請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80710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 | Chang-Yun Chung | en |
| dc.contributor.author | 鍾長運 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:13:41Z | - |
| dc.date.available | 2021-11-04 | |
| dc.date.available | 2022-11-24T03:13:41Z | - |
| dc.date.copyright | 2021-11-04 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-10-22 | |
| 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,' CA: A Cancer Journal for Clinicians, vol. 71, no. 3, pp. 209-249, 2021, doi: 10.3322/caac.21660. [2] E. N. Bredtoft, H. H. Madsen, and T. R. Rasmussen, 'Stage I lung cancer patients with or without symptoms – are the patients different and should we treat them differently?,' Acta Oncologica, vol. 60, no. 9, pp. 1169-1174, 2021, doi: 10.1080/0284186X.2021.1931959. [3] C. Cainap, L. A. Pop, O. Balacescu, and S. S. Cainap, 'Early diagnosis and screening in lung cancer,' (in eng), Am J Cancer Res, vol. 10, no. 7, pp. 1993-2009, 2020. [4] Z. Wang et al., 'Mortality outcomes of low-dose computed tomography screening for lung cancer in urban China: a decision analysis and implications for practice,' Chinese Journal of Cancer, vol. 36, no. 1, p. 57, 2017, doi: 10.1186/s40880-017-0221-8. [5] A. Del Ciello, P. Franchi, A. Contegiacomo, G. Cicchetti, L. Bonomo, and A. R. Larici, 'Missed lung cancer: when, where, and why?,' (in eng), Diagn Interv Radiol, vol. 23, no. 2, pp. 118-126, Mar-Apr 2017, doi: 10.5152/dir.2016.16187. [6] D. Shen, G. Wu, and H.-I. Suk, 'Deep Learning in Medical Image Analysis,' Annual Review of Biomedical Engineering, vol. 19, no. 1, pp. 221-248, 2017, doi: 10.1146/annurev-bioeng-071516-044442. [7] G. Litjens et al., 'A survey on deep learning in medical image analysis,' Medical Image Analysis, vol. 42, pp. 60-88, 2017, doi: 10.1016/j.media.2017.07.005. [8] 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 (CVPR), 2016. [9] J. Ning, H. Zhao, L. Lan, P. Sun, and Y. Feng, 'A Computer-Aided Detection System for the Detection of Lung Nodules Based on 3D-ResNet,' Applied Sciences, vol. 9, no. 24, 2019, doi: 10.3390/app9245544. [10] J. Hu, L. Shen, and G. Sun, 'Squeeze-and-Excitation Networks,' 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. [11] L. Gong, S. Jiang, Z. Yang, G. Zhang, and L. Wang, 'Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks,' International Journal of Computer Assisted Radiology and Surgery, vol. 14, no. 11, pp. 1969-1979, 2019, doi: 10.1007/s11548-019-01979-1. [12] O. Ronneberger, P. Fischer, and T. Brox, 'U-Net: Convolutional Networks for Biomedical Image Segmentation,' Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 234–241-234–241, 2015. [13] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, 'YOLOv4: Optimal Speed and Accuracy of Object Detection,' arXiv preprint arXiv:2004.10934, 2020. [14] C.-Y. Wang, H.-Y. Mark Liao, Y.-H. Wu, P.-Y. Chen, J.