請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68855完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張瑞峰(Ruey-Feng Chang) | |
| dc.contributor.author | Chih-Ching Tsai | en |
| dc.contributor.author | 蔡智晴 | zh_TW |
| dc.date.accessioned | 2021-06-17T02:38:47Z | - |
| dc.date.available | 2017-08-24 | |
| dc.date.copyright | 2017-08-24 | |
| dc.date.issued | 2017 | |
| dc.date.submitted | 2017-08-16 | |
| dc.identifier.citation | [1] R. L. Siegel, K. D. Miller, and A. Jemal, 'Cancer statistics, 2016,' CA: A Cancer Journal for Clinicians, vol. 66, no. 1, pp. 7-30, 2016.
[2] K. Drukker, M. L. Giger, K. Horsch, M. A. Kupinski, C. J. Vyborny, and E. B. Mendelson, 'Computerized lesion detection on breast ultrasound,' Medical Physics, vol. 29, no. 7, pp. 1438-1446, 2002. [3] B. Sahiner et al., 'Malignant and Benign Breast Masses on 3D US Volumetric Images: Effect of Computer-aided Diagnosis on Radiologist Accuracy,' Radiology, vol. 242, no. 3, pp. 716-724, 2007. [4] S. Singh, J. Maxwell, J. A. Baker, J. L. Nicholas, and J. Y. Lo, 'Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents,' Radiology, vol. 258, no. 1, pp. 73-80, 2011. [5] C.-M. Chen et al., 'Breast Lesions on Sonograms: Computer-aided Diagnosis with Nearly Setting-Independent Features and Artificial Neural Networks,' Radiology, vol. 226, no. 2, pp. 504-514, 2003. [6] M. C. Yang et al., 'Robust Texture Analysis Using Multi-Resolution Gray-Scale Invariant Features for Breast Sonographic Tumor Diagnosis,' IEEE Transactions on Medical Imaging, vol. 32, no. 12, pp. 2262-2273, 2013. [7] D.-R. Chen, R.-F. Chang, W.-J. Kuo, M.-C. Chen, and Y. u.-L. Huang, 'Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks,' Ultrasound in Medicine & Biology, vol. 28, no. 10, pp. 1301-1310, 2002/10/01/ 2002. [8] A. V. Alvarenga, W. C. A. Pereira, A. F. C. Infantosi, and C. M. Azevedo, 'Complexity curve and grey level co-occurrence matrix in the texture evaluation of breast tumor on ultrasound images,' Medical Physics, vol. 34, no. 2, pp. 379-387, 2007. [9] H. D. Cheng, J. Shan, W. Ju, Y. Guo, and L. Zhang, 'Automated breast cancer detection and classification using ultrasound images: A survey,' Pattern Recognition, vol. 43, no. 1, pp. 299-317, 2010/01/01/ 2010. [10] Y.-L. Huang, K.-L. Wang, and D.-R. Chen, 'Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines,' Neural Computing & Applications, journal article vol. 15, no. 2, pp. 164-169, April 01 2006. [11] K. Fukushima, 'Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,' Biological Cybernetics, journal article vol. 36, no. 4, pp. 193-202, April 01 1980. [12] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, 'Gradient-based learning applied to document recognition,' Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998. [13] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, 'Imagenet: A large-scale hierarchical image database,' in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 2009, pp. 248-255: Ieee. [14] Y. LeCun, Y. Bengio, and G. Hinton, 'Deep learning,' Nature, Insight vol. 521, no. 7553, pp. 436-444, 05/28/print 2015. [15] O. Russakovsky et al., 'ImageNet Large Scale Visual Recognition Challenge,' International Journal of Computer Vision, journal article vol. 115, no. 3, pp. 211-252, December 01 2015. [16] K. He, X. Zhang, S. Ren, and J. Sun, 'Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification,' ArXiv e-prints, vol. 1502, February 6, 2015. [17] W. Zhang et al., 'Deep Convolutional Neural Networks for Multi-Modality Isointense Infant Brain Image Segmentation,' NeuroImage, vol. 108, pp. 214-224, 01/03 2015. [18] M. Anthimopoulos, S. Christodoulidis, L. Ebner, A. Christe, and S. Mougiakakou, 'Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network,' IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1207-1216, 2016. [19] H. R. Roth et al., 'Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation,' IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1170-1181, 2016. [20] D. Erhan, P.