請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83045完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 郭柏齡(Po-Ling Kuo) | |
| dc.contributor.author | Cheng-Liang Yeh | en |
| dc.contributor.author | 葉政樑 | zh_TW |
| dc.date.accessioned | 2022-11-25T08:06:06Z | - |
| dc.date.copyright | 2022-02-21 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-02-10 | |
| dc.identifier.citation | [ 1 ] I Ibrahim, W.S Khan, N Goddard, P Smitham. “Carpal Tunnel Syndrome: A Review of the Recent Literature” Open Orthop. J. June, 2012. P.69-76. [ 2 ] Paget J. Lectures on surgical pathology. Philadelphia: Lindsay and Blakiston 1854 [ 3 ] Phalen, G.S. “The carpal-tunnel syndrome. Seventeen years’ experience in diagnosis and treatment of six hundred fifty-four hands.” The Journal of bone and joint surgery. 1966. 48, P.211-228 [ 4 ] Mauro Mondelli, Fabio Giannini, Mariano Giacchi. “Carpal tunnel syndrome incidence in a general population” Neurology. Jan., 2002. P.289-294. [ 5 ] American Academy of Orthopaedic Surgeons Work Group Panel. Clinical guidelines on diagnosis of carpal tunnel syndrome, 2007. [ 6 ] Rask M.R. “Anterior interosseous nerve entrapment: (Kiloh-Nevin syndrome) report of seven cases.” Clinical Orthopaedics and Related Research. Jul., 1979. 142:P.176-181. [ 7 ] Bruce A Perkins, David Olaleye, Vera Bril. “Carpal tunnel syndrome in patients with diabetic polyneuropathy” Diabetes Care. Mar., 2002. P.565-569. [ 8 ] Vilhjalmur Finsen, Heike Zeitlmann. “Carpal tunnel syndrome during pregnancy” Scandinavian Journal of Plastic and Reconstructive Surgery and Hand Surgery. Feb.,2006. P.41-45. [ 9 ] Yuichi Yoshii, Chunfeng Zhao and Peter C. Amadio. “Recent Advances in Ultrasound Diagnosis of Carpal Tunnel Syndrome” Diagnostics. August, 2020. [ 10 ] Joy C MacDermid, Tim Doherty. “Clinical and electrodiagnostic testing of carpal tunnel syndrome: a narrative review” J. Orthop. Sports Phys. Ther. Oct., 2004. P.565-588. [ 11 ] Cara McDonagh, Michael Alexander, David Kane. “The role of ultrasound in the diagnosis and management of carpal tunnel syndrome: a new paradigm” Rheumatology. January, 2015. 54, P.9-19 [ 12 ] F. S. Ferrari, L. Della Sala, S. Cozza, G. Guazzi, L. Belcapo, A. Mariottini, A. Bolognini, P. Stefani. “High-resolution ultrasonography in the study of carpal tunnel syndrome” Radiol Med. April, 1997. 93, P.336-341. [ 13 ] I. Duncan, P. Sullivan, F. Lomas. “Sonography in the diagnosis of carpal tunnel syndrome” American Journal of Roentgenology. 1999. 173, P.681-684. [ 14 ] Michael S. Cartwright, Lisa D. Hobson-Webb, Andrea J. Boon, Katharine E. Alter, Christopher H. Hunt, Victor H. Flores , Robert A. Werner, Steven J. Shook, T. Darrell Thomas, Scott J. Primack, Francis O. Walker. “Evidence-based guideline: Neuromuscular ultrasound for the diagnosis of carpal tunnel syndrome” Muscle Nerve. March, 2012. P.287-293 [ 15 ] Ken-Ichi Nakamichi, Shintaro Tachibana. “Ultrasonographic measurement of median nerve cross-sectional area in idiopathic carpal tunnel syndrome: Diagnostic accuracy” Muscle Nerve. October, 2002. P.798-803 [ 16 ] Santoshi Billakota, Lisa D.Hobson-Webb. “Standard median nerve ultrasound in carpal tunnel syndrome: A retrospective review of 1,021 cases” Clinical Neurophysiology Practice. 