請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/20731
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳中平(Chung-Ping Chen) | |
dc.contributor.author | Hong-Jhu Tsai | en |
dc.contributor.author | 蔡宏竹 | zh_TW |
dc.date.accessioned | 2021-06-08T03:00:47Z | - |
dc.date.copyright | 2021-02-26 | |
dc.date.issued | 2021 | |
dc.date.submitted | 2021-02-18 | |
dc.identifier.citation | [1] 'Ultrasound Equipment Market Size, Share and Industry Analysis.' Fortune Business Insights. https://www.fortunebusinessinsights.com/industry-reports/ultrasound-equipment-market-100515 (accessed Oct. 23, 2020). [2] 'Handheld portable ultrasound machine.' Butterfly Network. https://www.butterflynetwork.com/ (accessed Oct. 23, 2020). [3] T.-G. Wang, W.-S. Chen, Y.-C. Wang, C.-H. Wu, M.-Y. Hsiao, and K.-V. Chang, Musculoskeletal Ultrasound Examination. Taipei, Taiwan: Leader Book, 2014. [4] 'Arteries and Nerves of Upper Limb: Anterior View Anatomy.' pediagenosis.com. https://www.pediagenosis.com/2019/09/arteries-and-nerves-of-upper-limb.html (accessed Sept. 24, 2020). [5] S. Liu et al., 'Deep Learning in Medical Ultrasound Analysis: A Review,' Engineering, vol. 5, no. 2, pp. 261-275, Apr. 2019, doi: 10.1016/j.eng.2018.11.020. [6] R. Girshick, J. Donahue, T. Darrell, and J. Malik, 'Region-Based Convolutional Networks for Accurate Object Detection and Segmentation,' IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, no. 1, pp. 142-158, Jan. 2016, doi: 10.1109/TPAMI.2015.2437384. [7] R. Girshick, 'Fast R-CNN,' in 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, Dec. 7-13 2015, pp. 1440-1448, doi: 10.1109/ICCV.2015.169. [8] S. Ren, K. He, R. Girshick, and J. Sun, 'Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,' IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 6, pp. 1137-1149, June 2017, doi: 10.1109/TPAMI.2016.2577031. [9] W. Liu et al., 'SSD: Single Shot MultiBox Detector,' 2015, arXiv:1512.02325. [10] C.-Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg, 'DSSD : Deconvolutional Single Shot Detector,' 2017, arXiv:1701.06659. [11] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, 'You Only Look Once: Unified, Real-Time Object Detection,' in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 27-30 2016, pp. 779-788, doi: 10.1109/CVPR.2016.91. [12] J. Redmon and A. Farhadi, 'YOLO9000: Better, Faster, Stronger,' in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, July 21-26 2017, pp. 6517-6525, doi: 10.1109/CVPR.2017.690. [13] J. Redmon and A. Farhadi, 'YOLOv3: An Incremental Improvement,' 2018, arXiv:1804.02767. [14] T.-Y. Lin et al., 'Microsoft COCO: Common Objects in Context,' in European Conference on Computer Vision (ECCV), Zurich, Switzerland, Sept. 6-12 2014, vol. 8693: Springer, pp. 740-755. [15] H. D. Cheng and X. J. Shi, 'A simple and effective histogram equalization approach to image enhancement,' Digital Signal Processing, vol. 14, no. 2, pp. 158-170, Mar. 2004, doi: 10.1016/j.dsp.2003.07.002. [16] C. R. Nithyananda, A. C. Ramachandra, and Preethi, 'Survey on Histogram Equalization method based Image Enhancement techniques,' in 2016 International Conference on Data Mining and Advanced Computing (SAPIENCE), Ernakulam, India, Mar. 16-18 2016, pp. 150-158, doi: 10.1109/SAPIENCE.2016.7684156. [17] X. Wu, X. Liu, K. Hiramatsu, and K. Kashino, 'Contrast-accumulated histogram equalization for image enhancement,' in 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, Sept. 17-20 2017, pp. 3190-3194, doi: 10.1109/ICIP.2017.8296871. [18] L. Zhuang and Y. Guan, 'Image Enhancement via Subimage Histogram Equalization Based on Mean and Variance,' Computational Intelligence and Neuroscience, vol. 2017, p. 6029892, Dec. 2017, doi: 10.1155/2017/6029892. [19] O. V. Michailovich and A. Tannenbaum, 'Despeckling of medical ultrasound images,' IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 53, no. 1, pp. 64-78, Jan. 2006, doi: 10.1109/TUFFC.2006.1588392. [20] Y. Yue, M. M. Croitoru, A. Bidani, J. B. Zwischenberger, and J. W. Clark, 'Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images,' IEEE