-W. Hsieh, and I. H. Yeh, 'CSPNet: A New Backbone that can Enhance Learning Capability of CNN,' 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020. [15] H. Zhang et al., 'ResNeSt: Split-Attention Networks,' arXiv preprint arXiv:2004.08955, 2020. [16] M. Amrani, M. Hammad, F. Jiang, K. Wang, and A. Amrani, 'Very deep feature extraction and fusion for arrhythmias detection,' Neural Computing and Applications, vol. 30, no. 7, pp. 2047-2057, 2018, doi: 10.1007/s00521-018-3616-9. [17] L. Yu, H. Chen, Q. Dou, J. Qin, and P. Heng, 'Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks,' IEEE Transactions on Medical Imaging, vol. 36, no. 4, pp. 994-1004, 2017, doi: 10.1109/TMI.2016.2642839. [18] A. Srivastava et al., 'Deep Learning for Detecting Diseases in Gastrointestinal Biopsy Images,' in 2019 Systems and Information Engineering Design Symposium (SIEDS), 2019, doi: 10.1109/SIEDS.2019.8735619. [19] L. Yu, Y. Gao, J. Zhou, J. Zhang, and Q. Wu, 'Multi-layer Feature Aggregation for Deep Scene Parsing Models,' arXiv preprint arXiv:2011.02572, 2020. [20] N. O. Salscheider, 'FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings,' in 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 7848-7854, doi: 10.1109/ICPR48806.2021.9412930. [21] A. Fajar, R. Sarno, C. Fatichah, and A. Fahmi, 'Reconstructing and resizing 3D images from DICOM files,' Journal of King Saud University - Computer and Information Sciences, 2020, doi: 10.1016/j.jksuci.2020.12.004. [22] L. Cabaret, L. Lacassagne, and D. Etiemble, 'Distanceless label propagation: An efficient direct connected component labeling algorithm for GPUs,' in 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), 2017, doi: 10.1109/IPTA.2017.8310147. [23] Z. Huang, J. Wang, X. Fu, T. Yu, Y. Guo, and R. Wang, 'DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection,' Information Sciences, vol. 522, pp. 241-258, 2020, doi: 10.1016/j.ins.2020.02.067. [24] S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, 'Path Aggregation Network for Instance Segmentation,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [25] A. Benali Amjoud and M. Amrouch, 'Convolutional Neural Networks Backbones for Object Detection,' in International Conference on Image and Signal Processing, Cham, 2020: Springer International Publishing, pp. 282-289. [26] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, 'Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression,' in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [27] R. Takahashi, T. Matsubara, and K. Uehara, 'Data Augmentation Using Random Image Cropping and Patching for Deep CNNs,' IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 9, pp. 2917–2931-2917–2931, 2020, doi: 10.1109/tcsvt.2019.2935128. [28] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, 'Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression,' Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12993–13000-12993–13000, 2020, doi: 10.1609/aaai.v34i07.6999. [29] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, 'Focal Loss for Dense Object Detection,' 2017 IEEE International Conference on Computer Vision (ICCV), 2017, doi: 10.1109/iccv.2017.324. [30] I. Garali, M. Adel, S. Bourennane, and E. Guedj, 'Histogram-Based Features Selection and Volume of Interest Ranking for Brain PET Image Classification,' IEEE Journal of Translational Engineering in Health and Medicine, vol. 6, pp. 1-12, 2018, doi: 10.1109/JTEHM.2018.2796600. [31] K. J. Grimm, G. L. Mazza, and P. Davoudzadeh, 'Model Selection in Finite Mixture Models: A k-Fold Cross-Validation Approach,' Structural Equation Modeling: A Multidisciplinary Journal, vol. 24, no. 2, pp. 246-256, 2017, doi: 10.1080/10705511.2016.1250638. [32] Y. Gu et al., 'Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs,' Computers in Biology and Medicine, vol. 103, pp. 220-231, 2018, doi: 10.1016/j.compbiomed.2018.10.011. [33] Q.