2017. p.188-191. [ 17 ] A.W.H. Ng, J.F. Griffith, R.K.L. Lee, W.L. Tse, C.W.Y. Wong, P.C. Ho. “Ultrasound carpal tunnel syndrome: additional criteria for diagnosis” Clinical Radiology. February, 2018. 214.E11-214.E18. [ 18 ] Yoshii Yuichi, Villarraga Hector R., Henderson Jacqueline, Zhao Chunfeng, An Kai-Nan, Amadio Peter C. “Ultrasound Assessment of the Displacement and Deformation of the Median Nerve in the Human Carpal Tunnel with Active Finger Motion” The Journal of bone and joint surgery. December, 2009. P.2922-2930. [ 19 ] Margriet H. M. van Doesburg, Jacqueline Henderson, Yuichi Yoshii, Aebele B. Mink van der Molen, Stephen S. Cha, Kai-Nan An, Peter C. Amadio. “Median nerve deformation in differential finger motions: Ultrasonographic comparison of carpal tunnel syndrome patients and healthy controls” Journal of Orthopaedic Research. September, 2011. P.643-648. [ 20 ] Yuichi Yoshii, Tomoo Ishii, Wen-Lin Tung, Shinsuke Sakai, Peter C. Amadio. “Median nerve deformation and displacement in the carpal tunnel during finger motion” Journal of Orthopaedic Research. August, 2013. P.1876-1880. [ 21 ] F. ROSENBLATT. “THE PERCEPTRON: A PROBABILISTIC MODEL FOR INFORMATION STORAGE AND ORGANIZATION IN THE BRAIN” Psychological Review. Jun., 1958. [ 22 ] J.R. QUINLAN. “Induction of Decision Trees” Machine Learning. 1986. P.81-106. [ 23 ] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt and B. Scholkopf, 'Support vector machines' IEEE Intelligent Systems and their Applications. July-Aug., 1998. P.18-28. [ 24 ] David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams. “Learning representations by back-propagating errors” Nature. Oct., 1986. P.533-536. [ 25 ] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel. “Backpropagation Applied to Handwritten Zip Code Recognition” Neural Computation. 1989. P.541-551. [ 26 ] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton. “ImageNet Classification with Deep Convolutional Neural Networks” 2012. [ 27 ] Karen Simonyan, Andrew Zisserman. “VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION” ICLR. 2015. [ 28 ] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. “Going Deeper with Convolutions” arXiv:1409.4842 [cs.CV] Sep., 2014. [ 29 ] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. “Deep Residual Learning for Image Recognition” arXiv:1512.03385 [cs.CV] Dec., 2015. [ 30 ] Paul Viola, Michael Jones. “Rapid Object Detection using a Boosted Cascade of Simple Features” Conference on COMPUTER VISION AND PATTERN RECOGNITION. 2001. [ 31 ] Navneet Dalal, Bill Triggs. “Histograms of Oriented Gradients for Human Detection” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005. P.886-893 [ 32 ] J. Canny. “A Computational Approach to Edge Detection” In IEEE Transactions on Pattern Analysis and Machine Intelligence. Nov., 1986. P.679-698. [ 33 ] N. Otsu. “A Threshold Selection Method from Gray-Level Histograms” In IEEE Transactions on Systems, Man, and Cybernetics. Jan., 1979. P.62-66. [ 34 ] Shengfeng Liu , Yi Wang, Xin Yang, Baiying Lei, Li Liu, Shawn Xiang Li, Dong Ni, Tianfu Wang. “Deep Learning in Medical Ultrasound Analysis: A Review” Engineering, Volume 5, Issue 2. 