Transactions on Medical Imaging (T-MI), vol. 25, no. 3, pp. 297-311, Mar. 2006, doi: 10.1109/TMI.2005.862737. [21] H. Lazrag and M. S. Naceur, 'Despeckling of Intravascular Ultrasound images using curvelet transform,' in 2012 6th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), Sousse, Tunisia, Mar. 21-24 2012, pp. 365-369, doi: 10.1109/SETIT.2012.6481942. [22] S. Wu, Q. Zhu, and Y. Xie, 'Evaluation of various speckle reduction filters on medical ultrasound images,' in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, July 3-7 2013, pp. 1148-1151, doi: 10.1109/EMBC.2013.6609709. [23] S. Gai, B. Zhang, C. Yang, and L. Yu, 'Speckle noise reduction in medical ultrasound image using monogenic wavelet and Laplace mixture distribution,' Digital Signal Processing, vol. 72, pp. 192-207, Jan. 2018, doi: 10.1016/j.dsp.2017.10.006. [24] H. Li, J. Gao, and D. C. Liu, 'Adaptive Edge Enhancement of the Ultrasound Image,' in Fourth International Conference on Image and Graphics (ICIG 2007), Chengdu, China, Aug. 22-24 2007, pp. 86-91, doi: 10.1109/ICIG.2007.47. [25] B. Wang and D. C. Liu, 'A Novel Edge Enhancement Method for Ultrasound Imaging,' in 2008 2nd International Conference on Bioinformatics and Biomedical Engineering, Shanghai, China, May 16-18 2008, pp. 2414-2417, doi: 10.1109/ICBBE.2008.936. [26] S. H. Contreras Ortiz, T. Chiu, and M. D. Fox, 'Ultrasound image enhancement: A review,' Biomedical Signal Processing and Control, vol. 7, no. 5, pp. 419-428, Sept. 2012, doi: 10.1016/j.bspc.2012.02.002. [27] J. Kang, J. Y. Lee, and Y. Yoo, 'A New Feature-Enhanced Speckle Reduction Method Based on Multiscale Analysis for Ultrasound B-Mode Imaging,' IEEE Transactions on Biomedical Engineering, vol. 63, no. 6, pp. 1178-1191, June 2016, doi: 10.1109/TBME.2015.2486042. [28] P. V. Sudeep et al., 'Speckle reduction in medical ultrasound images using an unbiased non-local means method,' Biomedical Signal Processing and Control, vol. 28, pp. 1-8, July 2016, doi: 10.1016/j.bspc.2016.03.001. [29] C. A. Duarte-Salazar, A. E. Castro-Ospina, M. A. Becerra, and E. Delgado-Trejos, 'Speckle Noise Reduction in Ultrasound Images for Improving the Metrological Evaluation of Biomedical Applications: An Overview,' IEEE Access, vol. 8, pp. 15983-15999, Jan. 2020, doi: 10.1109/ACCESS.2020.2967178. [30] C.-H. Wu et al., 'Sonographic Tracking of the Upper Limb Peripheral Nerves: A Pictorial Essay and Video Demonstration,' American Journal of Physical Medicine Rehabilitation, vol. 94, no. 9, pp. 740-747, Sept. 2015, doi: 10.1097/phm.0000000000000344. [31] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, 'Object Detection with Discriminatively Trained Part-Based Models,' IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 32, no. 9, pp. 1627-1645, Sept. 2010, doi: 10.1109/TPAMI.2009.167. [32] J. Yan, Z. Lei, L. Wen, and S. Z. Li, 'The Fastest Deformable Part Model for Object Detection,' in 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, June 23-28 2014, pp. 2497-2504, doi: 10.1109/CVPR.2014.320. [33] T. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, 'Focal Loss for Dense Object Detection,' in 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, Oct. 22-29 2017, pp. 2999-3007, doi: 10.1109/ICCV.2017.324. [34] E. Y. Li. 'Dive Really Deep into YOLO v3: A Beginner’s Guide.' Towards Data Science. https://towardsdatascience.com/dive-really-deep-into-yolo-v3-a-beginners-guide-9e3d2666280e (accessed Nov. 10, 2020). [35] Q. Zhang, J. Sang, W. Wu, B. Cai, Z. Wu, and H. Hu, 'An Image Splicing and Copy-Move Detection Method Based on Convolutional Neural Networks with Global Average Pooling,' in International Conference on Image and Graphics (ICIG), Beijing, China, Aug. 23-25 2019: Springer, pp. 255-265, doi: 10.1007/978-3-030-34113-8_22. [36] K. Simonyan and A. Zisserman, 'Very Deep Convolutional Networks for Large-Scale Image Recognition,' 2014, arXiv:1409.1556. [37] C. Szegedy et al., 'Going deeper with convolutions,' in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 7-12 2015, pp. 1-9, doi: 10.1109/CVPR.2015.7298594. [38] M. Lin, Q. Chen, and S. Yan, 'Network In Network,' 2013, arXiv:1312.4400. [39] K. He, X. Zhang, S. Ren, and J. Sun, 'Deep Residual Learning for Image Recognition,' in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, June 27-30 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90. [40] T. