請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/79780完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李明穗(Ming-Sui Lee) | |
| dc.contributor.author | Shung-Cyuan Hong | en |
| dc.contributor.author | 洪商荃 | zh_TW |
| dc.date.accessioned | 2022-11-23T09:11:05Z | - |
| dc.date.available | 2021-09-02 | |
| dc.date.available | 2022-11-23T09:11:05Z | - |
| dc.date.copyright | 2021-09-02 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-13 | |
| dc.identifier.citation | [1] W. Al-Dhabyani, M. Gomaa, H. Khaled, and A. Fahmy. Dataset of breast ultrasound images. In Data in Brief, 2020. [2] L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. In European Conference on Computer Vision, 2018. [3] B. Cheng, R. Girshick, P. Doll´ar, A. C. Berg, and A. Kirillov. Boundary iou: Improving object centric image segmentation evaluation. In Conference on Computer Vision and Pattern Recognition, 2021. [4] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Conference on Computer Vision and Pattern Recognition, 2016. [5] S. Hochreiter and J. Schmidhuber. Long shortterm memory. In Neural computation, 1997. [6] G. Huang, Z. Liu, and L. van der Maaten. Densely connected convolutional networks. In Conference on Computer Vision and Pattern Recognition, 2017. [7] J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In Conference on Computer Vision and Pattern Recognition, 2015 [8] F. Milletari1, N. Navab, and S.A. Ahmadi. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In International Conference on 3D Vision, 2016. [9] O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer Assisted Interventionn, 2015. [10] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations, 2015. [11] C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi. Inceptionv4, inception-resnet and the impact of residual connections on learning. In AAAI Conference on Artificial Intelligence, 2017. [12] W.H. Tseng, M.S. Lee, C.C. Wang, Y.W. Chen, T.Y. Hsiao, and T.L. Yang. Objective evaluation of biomaterial effects after injection laryngoplasty–introduction of artificial intelligence-based ultrasonic image analysis. In Wiley Online Library, 2021. [13] S. Xie, R. Girshick, P. Dollar, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. In Conference on Computer Vision and Pattern Recognition, 2017. [14] S. Xingjian, Z. Chen, H. Wang, D.Y. Yeung, and W.K. W. W. chun Woo. Convolutional lstm network: A machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems, 2015. [15] H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia. Pyramid scene parsing network. In Conference on Computer Vision and Pattern Recognition, 2017. [16] Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang. Unet++: A nested unet architecture for medical image segmentation. In Medical Image Computing and Computer Assisted Interventionn, 2015. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/79780 | - |