2019. P.261-275. [ 35 ] Olaf Ronneberger, Philipp Fischer, Thomas Brox. “U-Net: Convolutional Networks for Biomedical Image Segmentation” arXiv:1505.04597 [cs.CV] May, 2015. [ 36 ] Rafał Obuchowicz, Julia Kruszyn´ska, Michał Strzelecki. “Classifying median nerves in carpal tunnel syndrome: Ultrasound image analysis” Biocybernetics and Biomedical engineering. Mar., 2021. P.335-351. [ 37 ] Fariborz Faeghi, Ali Abbasian Ardakani, U Rajendra Acharya, Mohammad Mirza-Aghazadeh-Attari, Jamileh Abolghasemi, Sajjad Ejtehadifar, Afshin Mohammadi. “Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists’ assessment” Radiology. Jan., 2021. [ 38 ] Aerts, H., Velazquez, E., Leijenaar, R. et al. “Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach” Nat Commun 5, 4006 (2014). https://doi.org/10.1038/ncomms5006 [ 39 ] RAYMOND T. FESTEN, VERENA J.M.M. SCHRIER, PETER C. AMADIO. “AUTOMATED SEGMENTATION OF THE MEDIAN NERVE IN THE CARPAL TUNNEL USING U-NET” Ultrasound in Med. and Biol. 2021. P.1964-1969. [ 40] Ali Abbasian Ardakani, Ahmadreza Afshar, Shweta Bhatt, Nathalie J Bureaue, Aylin Tahmasebi, U Rajendra Acharya, Afshin Mohammadi. “Diagnosis of carpal tunnel syndrome: A comparative study of shear wave elastography, morphometry and artificial intelligence techniques” Pattern Recognition Letters 133 (2020) P.77-85. [ 41 ] MING-HUWI HORNG, CHENG-WEI YANG, YUNG-NIEN SUN, TAI-HUA YANG. “DEEPNERVE: A NEW CONVOLUTIONAL NEURAL NETWORK FOR THE LOCALIZATION AND SEGMENTATION OF THE MEDIAN NERVE IN ULTRASOUND IMAGE SEQUENCES” Ultrasound in Med. and Biol. 2020. P.2439-2452. [ 42 ] Anna Khoreva, Federico Perazzi, Rodrigo Benenson, Bernt Schiele, Alexander Sorkine-Hornung. “Learning Video Object Segmentation from Static Images” arXiv:1612.02646v1 [cs.CV] 8 Dec. 2016. [ 43 ] Has¸im Sak, Andrew Senior, Franc¸oise Beaufays. “Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling”. Google. [ 44 ] J. Dai, K. He, and J. Sun. “Convolutional feature masking for joint object and stuff segmentation” In CVPR. 2015. [ 45 ] B. Hariharan, P. Arbelaez, R. Girshick, J. Malik. “Simultaneous detection and segmentation” In ECCV. 2014. [ 46 ] B. Hariharan, P. Arbelaez, R. Girshick, J. Malik. “Hypercolumns for object segmentation and fine-grained localization” In CVPR. 2015. [ 47 ] Pedro O. Pinheiro, Ronan Collobert, Piotr Dollar. “Learning to Segment Object Candidates” arXiv:1506.06204v2 [cs.CV] 2015. [ 48 ] Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji, Yichen Wei. “Fully Convolutional Instance-aware Semantic Segmentation” arXiv:1611.07709v2 [cs.CV] 2016. [ 49 ] Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik. “Rich feature hierarchies for accurate object detection and semantic segmentation” arXiv:1311.2524v5 [cs.CV] 2014. [ 50 ] David G. Lowe. “Distinctive Image Features from Scale-Invariant Keypoints” International Journal of Computer Vision. 