-A. Manzagol, Y. Bengio, S. Bengio, and P. Vincent, 'The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training,' presented at the Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, 2009. [21] A. S. Razavian, H. Azizpour, J. Sullivan, and S. Carlsson, 'CNN Features Off-the-Shelf: An Astounding Baseline for Recognition,' in 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014, pp. 512-519. [22] J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, 'How transferable are features in deep neural networks?,' presented at the Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, 2014. [23] N. Tajbakhsh et al., 'Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?,' IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1299-1312, 2016. [24] H. C. Shin et al., 'Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning,' IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285-1298, 2016. [25] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, 'Improving neural networks by preventing co-adaptation of feature detectors,' ArXiv e-prints, vol. 1207, July 3, 2012. [26] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, 'Dropout: a simple way to prevent neural networks from overfitting,' J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929-1958, 2014. [27] V. Nair and G. E. Hinton, 'Rectified Linear Units Improve Restricted Boltzmann Machines,' presented at the ICML, 2010. [28] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'ImageNet classification with deep convolutional neural networks,' presented at the Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, 2012. [29] A. L. Maas, A. Y. Hannun, and A. Y. Ng, 'Rectifier nonlinearities improve neural network acoustic models,' in Proc. ICML, 2013, vol. 30, no. 1. [30] B. Xu, N. Wang, T. Chen, and M. Li, 'Empirical Evaluation of Rectified Activations in Convolutional Network,' ArXiv e-prints, vol. 1505, May 5, 2015. [31] K. Simonyan and A. Zisserman, 'Very Deep Convolutional Networks for Large-Scale Image Recognition,' ArXiv e-prints, vol. 1409, April 10, 2015. [32] R. Kohavi, 'A study of cross-validation and bootstrap for accuracy estimation and model selection,' presented at the Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2, Montreal, Quebec, Canada, 1995. [33] D. P. Kingma and J. Ba, 'Adam: A Method for Stochastic Optimization,' in Proceedings of the 3rd International Conference on Learning Representations (ICLR), 2014. [34] A. T. Stavros, D. Thickman, C. L. Rapp, M. A. Dennis, S. H. Parker, and G. A. Sisney, 'Solid breast nodules: use of sonography to distinguish between benign and malignant lesions,' Radiology, vol. 196, no. 1, pp. 123-134, 1995. [35] G. Rahbar et al., 'Benign versus Malignant Solid Breast Masses: US Differentiation,' Radiology, vol. 213, no. 3, pp. 889-894, 1999. [36] G. C. Kagadis et al., 'Cloud computing in medical imaging,' Medical Physics, vol. 40, no. 7, pp. 070901-n/a, 2013, Art. no. 070901. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68855 | - |
| dc.description.abstract | 在女性癌症中，乳癌是盛行率最高的癌症，其死亡率也高居第二位，而早期診斷及治療則可大幅降低致死率。乳癌可以透過乳房超音波做診斷，而電腦輔助診斷可以降低人為差異。隨著電腦運算速率的提升，深度學習已被廣泛應用於各個領域，尤其常用於影像辨識。本研究共採用1225個經病理驗證的腫瘤病例，其中包含847個良性病例以及378個惡性病例。本研究並提出以卷積神經網絡中知名的VGG架構為基礎進行簡化的診斷方法，可以在GPU加速的情況下減少15倍的訓練時間。本實驗結果的準確率為84.39%、靈敏性為74.00%、特異性為88.21%及ROC曲線面積為0.91，與傳統的基於紋路的診斷方法沒有顯著差異。而在採用學習遷移（Transfer Learning）之技術後，實驗結果的ROC曲線面積更可高達0.94且具有顯著差異。即便在僅使用原訓練資料的十分之一的情況下，學習遷移仍可達到ROC曲線面積0.89，與傳統方法的0.79比起來有顯著的進步。因此，相較於傳統診斷方式，基於卷積神經網絡的電腦輔助乳癌診斷方法將更為強健。 | zh_TW |