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, 'Feature Pyramid Networks for Object Detection,' in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, July 21-26 2017, pp. 936-944, doi: 10.1109/CVPR.2017.106. [41] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, 'The PASCAL Visual Object Classes (VOC) Challenge,' International Journal of Computer Vision (IJCV), vol. 88, no. 2, pp. 303-338, June 2010, doi: 10.1007/s11263-009-0275-4. [42] J. Hui. 'mAP (mean Average Precision) for Object Detection.' Medium. https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173 (accessed Nov. 21, 2020). [43] M. Everingham and J. Winn, 'The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Development Kit,' May, 2012. [44] M. Everingham, S. M. A. Eslami, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, 'The PASCAL Visual Object Classes Challenge: A Retrospective,' International Journal of Computer Vision (IJCV), vol. 111, no. 1, pp. 98-136, Jan. 2015, doi: 10.1007/s11263-014-0733-5. [45] T.-Y. Lin et al. 'Detection Evaluation Metrics.' Microsoft COCO. https://cocodataset.org/#detection-eval (accessed Nov. 21, 2020). [46] C.-H. Tseng. 'Python and OpenCV - Blurring.' chtseng.wordpress.com. https://chtseng.wordpress.com/2016/11/17/python-%E8%88%87-opencv-%E6%A8%A1%E7%B3%8A%E8%99%95%E7%90%86/ (accessed Jan. 5, 2021). [47] S. Ruder, 'An overview of gradient descent optimization algorithms,' 2016, arXiv:1609.04747. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/20731 | - |
dc.description.abstract | 醫學超音波檢查是現今非常普及且有效的診斷方式。肌肉骨骼超音波因為涉及身體的部位眾多,解剖結構複雜,且組織紋理多變,造成超音波影像辨識難度相當高。在有限的範例圖譜以及需要大量練習才能精熟的情況下,導致初學者面臨學習門檻過高的困境。因此有必要發展一套電腦輔助自動化超音波影像即時標註系統,將超音波影像中不同器官組織自動標示出來,即時呈現在螢幕上,以協助醫師檢查與診斷。本論文選擇正中神經作為主要偵測目標,以及使用目前性能強大的人工智慧深度學習來實現物體偵測技術。由於需要演算法可達到即時偵測的速度,本論文使用YOLOv3作為物體偵測演算法。為確保實驗的公平性與客觀性,實驗過程中使用不同的資料集分割方式與多重交叉驗證。為增加對特定應用領域的偵測效果,在研究方法中加入對影像額外的前處理與後處理。經實驗結果證實,後處理可有效增加偵測流暢度以及提升準確率。根據實驗數據顯示,本研究方法在平均情況下可以同時達到90%以上的準確率以及80以上的影格率。在使用解析度來調整速度與準確率之間的權衡下,準確率最高可達94.19%以及影格率最高可達87.6幀。本論文證實了使用深度學習應用於超音波物體偵測,可同時達到高準確率與即時的偵測速度。 | zh_TW |
dc.description.abstract | Medical ultrasound examination is a very popular and effective diagnostic method nowadays. Musculoskeletal ultrasound involves many parts of the body, complex anatomical structure, and variable tissue texture, which makes it very difficult to identify ultrasound images. With limited sample pictures and a lot of practice to be proficient, beginners face the dilemma of too high learning threshold. Therefore, it is necessary to develop a computer-aided real-time ultrasound image automatic annotation system to automatically label different organs and tissues in the ultrasound image and present it on the screen in real time to assist physicians in examination and diagnosis. This thesis chooses the median nerve as the main detection target, and uses the current powerful artificial intelligence deep learning to realize the object detection technology. Due to the need for the algorithm to achieve real-time detection speed, this thesis uses YOLOv3 as the object detection algorithm. To ensure the fairness and objectivity of the experiment, different dataset partitioning methods and multiple cross-validation were used during the experiment. In order to increase the detection effect for the specific application field, additional preprocessing and postprocessing of the image are added to the research methods. The experimental results have confirmed that postprocessing can effectively increase detection fluency and improve accuracy. According to experimental data, this research method can achieve an accuracy of more than 90% and a frame rate of more than 80 at the same time on average. Using resolution to adjust the tradeoff between speed and accuracy, the accuracy can reach up to 94.19% and the frame rate can reach up to 87.6 frames. This thesis proves that the use of deep learning in ultrasound object detection can achieve both high accuracy and real-time detection speed. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T03:00:47Z (GMT). No. of bitstreams: 1 U0001-1702202106335300.pdf: 12518191 bytes, checksum: 3fe403340b8c4eb1162a2e8b4ef31999 (MD5) Previous issue date: 2021 | en |