-Q. Zhou et al., 'Automatic detection and classification of rib fractures based on patients’ CT images and clinical information via convolutional neural network,' European Radiology, vol. 31, no. 6, pp. 3815-3825, 2021, doi: 10.1007/s00330-020-07418-z. [34] O. Kopuklu, N. Kose, A. Gunduz, and G. Rigoll, 'Resource Efficient 3D Convolutional Neural Networks,' 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019. [35] A. A. A. Setio et al., 'Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks,' IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1160-1169, 2016, doi: 10.1109/TMI.2016.2536809. [36] W. Rafael, R. Patrick, Z. Andre, and B. Thomas, 'Computer-aided lung nodule detection on high-resolution CT data,' in Proc.SPIE, 2002, vol. 4684. [37] W. C. Gillis, A. J. Gilbert, K. Pazdernik, and A. Erickson, 'A Partial-Volume Correction for Quantitative Spectral X-Ray Radiography,' IEEE Transactions on Nuclear Science, vol. 67, no. 11, pp. 2321-2328, 2020, doi: 10.1109/TNS.2020.3028009. [38] S. R. Prasad, C. Wittram, J.-A. Shepard, T. McLoud, and J. Rhea, 'Standard-Dose and 50%—Reduced-Dose Chest CT: Comparing the Effect on Image Quality,' American Journal of Roentgenology, vol. 179, no. 2, pp. 461-465, 2002, doi: 10.2214/ajr.179.2.1790461. [39] N. Karabulut, M. Törü, V. Gelebek, M. Gülsün, and M. O. Ariyürek, 'Comparison of low-dose and standard-dose helical CT in the evaluation of pulmonary nodules,' European Radiology, vol. 12, no. 11, pp. 2764-2769, 2002, doi: 10.1007/s00330-002-1368-4. [40] D. Wormanns, K. Ludwig, F. Beyer, W. Heindel, and S. Diederich, 'Detection of pulmonary nodules at multirow-detector CT: effectiveness of double reading to improve sensitivity at standard-dose and low-dose chest CT,' European Radiology, vol. 15, no. 1, pp. 14-22, 2005, doi: 10.1007/s00330-004-2527-6. [41] Y. Nagatani et al., 'Lung nodule detection performance in five observers on computed tomography (CT) with adaptive iterative dose reduction using three-dimensional processing (AIDR 3D) in a Japanese multicenter study: Comparison between ultra-low-dose CT and low-dose CT by receiver-operating characteristic analysis,' European Journal of Radiology, vol. 84, no. 7, pp. 1401-1412, 2015, doi: 10.1016/j.ejrad.2015.03.012. [42] D. Choi, A. Passos, C. J. Shallue, and G. E. Dahl, 'Faster Neural Network Training with Data Echoing,' arXiv preprint arXiv:1907.05550, 2019. [43] Z. Liu, M. Sun, T. Zhou, G. Huang, and T. Darrell, 'Rethinking the Value of Network Pruning,' arXiv preprint arXiv:1810.05270, 2018. [44] J. H. Cho and B. Hariharan, 'On the Efficacy of Knowledge Distillation,' in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019. [45] A. Newell and J. Deng, 'How Useful Is Self-Supervised Pretraining for Visual Tasks?,' in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80710 | - |
