances in neural information processing systems, vol. 25, pp. 1097-1105, 2012. [27] O. Russakovsky et al., 'Imagenet large scale visual recognition challenge,' International journal of computer vision, vol. 115, no. 3, pp. 211-252, 2015. [28] S. Hochreiter, 'The vanishing gradient problem during learning recurrent neural nets and problem solutions,' International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 6, no. 02, pp. 107-116, 1998. [29] K. He, X. Zhang, S. Ren, and J. Sun, 'Deep residual learning for image recognition,' pp. 770-778. [30] H. Zhang et al., 'Resnest: Split-attention networks,' arXiv preprint arXiv:2004.08955, 2020. [31] S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, 'Aggregated residual transformations for deep neural networks,' in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1492–1500-1492–1500. [32] W. Wu, Y. Zhang, D. Wang, and Y. Lei, 'SK-Net: Deep learning on point cloud via end-to-end discovery of spatial keypoints,' vol. 34, pp. 6422-6429. [33] J. Hu, L. Shen, and G. Sun, 'Squeeze-and-excitation networks,' pp. 7132-7141. [34] Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, 'Supplementary Material for “ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks”.' [35] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk, 'Slic superpixels,' 2010. [36] D. G. Bedi et al., 'Cortical morphologic features of axillary lymph nodes as a predictor of metastasis in breast cancer: in vitro sonographic study,' American Journal of Roentgenology, vol. 191, no. 3, pp. 646-652, 2008. [37] H. Abe, R. A. Schmidt, C. A. Sennett, A. Shimauchi, and G. M. Newstead, 'US-guided core needle biopsy of axillary lymph nodes in patients with breast cancer: why and how to do it,' Radiographics, vol. 27, no. suppl_1, pp. S91-S99, 2007. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80778 | - |
| dc.description.abstract | 乳腺癌是女性最常見的癌症，也是導致女性死亡的第二大常見癌症。腋窩淋巴結的狀態對於乳腺癌患者的預後和治療具有至關重要的影響，目前診斷腋窩淋巴結狀態的方法是臨床醫生透過超音波影像進行診斷接著執行侵入式手術，然而診斷腋窩淋巴結的狀態十分仰賴於臨床醫生的經驗。因此。我們開發了一種術前診斷腋窩淋巴結狀態的電腦輔助診斷系統(computer-aided diagnosis system)。該系統使用了腋窩淋巴結的超音波影像來診斷腋窩淋巴結的轉移狀態。首先，由於超音波的雜訊以及周圍組織干擾，我們採用深度強化學習的框架來偵測超音波影像中的腋窩淋巴結。在獲取腋窩淋巴結的區域後，我們使用了具有高效的通道注意力機制的拆分注意力網路進行腋窩淋巴結狀態的診斷。在我們的實驗之中，總共有217例女性乳腺癌患者，其中有103例腋窩淋巴結的非轉移性影像，266例腋窩淋巴結的轉移性影像，用於評估我們所提出的系統。根據我們實驗的結果，所提出的系統具有準確度81.3% (300/369)、靈敏度80.5% (83/103)、特異性82.0% (218/266)、F1分數75.4%、陽性預測值(PPV) 67.7%、陰性預測值(NPV) 91.4%以及ROC曲線下的面積(AUC) 0.8378的效能。該結果顯示了我們的所提出的系統對於診斷超音波影像中的腋窩淋巴結具有良好的性能。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:16:15Z (GMT). No. of bitstreams: 1 U0001-1110202114550900.pdf: 4068388 bytes, checksum: b9ab455af599aaab62c121e15e25e2ae (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 口試委員會審定書 i 致謝 ii 摘要 iii Abstract iv Table of Contents vi List of Figures viii List of Tables ix Chapter 1 Introduction 1 Chapter 2 Material 4 Chapter 3 Methods 6 3.1. Problem Description 6 3.2. ALN Detection Module 7 3.2.1. MDP Parameters 9 3.2.2. Double Deep Q Learning (DDQN) 12 3.3. ALN Diagnosis module 15 3.3.1. Network Architecture CNN backbone 16 3.3.2. Efficient Channel Attention (ECA) 18 3.3.3. Network with ECA module 20 3.4. Local Interpretable Model Explanation 21 Chapter 4 Experiments 23 4.1. Experimental Environment 23 4.2. Implementation Details 23 4.3. Statistical Analysis 24 4.4. Comparison of Different CNN Architectures 24 4.5. Ablation Study 27 4.6. Interpretability Experiment 29 Chapter 5 Discussion and Conclusions 31 References 35 | |
| dc.language.iso | en | |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 乳腺癌 | zh_TW |
| dc.subject | 腋窩淋巴結 | zh_TW |
| dc.subject | 超音波影像 | zh_TW |
| dc.subject | 電腦輔助診斷 | zh_TW |
| dc.subject | 深度強化學習 | zh_TW |
| dc.subject | Breast cancer | en |
| dc.subject | Deep reinforcement learning | en |
| dc.subject | Computer-aided diagnosis | en |
| dc.subject | Ultrasound image | en |
| dc.subject | Axillary lymph node | en |
| dc.subject | Convolutional neural network | en |
| dc.title | 使用深度Q強化學習框架和ResNeSt診斷超音波影像中的腋窩淋巴結 | zh_TW |
| dc.title | Diagnose Axillary Lymph Node In Ultrasound Images by using Deep Q Reinforcement Learning Framework and ResNeSt | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 羅崇銘(Hsin-Tsai Liu),陳啟禎(Chih-Yang Tseng) | |
| dc.subject.keyword | 乳腺癌,腋窩淋巴結,超音波影像,電腦輔助診斷,深度強化學習,卷積神經網路, | zh_TW |
| dc.subject.keyword | Breast cancer,Axillary lymph node,Ultrasound image,Computer-aided diagnosis,Deep reinforcement learning,Convolutional neural network, | en |
| dc.relation.page | 37 | |
| dc.identifier.doi | 10.6342/NTU202103648 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-10-18 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 生醫電子與資訊學研究所 | zh_TW |
| 顯示於系所單位： | 生醫電子與資訊學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1110202114550900.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 3.97 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。