dc.description.tableofcontents | 口試委員會審定書 i 致謝 i 摘要 ii Abstract iii Table of Contents v List of Figures ix List of Tables xii Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation 4 1.3 Medical Ultrasound Object Detection 8 1.4 Ultrasound Image Characteristics 11 1.5 Median Nerve 12 Chapter 2 Literature Review 14 2.1 YOLO Object Detection Methods 14 2.1.1 YOLO 14 2.1.2 YOLO9000 21 2.1.3 YOLOv3 30 2.2 YOLO Related Methods 36 2.2.1 Anchor Boxes 36 2.2.2 Non-maximum Suppression 37 2.2.3 K-means Clustering 38 2.2.4 Global Average Pooling 39 2.2.5 VGG 40 2.2.6 GoogLeNet 40 2.2.7 ResNet 41 2.2.8 Feature Pyramid Network 42 Chapter 3 Datasets and Evaluation Metrics 44 3.1 Datasets Description 44 3.1.1 Data Collection 44 3.1.2 Data Labeling 47 3.2 Evaluation Metrics 50 3.2.1 Confusion Matrix 50 3.2.2 IoU 51 3.2.3 Precision 52 3.2.4 Recall 53 3.2.5 Mean Average Precision 55 Chapter 4 Research Methods 61 4.1 System Flow 61 4.2 Preprocessing 62 4.3 Data Augmentation 69 4.4 Postprocessing 69 4.5 Training Methods 71 4.6 YOLOv3 Algorithm 75 4.7 YOLOv3 Model Architecture 76 Chapter 5 Experimental Results and Discussion 79 5.1 Data Augmentation Results 79 5.1.1 Accuracy of Dataset Divided by Case 79 5.1.2 Accuracy of Dataset Divided by Video 81 5.1.3 Accuracy of Dataset Divided by Image 82 5.2 Preprocessing Results 84 5.2.1 Accuracy of Dataset Divided by Case 84 5.2.2 Accuracy of Dataset Divided by Video 86 5.2.3 Accuracy of Dataset Divided by Image 88 5.3 Postprocessing Results 89 5.3.1 Accuracy of Dataset Divided by Case 89 5.3.2 Accuracy of Dataset Divided by Video 91 5.3.3 Accuracy of Dataset Divided by Image 93 5.4 Speed-Accuracy Tradeoff Results 95 5.4.1 Speed of Network Resolution 320x320 95 5.4.2 Speed of Network Resolution 416x416 95 5.4.3 Speed of Network Resolution 512x512 96 5.4.4 Speed of Network Resolution 608x608 96 5.4.5 Speed-Accuracy Tradeoff 97 5.5 Comparison of Experimental Results 98 5.5.1 Accuracy Comparison of Different Partition Ways 98 5.5.2 Accuracy Comparison of Different Processing Methods 99 5.5.3 Speed Comparison of Different Resolutions 99 5.6 Accuracy Distributions of 5-Fold Cross-Validation 100 5.6.1 Accuracy Distribution of Cases - Test Fold1 100 5.6.2 Accuracy Distribution of Cases - Test Fold2 101 5.6.3 Accuracy Distribution of Cases - Test Fold3 101 5.6.4 Accuracy Distribution of Cases - Test Fold4 102 5.6.5 Accuracy Distribution of Cases - Test Fold5 102 5.7 Video Test Results 103 5.7.1 Best Case with Postprocessing 103 5.7.2 Worst Case with Postprocessing 104 5.7.3 Average Case with Postprocessing 104 5.8 Discussion 105 Chapter 6 Conclusion and Future Work 108 6.1 Conclusion 108 6.2 Future Work 109 References 111 | |
dc.language.iso | en | |
dc.title | 基於深度學習之動態超音波影像的電腦輔助正中神經即時偵測方法 | zh_TW |
dc.title | Computer-Aided Real-Time Median Nerve Detection in Dynamic Ultrasonography Using Deep Learning | en |
dc.type | Thesis | |
dc.date.schoolyear | 109-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳少傑(Sao-Jie Chen),陳文翔(Wen-Shiang Chen),方劭云(Shao-Yun Fang),吳爵宏(Chueh-Hung Wu) | |
dc.subject.keyword | 超音波影像,正中神經,影像辨識,深度學習,物體偵測,即時系統,卷積神經網路, | zh_TW |
dc.subject.keyword | ultrasound image,median nerve,image recognition,deep learning,object detection,real-time system,convolutional neural network, | en |
dc.relation.page | 115 | |
dc.identifier.doi | 10.6342/NTU202100713 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2021-02-19 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1702202106335300.pdf 目前未授權公開取用 | 12.22 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。