2004. [ 51 ] Navneet Dalal, Bill Triggs. “Histograms of Oriented Gradients for Human Detection” In CVPR. 2005. P.886-893. [ 52 ] J.R.R. Uijlings, K.E.A. van de Sande, T. Gevers, A.W.M. Smeulders. “Selective Search for Object Recognition” IJCV. 2012. [ 53 ] A. Neubeck, L. Van Gool. “Efficient Non-Maximum Suppression” 18th International Conference on Pattern Recognition (ICPR'06). 2006. P. 850-855 [ 54 ] Ross Girshick. “Fast R-CNN” arXiv:1504.08083v2 [cs.CV] 2015. [ 55 ] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition” arXiv:1406.4729v4 [cs.CV] 2015. [ 56 ] Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” arXiv:1506.01497v3 [cs.CV] 2016. [ 57 ] Jonathan Long, Evan Shelhamer, Trevor Darrell. “Fully Convolutional Networks for Semantic Segmentation” arXiv:1411.4038v2 [cs.CV] 2015. [ 58 ] Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick. “Mask R-CNN” arXiv:1703.06870v3 [cs.CV] 2018. [ 59 ] Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, Jiaya Jia. “Path Aggregation Network for Instance Segmentation” arXiv:1803.01534v4 [cs.CV] 2018. [ 60 ] Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang. “Mask Scoring R-CNN” arXiv:1903.00241v1 [cs.CV] 2019. [ 61 ] Xinlei Chen, Ross Girshick, Kaiming He, Piotr Dollár. “TensorMask: A Foundation for Dense Object Segmentation” arXiv:1903.12174v2 [cs.CV] 2019. [ 62 ] Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun. “Instance-sensitive Fully Convolutional Networks” arXiv:1603.08678v1 [cs.CV] 2016. [ 63 ] Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee. “YOLACT: Real-time Instance Segmentation” arXiv:1904.02689v2 [cs.CV] 2019. [ 64 ] Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei Li. “SOLO: Segmenting Objects by Locations” arXiv:1912.04488v3 [cs.CV] 2020. [ 65 ] Xinlong Wang, Rufeng Zhang, Tao Kong, Lei Li, Chunhua Shen. “SOLOv2: Dynamic and Fast Instance Segmentation” arXiv:2003.10152v3 [cs.CV] 2020. [ 66 ] Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie. “Feature Pyramid Networks for Object Detection” arXiv:1612.03144v2 [cs.CV] 2017. [ 67 ] Hao Chen, Kunyang Sun, Zhi Tian, Chunhua Shen, Yongming Huang, Youliang Yan. “BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation” arXiv:2001.00309v3 [cs.CV] 2020. [ 68 ] Rosanne Liu, Joel Lehman, Piero Molino, Felipe Petroski Such, Eric Frank, Alex Sergeev, Jason Yosinski. “An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution” arXiv:1807.03247v2 [cs.CV] 2018. [ 69 ] Navaneeth Bodla, Bharat Singh, Rama Chellappa, Larry S. Davis. ” Soft-NMS -- Improving Object Detection With One Line of Code” arXiv:1704.04503v2 [cs.CV] 2017. [ 70 ] Zhi Tian, Chunhua Shen, Hao Chen, Tong He. “FCOS: Fully Convolutional One-Stage Object Detection” arXiv:1904.01355v5 [cs.CV] 2019. [ 71 ] Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam. “Rethinking Atrous Convolution for Semantic Image Segmentation” arXiv:1706.05587v3 [cs.CV] 2017. [ 72 ] Hao Fu, Chunyuan Li, Xiaodong Liu, Jianfeng Gao, Asli Celikyilmaz, Lawrence Carin. “Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing” arXiv:1903.10145v3 [cs.LG] 2019. [ 73 ] Yuxin Wu, Alexander Kirillov, Francisco Massa, Wan-Yen Lo, Ross Girshick. “Detectron2” 2019. url{https://github.com/facebookresearch/detectron2}. [ 74 ] Tian, Zhi and Chen, Hao and Wang, Xinlong and Liu, Yuliang and Shen, Chunhua. “AdelaiDet: A Toolbox for Instance-level Recognition Tasks” 2019. url{https://git.io/adelaidet}. [ 75 ] Daniel Bolya and Chong Zhou and Fanyi Xiao and Yong Jae Lee. “YOLACT: Real-time Instance Segmentation” ICCV. 2019. url{https://github.com/dbolya/yolact}. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83045 | - |
| dc.description.abstract | 使用動態超音波影像診斷與評估腕隧道症候群是一種新趨勢。腕隧道症為正中神經在腕隧道處受到纏套，而在相鄰組織移動時表現出異常時空活動特徵。傳統上採用人工分割纏套正中神經的動態超音波連續影像需要耗費大量專業人力，因此阻礙了該方法在臨床診斷中普及。目前使用基於深度學習的模型自動分割與追蹤正中神經是一項吸引人的方法，有幾項研究已經使用深度學習相關方法在動態超音波影像中自動分割神經。但是由於深度學習模型訓練與推斷過程需要大量計算並且可能會有人工標註介入等問題，因此要應用在臨床場域中仍相當困難。在超音波造影的過程中同時進行神經分割，或是在造影與影像分割兩步驟間只有極短的時間延遲，將可使臨床醫師在收取影像時立即根據模型分割結果做出診斷，並且能夠在影像因過於模糊或是雜訊過多導致模型無法正確分割時立即決定重錄影像。因此在本論文中我提出了一項實例分割模型。該模型簡化近期公開之SOLOv2模型架構，目的在保有與我們先前研究模型同等分割精確度的前提下，加快其影像分割速度達到能夠配合臨床操作的水平。我們將提出的簡化模型稱為SOLOv2-1-MN。在其模型架構中為了加速推斷過程，我從減少計算複雜度方面著手。相比於原始SOLOv2提出的設計，我將網格單元數量減少至四分之一，並且在模型推斷時將輸入影像尺寸等比例縮小至原圖的75%。另外為了維持分割精確度，我們將特徵金字塔每個層級負責對應的實例都重新調整尺寸。接著我們將SOLOv2-1-MN與幾種目前最先進的實例分割模型進行比較，其中包含了Mask R-CNN、YOLACT (一種針對即時性實例分割的全卷積模型)和BlendMask (一種結合由上到下與從下而上兩種不同方法的實例分割模型)。此外我還提出了一項集成學習模型MixedMN，該模型使用集成學習策略結合了幾種先進的實例分割模型。我們比較其分割結果以測試使用集成學習是否能夠進一步提高分割精確度。在結果中顯示MixedMN以IoU分數0.8655和Dice係數0.9279達到模型最佳分割準確度。在模型推斷速度方面，SOLOv2-1-MN以每秒28.9幀運行。其IoU分數為0.8546、Dice係數為0.9216，其在提升推理速度的同時保有與原始SOLOv2模型架構同等的分割精確度。最後我們還使用上述模型分割正中神經影像與進行形態學參數分析，展示此種方法的可行性。總結來說，我提出了一種基於SOLOv2的輕量化模型架構SOLOv2-1-MN，其能夠對於動態超音波正中神經影像進行即時性實例分割。另外我還利用了集成學習策略結合了幾種最先進的實例分割模型，最終提高了分割精確度。我們認為本研究極具有被應用於臨床診斷場域的潛力，其能夠幫助臨床醫師以最少的勞動成本完成對於腕隧道症即時性診斷與客觀評估。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-25T08:06:06Z (GMT). No. of bitstreams: 1 U0001-0602202222592700.pdf: 4564253 bytes, checksum: 750fd08faeafed82bf529939b4e4ab7f (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | "目錄: 口試委員會審定書 i 誌謝 ii 摘要 iii Abstract iv 圖目錄 x 表目錄 xii 第一章、緒論 1 1-1研究背景與目標 1 1-1-1研究背景 1 1-1-1-1 醫學研究領域 1 1-1-1-1-1 超音波靜態橫截面影像 3 1-1-1-1-2 超音波動態影像 4 1-1-1-2 電腦視覺與深度學習領域 5 1-1-2研究目標 9 1-2 相關文獻回顧 10 1-2-1 前言 10 1-2-2 應用機器學習或深度學習於正中神經超音波影像的相關研究 11 1-2-3 深度學習領域中影像分割技術發展 13 1-2-3-1 前言 13 1-2-3-2 Top-down instance segmentation 14 1-2-3-2-1 R-CNN 14 1-2-3-2-2 Fast R-CNN 15 1-2-3-2-3 Faster R-CNN 17 1-2-3-2-4 Mask R-CNN 19 1-2-3-2-5 在R-CNN系列之後的新模型架構 20 1-2-3-3 Bottom-up instance segmentation 21 第二章、研究資料與模型建立 22 2-1 研究資料 22 2-1-1 資料蒐集 22 2-1-2 資料標註 23 2-1-3 資料分群 28 2-1-4 資料前處理與資料集擴增 29 2-2 模型建立 30 2-2-1 引言 30 2-2-2 Mask R-CNN 31 2-2-3 YOLACT 32 2-2-4 SOLOv1, SOLOv2 34 2-2-5 BlendMask 38 2-2-6 MixedMN 39 2-2-7 SOLOv2-1-MN 43 第三章、結果 46 3-1 模型訓練計畫與訓練結果評估參數 46 3-1-1 前言 46 3-1-2 通用訓練計畫 46 3-1-3 訓練結果評估參數 47 3-2 模型訓練結果 50 3-3 模型應用結果與分析 53 3-3-1 前言 53 3-3-2 臨床醫學參數 53 3-3-3 參數分析結果 54 3-3-3-1 前言 54 3-3-3-2 正常受試者手掌Active、Passive活動正中神經影像參數分析 55 3-3-3-3 CTS患者施打藥物前後正中神經影像參數分析 57 3-3-3-4 所有CTS患者施打藥物前正中神經影像參數分析 59 第四章、討論 60 4-1 模型訓練討論 60 4-1-1 CNN Bone Model: 60 4-1-2 Transfer Learning: 60 4-1-3 Warm Up Learning Strategy: 61 4-1-4 Data Augmentation: 61 4-1-5 Models: 62 4-1-6 Case Study: 63 4-2 模型應用結果討論 64 4-2-1 正常受試者影像討論 64 4-2-2 CTS患者施打藥物前後影像討論 65 4-2-3 所有CTS患者施打藥物前影像綜合分析討論 65 第五章、結論與未來展望 66 第六章、參考文獻 67 附錄 73 圖目錄: Figure 1:手腕部橫切面示意圖[Wikipedia, Transverse section of the wrist.] 