| dc.description.abstract | "肺癌已成為全球癌症死亡的主因，電腦斷層（computed tomography, CT）與低劑量電腦斷層（low-dose computed tomography, LDCT）是目前最常見的肺癌檢查方法。透過電腦斷層或低劑量電腦斷層，可以早期偵測到可能是癌症的可疑肺部結節，進而降低肺癌死亡率。然而，放射科醫生要在一大疊的電腦斷層切片中找出肺結節是一項非常耗時的工作，因此可以使用電腦輔助偵測（computer-aided detection）系統來幫助放射科醫生自動找出肺結節。最近，卷積神經網路（convolutional neural network, CNN）因其在醫學影像上有出色的特徵提取能力，而越來越常被用在電腦輔助偵測系統中。 因此，本研究提出了一個基於卷積神經網路的電腦輔助偵測系統以用於肺部結節偵測來減輕放射科醫師的工作量。這個系統包含了影像前處理、肺結節偵測與後處理三個部分。在影像前處理的部分，影像先被標準化並調整大小以配合我們模型的輸入格式。另外也切除了影像中肺部以外的背景區域以減少無謂的計算量。接著，前處理完的影像就送到我們提出的被稱作3-D CSP-SA-SSR-YOLOv4的模型以進行肺部結節偵測。這個模型是從YOLOv4修改而來，並加入了部分跨階段與分組注意力（cross stage partial and split attention, CSP-SA）模塊來抽取出有關肺結節的多樣特徵。另外也加入了我們所提出的空間語意重新校正（spatial-semantic recalibration, SSR）模塊來提升在不同空間尺度下的肺結節偵測能力。通過我們的模型會產生許多的肺結節偵測框，並在之後透過後處理來過濾掉重複的偵測框以獲得最終的偵測結果。在本研究中，使用了1.25毫米厚度的672張電腦斷層影像和94張低劑量電腦斷層影像來評估我們偵測系統的表現。另外也透過圖像模擬方法模擬出各種解析度的影像，來驗證我們系統在低解析度影像上的適應性。實驗結果顯示我們的系統在厚度為1.25毫米的影像上獲得了0.8057的競爭績效指標（competition performance matrix, CPM）分數。在厚度為2.5毫米與5.0毫米的影像上也分別獲得了0.7252與0.7025的競爭績效指標分數。這些結果指出我們的模型在各種解析度的電腦斷層或低劑量電腦斷層影像上都有良好的肺部結節偵測能力。" | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:13:41Z (GMT). No. of bitstreams: 1 U0001-1810202105303000.pdf: 1481875 bytes, checksum: 35d71d76be82558f3a70499916c8fe66 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 口試委員審定書 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 8 3.1 Data Preprocessing 10 3.2 Lung Nodule Detection 12 3.2.1. YOLOv4 14 3.2.2. CSP-SA block 16 3.2.3. SSR module 19 3.3 Post-processing 21 3.4 Model Training 21 3.4.1. Data Augmentation 22 3.4.2. Loss Function 23 3.4.3. Iterative Self-FP Reduction 24 Chapter 4 Experimental Results and Discussion 26 4.1 Evaluation 26 4.2 Experiment Results 27 4.2.1. Ablation Study on YOLOv4 28 4.2.2. Detection on different resolution CT images 31 4.2.3. Detection on CT and LDCT 32 4.3 Discussion 33 Chapter 5 Conclusion 41 Reference 42 | |
| dc.language.iso | en | |
| dc.subject | YOLOv4 | zh_TW |
| dc.subject | 肺部結節 | zh_TW |
| dc.subject | 電腦斷層 | zh_TW |
| dc.subject | 低劑量電腦斷層 | zh_TW |
| dc.subject | 電腦輔助偵測 | zh_TW |
| dc.subject | 通道注意力機制 | zh_TW |
| dc.subject | computed tomography | en |
| dc.subject | YOLOv4 | en |
| dc.subject | channel-wise attention | en |
| dc.subject | computer-aided detection | en |
| dc.subject | low-dose computed tomography | en |
| dc.subject | lung nodule | en |
| dc.title | 具分組注意力和自我偽陽性減少機制的三維YOLOv4應用於不同解析度的電腦斷層影像肺部結節偵測 | zh_TW |
| dc.title | 3-D YOLOv4 with Split-attention Mechanism and Self-FP Reduction for Different Resolution Lung Nodule Detection in CT Images | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳啟禎(Hsin-Tsai Liu),羅崇銘(Chih-Yang Tseng) | |
| dc.subject.keyword | 肺部結節,電腦斷層,低劑量電腦斷層,電腦輔助偵測,通道注意力機制,YOLOv4, | zh_TW |
| dc.subject.keyword | lung nodule,computed tomography,low-dose computed tomography,computer-aided detection,channel-wise attention,YOLOv4, | en |
| dc.relation.page | 46 | |
| dc.identifier.doi | 10.6342/NTU202103804 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-10-22 | |
| 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 | |
|---|---|---|---|
| U0001-1810202105303000.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 1.45 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。