請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82311
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 | Tzu-An Chen | en |
dc.contributor.author | 陳子安 | zh_TW |
dc.date.accessioned | 2022-11-25T07:29:05Z | - |
dc.date.available | 2023-07-30 | |
dc.date.copyright | 2021-11-09 | |
dc.date.issued | 2021 | |
dc.date.submitted | 2021-08-08 | |
dc.identifier.citation | [1] H. Sung et al., 'Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries,' (in eng), CA Cancer J Clin, vol. 71, no. 3, pp. 209-249, May 2021, doi: 10.3322/caac.21660. [2] T. National Lung Screening Trial Research et al., 'Reduced lung-cancer mortality with low-dose computed tomographic screening,' N Engl J Med, vol. 365, no. 5, pp. 395-409, Aug 4 2011, doi: 10.1056/NEJMoa1102873. [3] T. National Lung Screening Trial Research, 'Lung Cancer Incidence and Mortality with Extended Follow-up in the National Lung Screening Trial,' (in eng), J Thorac Oncol, vol. 14, no. 10, pp. 1732-1742, Oct 2019, doi: 10.1016/j.jtho.2019.05.044. [4] U. Pastorino et al., 'Prolonged lung cancer screening reduced 10-year mortality in the MILD trial: new confirmation of lung cancer screening efficacy,' (in eng), Ann Oncol, vol. 30, no. 7, pp. 1162-1169, Jul 1 2019, doi: 10.1093/annonc/mdz117. [5] H. J. de Koning et al., 'Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial,' (in eng), N Engl J Med, vol. 382, no. 6, pp. 503-513, Feb 6 2020, doi: 10.1056/NEJMoa1911793. [6] A. Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, 'Deep Learning for Computer Vision: A Brief Review,' (in eng), Comput Intell Neurosci, vol. 2018, p. 7068349, 2018, doi: 10.1155/2018/7068349. [7] L. Cai, J. Gao, and D. Zhao, 'A review of the application of deep learning in medical image classification and segmentation,' Annals of Translational Medicine, vol. 8, no. 11, 2020. [8] S. K. Zhou et al., 'A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises,' Proceedings of the IEEE, https://doi.org/10.1109/jproc.2021.3054390 vol. 109, no. 5, pp. 820–838-820–838, 2021. [9] C.-Y. W. Alexey Bochkovskiy, Hong-Yuan Mark Liao, 'YOLOv4: Optimal Speed and Accuracy of Object Detection,' Computer Vision and Pattern Recognition, 2020. [10] J. Hu, L. Shen, and G. Sun, 'Squeeze-and-Excitation Networks,' IEEE/CVF Conference on Computer Vision and Pattern Recognition, https://doi.org/10.1109/cvpr.2018.00745 2018. [11] S. Liu, D. Huang, and Y. Wang, 'Receptive Field Block Net for Accurate and Fast Object Detection,' Lecture Notes in Computer Science, https://doi.org/10.1007/978-3-030-01252-6_24 pp. 404–419-404–419, 2018. [12] Y. Wu et al., 'Rethinking Classification and Localization for Object Detection,' in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [13] A. A. A. Setio et al., 'Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge,' (in eng), Med Image Anal, vol. 42, pp. 1-13, Dec 2017, doi: 10.1016/j.media.2017.06.015. [14] S. G. Armato, 3rd et al., 'The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans,' Med Phys, vol. 38, no. 2, pp. 915-31, Feb 2011, doi: 10.1118/1.3528204. [15] R. C. González, R. Woods, and B. Masters, 'Digital Image Processing, Third Edition,' Journal of Biomedical Optics, vol. 14, pp. 029901-029901, 2009. [16] S. Ioffe and C. Szegedy, 'Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,' presented at the ICML, 2015. [17] D. Misra, 'Mish: A Self Regularized Non-Monotonic Neural Activation Function,' arXiv, 2019. [18] W. Luo, Y. Li, R. Urtasun, and R. Zemel, 'Understanding the Effective Receptive Field in Deep Convolutional Neural Networks,' in International Conference on Neural Information Processing Systems, 2016: Curran Associates Inc., pp. 4905–4913-4905–4913. [19] A. Vaswani et al., 'Attention is All You Need,' in International Conference on Neural Information Processing Systems, 2017: Curran Associates Inc., pp. 6000–6010-6000–6010. [20] V. Nair