| dc.description.abstract | Breast cancer is the most commonly diagnosed cancer and is the second leading cause of cancer death in women. Therefore, early diagnosis leads to early treatment and reduces mortality rates. Breast ultrasound is used to diagnose breast cancer and computer-aided diagnosis (CADx) has been used to decrease inter-observer variation. With the growth of computing power, particularly graphics processing unit (GPU) computing, deep learning has been applied in many different domains and especially in image recognition. In this study, the diagnostic performance was evaluated with 1225 cases with biopsy-proven diagnosis. There were 847 benign cases and 378 malignant cases. The convolutional neural network (CNN) based method proposed in this study, VGG-Lite, is based on the famous VGG network and can be trained 15 times faster with GPU. VGG-Lite produced diagnostic performance with 84.39% in accuracy, 74.00% in sensitivity, 88.21% in specificity and 0.91 in AUC (Area under the Curve of ROC). There was no significant difference compared to the conventional texture analysis method (p-value > 0.05). After applying transfer learning, AUC as high as 0.94 was obtained. When using only 10% of the original training set, the VGG16 architecture achieved an AUC of 0.89 with transfer learning, showing a significant difference compared to the texture analysis method (AUC=0.79, p-value < 0.05). Hence, CNN-based methods are much more robust than conventional methods. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T02:38:47Z (GMT). No. of bitstreams: 1 ntu-106-R04945041-1.pdf: 1552932 bytes, checksum: 3f1feb8defbaa0341e52ede6f1d2c72b (MD5) Previous issue date: 2017 | en |
| dc.description.tableofcontents | 口試委員會審定書 ii
致謝 iii 摘要 iv Abstract v Table of Contents vi List of Figures viii List of Tables ix Chapter 1 Introduction 1 Chapter 2 Materials 4 2.1 Data Acquisition 4 2.2 Data Characteristics 6 Chapter 3 CNN Based Tumor Diagnosis Method 7 3.1 Convolutional Neural Network (CNN) 8 3.1.1 Convolutional Layer (Conv) 8 3.1.2 Activation Layer 9 3.1.3 Max Pooling Layer 10 3.1.4 Fully-Connected Layer 11 3.1.5 Dropout Layer 11 3.2 VGG Network 12 3.2.1 VGG16 Architecture 13 3.2.2 Proposed VGG-Lite Architecture 13 3.3 Transfer Learning (Fine-Tuning) 16 3.4 Training Details 17 Chapter 4 Experiment Results and Discussions 19 4.1 Experiment Environment 20 4.2 Statistical Analysis 20 4.3 Results 21 4.3.1 Architecture Depth 21 4.3.2 Training Time 24 4.3.3 Comparison to Conventional Texture Analysis 25 4.3.4 Training on the Whole Dataset with Transfer Learning 28 4.3.5 Training on Small Dataset with Transfer Learning 31 4.4 Discussions 33 Chapter 5 Conclusions and Future Works 36 References 38 | |
| dc.language.iso | en | |
| dc.subject | 卷積神經網絡 | zh_TW |
| dc.subject | 乳癌 | zh_TW |
| dc.subject | 乳房超音波影像 | zh_TW |
| dc.subject | 電腦輔助診斷 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | Computer-aided diagnosis | en |
| dc.subject | Convolutional neural network | en |
| dc.subject | Deep learning | en |
| dc.subject | Breast cancer | en |
| dc.subject | Breast ultrasound | en |
| dc.title | 深度學習應用於乳房超音波影像之電腦輔助診斷 | zh_TW |
| dc.title | Breast Ultrasound Computer-Aided Diagnosis based on Convolutional Neural Network | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 105-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李百祺,羅崇銘 | |
| dc.subject.keyword | 乳癌,乳房超音波影像,電腦輔助診斷,深度學習,卷積神經網絡, | zh_TW |
| dc.subject.keyword | Breast cancer,Breast ultrasound,Computer-aided diagnosis,Deep learning,Convolutional neural network, | en |
| dc.relation.page | 40 | |
| dc.identifier.doi | 10.6342/NTU201703617 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2017-08-17 | |
| 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 | |
|---|---|---|---|
| ntu-106-1.pdf 未授權公開取用 | 1.52 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。