請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/63071完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 王偉仲(Weichung Wang) | |
| dc.contributor.author | Yuyuan Yuan | en |
| dc.contributor.author | 袁佑緣 | zh_TW |
| dc.date.accessioned | 2021-06-16T16:21:19Z | - |
| dc.date.available | 2021-02-22 | |
| dc.date.copyright | 2021-02-22 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-02-04 | |
| dc.identifier.citation | [1] ABCs: Anatomical brain barriers to cancer spread: Segmentation from ct and mr images, miccai 2020. https://abcs.mgh.harvard.edu/. [2] PDDCA: A public domain database for computational anatomy. https://www. imagenglab.com/newsite/pddca/. [3] M. Arjovsky, S. Chintala, and L. Bottou. Wasserstein generative adversarial net works. In International conference on machine learning, pages 214–223. PMLR, 2017. [4] C. Chen, Q. Dou, H. Chen, J. Qin, and P.A. Heng. Synergistic image and feature adaptation: Towards crossmodality domain adaptation for medical image segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 865–872, 2019. [5] Q. Dou, C. Ouyang, C. Chen, H. Chen, and P.A. Heng. Unsupervised crossmodality domain adaptation of convnets for biomedical image segmentations with adversarial loss. arXiv preprint arXiv:1804.10916, 2018. [6] M. Drozdzal, E. Vorontsov, G. Chartrand, S. Kadoury, and C. Pal. The importance of skip connections in biomedical image segmentation. In Deep learning and data [7] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marc hand, and V. Lempitsky. Domainadversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016. [8] I. J. Goodfellow, J. PougetAbadie, M. Mirza, B. Xu, D. WardeFarley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial networks. arXiv preprint arXiv:1406.2661, 2014. [9] Z. Guo, X. Li, H. Huang, N. Guo, and Q. Li. Medical image segmentation based on multimodal convolutional neural network: Study on image fusion schemes. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 903–907. IEEE, 2018. [10] W.C. Hung, Y.H. Tsai, Y.T. Liou, Y.Y. Lin, and M.H. Yang. Adversarial learning for semisupervised semantic segmentation. arXiv preprint arXiv:1802.07934, 2018. [11] B. Ibragimov and L. Xing. Segmentation of organsatrisks in head and neck ct images using convolutional neural networks. Medical physics, 44(2):547–557, 2017. [12] D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. [13] M. Long, Y. Cao, J. Wang, and M. Jordan. Learning transferable features with deep adaptation networks. In International conference on machine learning, pages 97– 105. PMLR, 2015. [14] F. Milletari, N. Navab, and S.A. Ahmadi. Vnet: Fully convolutional neural net works for volumetric medical image segmentation. In 2016 fourth international [15] S. Nikolov, S. Blackwell, R. Mendes, J. De Fauw, C. Meyer, C. Hughes, H. Askham, B. RomeraParedes, A. Karthikesalingam, C. Chu, et al. Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy. arXiv preprint arXiv:1809.04430, 2018. [16] F. PérezGarcía, R. Sparks, and S. Ourselin. Torchio: a python library for efficient loading, preprocessing, augmentation and patchbased sampling of medical images in deep learning. arXiv preprint arXiv:2003.04696, 2020. [17] P. F. Raudaschl, P. Zaffino, G. C. Sharp, M. F. Spadea, A. Chen, B. M. Dawant, T. Albrecht, T. Gass, C. Langguth, M. Lüthi, et al. Evaluation of segmentation methods on head and neck ct: autosegmentation challenge 2015. Medical physics, 44(5):2020–2036, 2017. [18] X. Ren, L. Xiang, D. Nie, Y. Shao, H. Zhang, D. Shen, and Q. Wang. Interleaved 3dcnns for joint segmentation of smallvolume structures in head and neck ct images. Medical physics, 45(5):2063–2075, 2018. [19] O. Ronneberger, P. Fischer, and T. Brox. Unet: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computerassisted intervention, pages 