and G. E. Hinton, 'Rectified Linear Units Improve Restricted Boltzmann Machines,' in ICML, J. Fürnkranz and T. Joachims, Eds., 2010: Omnipress, pp. 807-814. [21] C. E. Nwankpa, W. Ijomah, A. Gachagan, and S. Marshall, 'Activation functions: comparison of trends in practice and research for deep learning,' in International Conference on Computational Sciences and Technology, 2021, pp. 124 – 133-124 – 133. [22] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, 'DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,' IEEE Transactions on Pattern Analysis and Machine Intelligence, https://doi.org/10.1109/tpami.2017.2699184 vol. 40, no. 4, pp. 834–848-834–848, 2018. [23] Y. Zhang and J. Schneider, 'Projection Penalties: Dimension Reduction without Loss,' in ICML, 2010. [24] J. Hosang, R. Benenson, and B. Schiele, 'Learning Non-maximum Suppression,' IEEE Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.org/10.1109/cvpr.2017.685 2017. [25] R. Girshick, 'Fast R-CNN,' IEEE International Conference on Computer Vision (ICCV), https://doi.org/10.1109/iccv.2015.169 2015. [26] X. Ying, 'An Overview of Overfitting and its Solutions,' Journal of Physics: Conference Series, vol. 1168, p. 022022, 2019, doi: 10.1088/1742-6596/1168/2/022022. [27] K. Sung and T. Poggio, 'Example-based learning for view-based human face detection,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 39-51, 1998, doi: 10.1109/34.655648. [28] K. Simonyan and A. Zisserman, 'Very Deep Convolutional Networks for Large-Scale Image Recognition,' in International Conference on Learning Representations, Y. Bengio and Y. LeCun, Eds., 2015. [29] J. Zhuang et al., 'AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients,' in Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin, Eds., 2020, vol. 33: Curran Associates, Inc., pp. 18795–18806-18795–18806. [30] I. Loshchilov and F. Hutter, 'SGDR: Stochastic Gradient Descent with Warm Restarts,' presented at the ICLR, 2017. [31] A. Sylvain and C. Alain, 'A survey of cross-validation procedures for model selection,' Statistics Surveys, vol. 4, no. none, pp. 40-79, 1/1 2010, doi: 10.1214/09-SS054. [32] M. Niemeijer, M. Loog, M. D. Abramoff, M. A. Viergever, M. Prokop, and B. van Ginneken, 'On combining computer-aided detection systems,' IEEE transactions on medical imaging, vol. 30, pp. 215-23, 2011. [33] D. P. Chakraborty, 'Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data,' Medical physics, vol. 16, pp. 561-8, 1989. [34] Y. Li and Y. Fan, 'DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection,' in IEEE International Symposium on Biomedical Imaging (ISBI), 2020, pp. 1866-1869. [35] T. Song et al., 'CPM-Net: A 3D Center-Points Matching Network for Pulmonary Nodule Detection in CT Scans,' in Medical Image Computing and Computer Assisted Intervention (MICCAI), Cham, A. L. Martel et al., Eds., 2020: Springer International Publishing, pp. 550-559. [36] J. Mei, M. M. Cheng, G. Xu, L. R. Wan, and H. Zhang, 'SANet: A Slice-Aware Network for Pulmonary Nodule Detection,' IEEE Trans Pattern Anal Mach Intell, vol. PP, Mar 9 2021, doi: 10.1109/TPAMI.2021.3065086. [37] B. Wang, G. Qi, S. Tang, L. Zhang, L. Deng, and Y. Zhang, 'Automated Pulmonary Nodule Detection: High Sensitivity with Few Candidates,' in Medical Image Computing and Computer Assisted Intervention, Cham, A. F. Frangi, J. A. Schnabel, C. Davatzikos, C. Alberola-López, and G. Fichtinger, Eds., 2018: Springer International Publishing, pp. 759-767. [38] J. Ding, A. Li, Z. Hu, and L. Wang, 'Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks,' Lecture Notes in Computer Science, https://doi.org/10.1007/978-3-319-66179-7_64 pp. 559–567-559–567, 2017. [39] N. Khosravan and U. Bagci, 'S4ND: Single-Shot Single-Scale Lung Nodule Detection,' Lecture Notes in Computer Science, https://doi.org/10.1007/978-3-030-00934-2_88 pp. 794–802-794–802, 2018. [40] T.-Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, and S. Belongie, 'Feature Pyramid Networks for Object Detection,' IEEE Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.org/10.1109/cvpr.2017.106 2017. [41] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, 'Densely Connected Convolutional Networks,' IEEE Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.org/10.1109/cvpr.2017.243 2017. [42] D. Blalock, J. J. G. Ortiz, J. Frankle, and J. Guttag, 'What is the State of Neural Network Pruning?,' in Machine Learning and Systems, 2020. [43] G. Hinton, O. Vinyals, and J. Dean, 'Distilling the Knowledge in a Neural Network,' in NIPS Deep Learning and Representation Learning Workshop, 2015. [44] M. Wistuba, A. Rawat, and T. Pedapati, 'A Survey on Neural Architecture Search,' presented at the arXiv, 2019. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82311 | - |
dc.description.abstract | "低顯影劑量電腦斷層掃描造影 (Low-dose Computed Tomography, LDCT) 技術被廣泛應用於肺癌初期的結節偵測,以提高病患的存活率。然而,觀察數百張的LDCT影像及每張掃描影像內部的小型結節非常耗時。因此,電腦輔助偵測 (Computer-aided Detection, CADe) 系統被用於加速檢測流程及減輕放射科醫師的負擔。由於近年來深度學習技術於電腦視覺領域的成功發展,越來越多以卷積神經網路 (Convolutional Neural Network, CNN) 為基礎的CADe系統被應用於醫學使用上。 此研究提出了一以CNN為基礎的肺部結節偵測CADe系統,該系統包含了資料前處理、肺部結節偵測及初步結果後處理,共三個階段。在資料前處理的階段中,影像的間距被標準化為相同,並對去除肺部外區域後的影像進行了正規化處理,再將影像裁切為具有相同格式的數個部分。接著,經過前處理的影像會作為偵測模型的輸入,並由模型輸出一序列的候選結節及其位置、直徑大小。所提出的CNN偵測模型被取名為3-D Hyper Receptive Field and Dual Head YOLOv4 (3-D HD-YOLOv4) ,是修改自YOLOv4網路的架構。為了提升原YOLOv4所萃取特徵的代表性,加入了壓縮激勵 (Squeeze-and-excitation, SE) 模塊和感知域 (Receptive Field Block, RFB) 模塊。此外,雙頭 (Dual Head, D-head) 模塊和跨階平行分支 (cross stage parallel branch) 機制也被用於增強原YOLOv4的結節偵測能力。最後,在初步結果後處理的部分,對於相同結節的重複預測將會被去除。 根據實驗結果顯示,SE 和 RFB 模塊可以大幅降低誤報 (false positives, FPs) 的數量,以及D-head模塊和跨階平行分支機制可以大幅增加預測靈敏度 (Sensitivity)。除此之外,所提出的CADe系統在公開的資料集測試上獲得了0.911的競爭績效指標分數 (Competition Performance Metric, CPM),在誤報率 (FPs per Scan) 為8的靈敏度為0.982。相較於其他最新技術的系統,所提出的CADe系統展現了其優異的表現。整體結果指出,我們針對模型的改進可以大幅提升其對於結節的偵測能力,並達到目前最先進技術的表現。 " | zh_TW |
dc.description.provenance | Made available in DSpace on 2022-11-25T07:29:05Z (GMT). No. of bitstreams: 1 U0001-0508202118294600.pdf: 1551275 bytes, checksum: 14bee8955074a18f0736fd0c15b42ac8 (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 V Table of Contents VII List of Figures IX List of Tables XI Chapter 1 Introduction 1 Chapter 2 Materials 5 Chapter 3 Method 7 3.1 Data Preprocessing 9 3.2 Lung Nodule Detection 10 3.2.1 3-D YOLOv4 10 3.2.2 3-D HD-YOLOv4 13 3.2.2.1 SE-CSP Stage Block 14 3.2.2.2 Hyper Receptive Field 15 3.2.2.3 Dual Head and Cross Stage Parallel Branch 17 3.3 Initial Result Post-processing 20 3.4 Loss Function 21 3.5 Model Training 22 Chapter 4 Results and Discussion 24 4.1 Experiment Environment 24 4.2 Evaluation 24 4.3 Experiment Results 25 4.3.1 Ablation Study 25 4.3.2 Comparison with SOTA 27 4.4 Discussion 28 Chapter 5 Conclusions and Future Works 34 Reference 36 | |
dc.language.iso | en | |
dc.title | 3-D HD-YOLOv4: 三維超感知域雙分支預測YOLOv4於肺部電腦斷層掃描影像結節偵測 | zh_TW |
dc.title | 3-D HD-YOLOv4: 3-D Hyper Receptive Field and Dual Head YOLOv4 for Pulmonary Nodule Detection in Lung CT | en |
dc.date.schoolyear | 109-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 羅崇銘(Hsin-Tsai Liu),陳啓禎(Chih-Yang Tseng) | |
dc.subject.keyword | 低顯影劑量電腦斷層掃描,電腦輔助偵測系統,卷積神經網路,單階段物件偵測,YOLOv4, | zh_TW |
dc.subject.keyword | Low-dose computed tomography,Computer-aided detection system,Convolutional neural network,One-stage object detection,You Only Look Once version 4, | en |
dc.relation.page | 40 | |
dc.identifier.doi | 10.6342/NTU202102123 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2021-08-09 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
dc.date.embargo-lift | 2023-07-30 | - |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-0508202118294600.pdf | 1.51 MB | Adobe PDF | 檢視/開啟 |
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。