| dc.description.abstract | 隨著社會進步，人們之間的溝通越顯重要，人使用聲音的頻率大為增加，過度的使用聲帶導致聲帶萎縮和老化的好發年齡逐漸降低。聲帶萎縮的情況下，發聲時聲帶不易閉合，病患為了正常發聲則必續更用力的使用聲帶，在如此的惡性循環下病況變得越來越嚴重，造成病患日常生活上的問題。門診聲帶注射術發展多年已逐漸成熟，被廣泛的應用在大多數的聲帶問題上。要治療聲帶麻痺或聲帶萎縮的情況下便會通過聲帶玻尿酸注射來增加聲帶體積，幫助聲帶的閉合。因為要觀察玻尿酸在聲帶的目前狀況，因此醫生會使用超音波影像和病患發聲訊號來觀察，透過超音波影像我們可以明確觀察到玻尿酸在喉嚨中體積變化，有異狀即可採取立即行動處理。在這個任務中，我們希望利用超聲喉嚨圖像中玻尿酸的分割結果來計算玻尿酸的體積，可以用來跟踪和估計玻尿酸體積的變化趨勢，幫助醫生進行臨床判斷。 在醫學影像分割中，由前人的成果我們可以知道深度學習取得前所未得的優良效果。此任務中跟一般傳統醫學影像分割有所區別在於，此圖片前後的圖像是連續的跟前後彼此的幀是高度相關的。因此若使用一般2D的卷積神經網路，再把單張結果組合在一起可能會缺乏前後時間的資訊。但若使用3D卷積神經網路所花費的資源是相巨大觀的(其中包含大量記憶體及訓練時間)。在本文中我們提出了2D卷積神經網路結合時間循環神經網路達到可以同時致力於單張圖像的結果又可以考慮前後的時間資訊，在硬體上消耗的資源也是遠低於3D卷積神經網路的。 我們也進一步將方法應用在我們的資料集中，此資料集是病患喉嚨中的超音波影像在接受注入玻尿酸後的不同時間點。醫生藉由玻尿酸在聲帶中的體積降解情形，可以追蹤病人聲帶恢復情形，若我們能精準的預測出玻尿酸體積則進一步幫助醫生在臨床上的判斷。藉由我們的實驗，我們的架構有最好的表現相較於其他的架構。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-23T09:11:05Z (GMT). No. of bitstreams: 1 U0001-1108202111114500.pdf: 8837001 bytes, checksum: ae0326aa382fa307fa1c446d15994d8a (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i Acknowledgements ii 摘要 iv Abstract vi Contents ix List of Figures xi List of Tables xv Chapter 1 Introduction 1 Chapter 2 Related work 4 2.1 Image Sequence Segmentation 4 2.1.1 2D Convolutional Networks for Segmentation 4 2.1.2 3D Convolutional Networks for Segmentation 6 2.1.3 Recurrent Neural Network (RNN) 6 2.2 Ultrasonic Image Dataset 7 Chapter 3 Method 9 3.1 System Overview 9 3.1.1 Data Preprocessing 10 3.1.2 TCSNet 10 3.1.2.1 Extraction Module 12 3.1.2.2 Temporal Module 12 3.1.2.3 Refining Module 13 3.1.2.4 Temporal Loss 13 3.1.2.5 Refining Loss 14 3.1.3 Data Postprocessing 15 3.1.4 Calculating HA Volume 15 3.1.5 HA Volume Analysis 16 Chapter 4 Experiment and Results 17 4.1 Dataset 17 4.1.1 Patient Throat Dataset 17 4.1.2 Image Phantom Dataset 19 4.1.2.1 Normal Image Phantom Dataset 20 4.1.2.2 Calcified Image Phantom Dataset 20 4.2 Metrics 20 4.3 Implementation 21 4.4 ROC Curve and PR Curve 22 4.5 Network Parameters 23 4.6 Comparison to Other Segmentation Model 24 4.7 HA Volume Analysis 28 4.8 Discussion 32 Chapter 5 Conclusion 36 References 39 | |
| dc.language.iso | en | |
| dc.subject | 時間循環神經網路 | zh_TW |
| dc.subject | 圖像分割 | zh_TW |
| dc.subject | 超聲波影像 | zh_TW |
| dc.subject | 神經網路 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | RNN | en |
| dc.subject | Image segmentation | en |
| dc.subject | Neural network | en |
| dc.subject | Ultrasonic image | en |
| dc.subject | Deep learning | en |
| dc.title | 基於人工智慧分析玻尿酸體積於注射式喉成型手術後的降解情形 | zh_TW |
| dc.title | Artificial Intelligence-Based Ultrasonic Image Analysis for Estimating and Tracking the Degradation of Injection Laryngoplasty | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 曾文萱(Hsin-Tsai Liu),胡敏君(Chih-Yang Tseng) | |
| dc.subject.keyword | 圖像分割,超聲波影像,神經網路,深度學習,時間循環神經網路, | zh_TW |
| dc.subject.keyword | Image segmentation,Neural network,Ultrasonic image,Deep learning,RNN, | en |
| dc.relation.page | 41 | |
| dc.identifier.doi | 10.6342/NTU202102266 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2021-08-13 | |
| 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 |
| 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 | |
|---|---|---|---|
| U0001-1108202111114500.pdf | 8.63 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。