234–241. Springer, 2015. [20] R. L. Siegel, K. D. Miller, and A. Jemal. Cancer statistics, 2016. CA: a cancer journal for clinicians, 66(1):7–30, 2016. [21] A. L. Simpson, M. Antonelli, S. Bakas, M. Bilello, K. Farahani, B. Van Ginneken, A. KoppSchneider, B. A. Landman, G. Litjens, B. Menze, et al. A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv preprint arXiv:1902.09063, 2019. [22] N. Tong, S. Gou, S. Yang, D. Ruan, and K. Sheng. Fully automatic multiorgan segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks. Medical physics, 45(10):4558–4567, 2018. [23] E. Tzeng, J. Hoffman, K. Saenko, and T. Darrell. Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7167–7176, 2017. [24] M. Wang and W. Deng. Deep visual domain adaptation: A survey. Neurocomputing, 312:135–153, 2018. [25] Y. Wang, L. Zhao, M. Wang, and Z. Song. Organ at risk segmentation in head and neck ct images using a twostage segmentation framework based on 3d unet. IEEE Access, 7:144591–144602, 2019. [26] Q. Yu, D. Yang, H. Roth, Y. Bai, Y. Zhang, A. L. Yuille, and D. Xu. C2fnas: Coarsetofine neural architecture search for 3d medical image segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4126–4135, 2020. [27] J.Y. Zhu, T. Park, P. Isola, and A. A. Efros. Unpaired imagetoimage translation using cycleconsistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017. [28] W. Zhu, Y. Huang, L. Zeng, X. Chen, Y. Liu, Z. Qian, N. Du, W. Fan, and X. Xie. Anatomynet: Deep learning for fast and fully automated wholevolume segmentation of head and neck anatomy. Medical physics, 46(2):576–589, 2019. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/63071 | - |
| dc.description.abstract | 對於放射線治療來說，自動化的腦結構分割是至關重要，因為人工去畫輪廓不只需要專業的解剖知識，整個流程也非常耗時。我們在本研究用兩階段訓練來開發多模態學影像上的多結構分割。我們所提出的模型可以一次分割多達15種腦部結構。此外，我們也在 MICCAI 2020 ABCs 競賽中做一系列的分析來驗證所提出的兩階段訓練與多模態多結構分割的效果。 另一方面，即便深度學習的模型可以稀少的醫學影像資料集上拿到亮眼的表現，應用到外部測試集時常常會有表現上的落差。於是我們研究了不同種基於特徵來做的領域適方法以解決跨不同機構資料集上的領域差異。我們的方法利用了目標域的影像並達到接近使用目標域真實標注來做訓練的表現。此外，因為在額外無標注資料集上使用領域適應，來源域上的表現也獲得到了提昇。 | zh_TW |
| dc.description.abstract | Automatically segmenting brain structures is important for radiation therapy since manual delineation requires anatomical knowledge and the procedure is time-consuming. We develop a model for multi-structure segmentation on multi-modal images with two-stage training. Our proposed model can segment up to 15 brain structures. We evaluate the performance on the MICCAI 2020 ABCs Challenge with a comprehensive ablation study to show the efficacy of two-stage training and multi-structure segmentation on multi-modality. On the other hand, although deep learning models have achieved outstanding performance on rare medical image dataset, models often suffer from the performance drop on the external testing dataset. We study various feature-based unsupervised domain adaptation methods to address the domain shift while crossing datasets from different institutions. Our method leverages the image information from the target domain and achieves a result close to the one trained by target domain ground truth. Furthermore, we also raise up the performance on the source domain with the help of domain adaptation on an additional unlabeled dataset. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T16:21:19Z (GMT). No. of bitstreams: 1 U0001-0302202102130500.pdf: 2836035 bytes, checksum: efd0355cf211f10fb478ebea83ff3c5d (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 誌謝 3 摘要 5 Abstract 7 Contents 9 List of Figures 13 List of Tables 17 I EndtoEnd MultiModal Segmentation on Large and Small Brain Structures With CNNs Using TwoStage Training for the Brain Radiotherapy Treatment Planning 1 Chapter 1 Introduction 3 1.1 Medical Image Segmentation . . . . . . . . . . . . . . . . . . . . . 