2 Figure 2:Phalen's maneuver[Wikipedia, Phalen's maneuver] 3 Figure 3:腕隧道正中神經超音波橫截面影像 4 Figure 4:動態超音波影像 5 Figure 5:AlexNet[26] 7 Figure 6:GoogLeNet[28] 7 Figure 7:ResNet-34[29] 7 Figure 8:Computer Vision tasks[Stanford University CS231n, 2017.] 8 Figure 9:U-Net[35] 11 Figure 10:R-CNN[49] 15 Figure 11:Fast R-CNN[54] 16 Figure 12:Faster R-CNN[56] 18 Figure 13:Anchor Box示意圖[56] 18 Figure 14:RoI Align[58] 19 Figure 15:自製副木經馬達 23 Figure 16:切面挑選錯誤 24 Figure 17:回音訊號差影像 24 Figure 18:亮度差異(1) 25 Figure 19亮度差異(2) 25 Figure 20: 分叉的正中神經(median nerve bifidus) 26 Figure 21: MN邊緣不規則 26 Figure 22:影像裁切前、Figure 23影像裁切後 29 Figure 24:隨機裁切前、Figure 25:隨機裁切後 29 Figure 26水平翻轉前、Figure 27水平翻轉後 30 Figure 28:Mask R-CNN[58] 32 Figure 29:YOLACT[63] 34 Figure 30:SOLO[64] 36 Figure 31:SOLOv2[65] 38 Figure 32:BlendMask[67] 39 Figure 33:Multi training stages ensemble 40 Figure 34:Multi models ensemble 41 Figure 35:Multi training stages + Multi models ensemble 42 Figure 36:SOLOv2-1-MN Data Augmentation and Model Input 44 Figure 37:SOLOv2-1-MN Part1 45 Figure 38:SOLOv2-1-MN Part2 45 Figure 39:Intersection over Union 48 Figure 40 視覺化各模型推理結果-Part1 52 Figure 41 視覺化各模型推理結果-Part2 52 Figure 42 視覺化各模型推理結果-Part3 52 Figure 43:正常受試者手掌Active、Passive活動正中神經影像參數分析_Case_lin_左手 55 Figure 44:正常受試者手掌Active、Passive活動正中神經影像參數分析_Case_lin_右手 56 Figure 45:CTS患者 Case-27 左手施打藥物前後正中神經影像參數分析 57 Figure 46:CTS患者 Case-27 右手施打藥物前後正中神經影像參數分析 58 Figure 47: 所有CTS患者施打藥物前正中神經影像參數分析 59 Figure 48:Models Comparison-Speed v.s Accuracy 63 Figure 49:Case Study_1 63 Figure 50:Case Study_2 64 Figure 51:Case Study_3 64 表目錄 Table 1: Model result on validation dataset 50 Table 2: Model result on testing dataset 51 " | |
| dc.language.iso | zh-TW | |
| dc.subject | 正中神經 | zh_TW |
| dc.subject | 腕隧道症候群 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 即時性影像分割 | zh_TW |
| dc.subject | 超音波 | zh_TW |
| dc.subject | sonography | en |
| dc.subject | carpal tunnel syndrome | en |
| dc.subject | deep learning | en |
| dc.subject | real-time image segmentation | en |
| dc.subject | median nerve | en |
| dc.title | 應用新穎深度學習模型於動態超音波正中神經影像進行即時性影像分割 | zh_TW |
| dc.title | Real-time segmentation of median nerve in dynamic sonography using state-of-the-art deep learning models | en |
| dc.date.schoolyear | 110-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 吳爵宏(Ming-Jen Lin),張瑞峰 | |
| dc.subject.keyword | 即時性影像分割,深度學習,超音波,正中神經,腕隧道症候群, | zh_TW |
| dc.subject.keyword | real-time image segmentation,deep learning,sonography,median nerve,carpal tunnel syndrome, | en |
| dc.relation.page | 74 | |
| dc.identifier.doi | 10.6342/NTU202200311 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2022-02-11 | |
| 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 |
| dc.date.embargo-lift | 2025-02-09 | - |
| 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 | |
|---|---|---|---|
| U0001-0602202222592700.pdf 未授權公開取用 | 4.46 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。