3 1.2 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 Chapter 2 Materials and Methods 7 2.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3 Performance Evaluation . . . . . . . . . . . . . . . . . . . . . . . . 10 2.4 Modeling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.4.1 Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.4.2 Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.5 Network Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.6 Data Pipeline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.7 Training Strategy . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 2.7.1 Strategy I: Sampling only . . . . . . . . . . . . . . . . . . . . . . . 17 2.7.2 Strategy II: Sampling and then sliding Window . . . . . . . . . . . 18 2.7.3 Strategy III: Sampling and then random Sampling . . . . . . . . . . 18 Chapter 3 Results and Discussion 21 3.1 Effect of Multistage Training . . . . . . . . . . . . . . . . . . . . . 21 3.2 Multimodality Comparison . . . . . . . . . . . . . . . . . . . . . . 24 3.3 Efficacy of Multitask Joint Segmentation . . . . . . . . . . . . . . . 24 3.4 Comparison of MultiStructure Joint Segmentation . . . . . . . . . . 25 3.5 Boost the performance with ensemble modeling . . . . . . . . . . . . 27 3.6 Segmentation Results . . . . . . . . . . . . . . . . . . . . . . . . . . 27 Chapter 4 Conclusion 29 II Crossing Multisite Dataset Head and Neck MultiOrgan Segmentation Using Domain Adaptation with MultiLayer Feature Alignment on 3D UNet. 31 Chapter 5 Introduction 33 5.1 Problem of Domain Shift . . . . . . . . . . . . . . . . . . . . . . . . 33 5.2 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 Chapter 6 Materials and Methods 37 6.1 Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 6.2 Performance Evaluation . . . . . . . . . . . . . . . . . . . . . . . . 39 6.3 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 6.4 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 6.5 Adaptation Method . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 6.5.1 DANN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 6.5.2 ADDA . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 6.5.3 AE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 6.6 Position of Feature Alignment . . . . . . . . . . . . . . . . . . . . . 46 Chapter 7 Results and Discussion 49 7.1 Ablation Study on Adaptation Method . . . . . . . . . . . . . . . . . 49 7.2 Ablation Study on Feature Alignment Position . . . . . . . . . . . . 51 7.3 Ablation Study on Training Strategy . . . . . . . . . . . . . . . . . . 52 7.4 Comparison of Learning Curves on Source and Target Domains . . . 53 7.5 Efficacy of Domain Adaptation . . . . . . . . . . . . . . . . . . . . 53 7.6 Recall Rate Analysis on Optic Chiasm . . . . . . . . . . . . . . . . . 56 7.7 Domain Adaptation Crossing Multiple Datasets . . . . . . . . . . . . 58 Chapter 8 Conclusion 61 References 63 | |
| dc.language.iso | en | |
| dc.title | 在多模態腦部影像分割上研究兩階段訓練模型與跨資料集間之領域適應 | zh_TW |
| dc.title | Multi-Modal Segmentation for Brain Structure Images with Two-Stage Training and Multi-Site Domain Adaptation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 109-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 崔茂培(Mao-Pei Tsui),陳宜良(I-Liang Chern) | |
| dc.subject.keyword | 醫學影像,多器官分割,領域適應,兩階段訓練, | zh_TW |
| dc.subject.keyword | Medical image,multi-organ segmentation,domain adaptation,two-stage training, | en |
| dc.relation.page | 66 | |
| dc.identifier.doi | 10.6342/NTU202100426 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2021-02-05 | |
| dc.contributor.author-college | 理學院 | zh_TW |
| dc.contributor.author-dept | 應用數學科學研究所 | zh_TW |
| 顯示於系所單位： | 應用數學科學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0302202102130500.pdf 目前未授權公開取用 | 2.77 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。