請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/79288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 | Chung-Wei Tu | en |
| dc.contributor.author | 凃仲蔚 | zh_TW |
| dc.date.accessioned | 2022-11-23T08:57:26Z | - |
| dc.date.available | 2022-01-17 | |
| dc.date.available | 2022-11-23T08:57:26Z | - |
| dc.date.copyright | 2022-01-17 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-12-10 | |
| dc.identifier.citation | [1] R. L. Siegel, K. D. Miller, H. E. Fuchs, and A. Jemal, 'Cancer statistics, 2021,' CA: a cancer journal for clinicians, vol. 71, no. 1, pp. 7–33-7–33, 2021. [2] D. Thigpen, A. Kappler, and R. Brem, 'The role of ultrasound in screening dense breasts—a review of the literature and practical solutions for implementation,' Diagnostics, vol. 8, no. 1, pp. 20-20, 2018. [3] M. E. Hatzipanagiotou et al., 'FEASIBILITY OF ABUS AS AN ALTERNATIVE TO HAND HELD ULTRASOUND FOR RESPONSE CONTROL IN NEOADJUVANT BREAST CANCER TREATMENT,' Clinical Breast Cancer, 2021. [4] A. Arslan, G. Ertaş, and E. Arıbal, '3D automated breast ultrasound system: comparison of interpretation time of senior versus junior radiologist,' European journal of breast health, vol. 15, no. 3, pp. 153-153, 2019. [5] K. Tong, Y. Wu, and F. Zhou, 'Recent advances in small object detection based on deep learning: A review,' Image and Vision Computing, vol. 97, pp. 103910-103910, 2020. [6] S. M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and M. K. Khan, 'Medical image analysis using convolutional neural networks: a review,' Journal of medical systems, vol. 42, no. 11, pp. 1–13-1–13, 2018. [7] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. J. a. p. a. Liao, 'Yolov4: Optimal speed and accuracy of object detection,' arXiv preprint arXiv:2004.10934, 2020. [8] W. Liu et al., 'Ssd: Single shot multibox detector,' in European conference on computer vision, 2016 2016, pp. 21–37-21–37. [9] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, 'Focal loss for dense object detection,' in Proceedings of the IEEE international conference on computer vision, 2017 2017, pp. 2980–2988-2980–2988. [10] H. Zhang et al., 'ResNeSt: Split-Attention Networks,' ed, 2020. [11] A. Shrivastava, A. Gupta, and R. Girshick, 'Training region-based object detectors with online hard example mining,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016 2016, pp. 761–769-761–769. [12] 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. [13] S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, 'Path Aggregation Network for Instance Segmentation,' in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18-23 June 2018 2018, pp. 8759-8768, doi: 10.1109/CVPR.2018.00913. [14] K. He, X. Zhang, S. Ren, and J. Sun, 'Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,' in Computer Vision – ECCV 2014, Cham, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds., 2014// 2014: Springer International Publishing, pp. 346-361. [15] Y. Wu et al., 'Rethinking Classification and Localization for Object Detection,' ed, 2019. [16] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, 'Rethinking the Inception Architecture for Computer Vision,' in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June 2016 2016, pp. 2818-2826, doi: 10.1109/CVPR.2016.308. [17] 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, 2019 2019 pp. 658–666-658–666. [18] 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. [19] D. P. Chakraborty, 'Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data,' Medical physics, vol. 16, no. 4, pp. 561–568-561–568, 1989. [20] A. I. Bandos, H. E. Rockette, T. Song, and D. Gur, 'Area under the free-response ROC curve (FROC) and a related summary index,' Biometrics, vol. 65, no. 1, pp. 247–256-247–256, 2009. [21] S. Arlot and A. Celisse, 'A survey of cross-validation procedures for model selection,' Statistics surveys, vol. 4, pp. 40–79-40–79, 2010. [22] M. Zanotel et al., 'Automated breast ultrasound: basic principles and emerging clinical applications,' La radiologia medica, vol. 123, no. 1, pp. 1–12-1–12, 2018. [23] W. K. Moon, I. L. Chen, J. M. Chang, S. U. Shin, C.-M. Lo, and R.-F. Chang, 'The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound,' Ultrasonics, vol. 76, pp. 70–77-70–77, 2017. [24] B. Bosquet, M. Mucientes, and V. M. Brea, 'STDnet: Exploiting high resolution feature maps for small object detection,' Engineering Applications of Artificial Intelligence, vol. 91, pp. 103615-103615, 2020. [25] K. Fu, Z. Chen, Y. Zhang, and X. Sun, 'Enhanced feature representation in detection for optical remote sensing images,' Remote Sensing, vol. 11, no. 18, pp. 2095-2095, 2019. [26] M. Tan, R. Pang, and Q. V. Le, 'Efficientdet: Scalable and efficient object detection,' in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020 2020, pp. 10781–10790-10781–10790. [27] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, 'Learning transferable architectures for scalable image recognition,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018 2018, pp. 8697–8710-8697–8710. [28] P. Balaprakash, M. Salim, T. D. Uram, V. Vishwanath, and S. M. Wild, 'DeepHyper: Asynchronous hyperparameter search for deep neural networks,' in 2018 IEEE 25th international conference on high performance computing (HiPC), 2018 2018, pp. 42–51-42–51. [29] V. François-Lavet, P. Henderson, R. Islam, M. G. Bellemare, and J. Pineau, 'An introduction to deep reinforcement learning,' arXiv preprint arXiv:1811.12560, 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/79288 | - |
| dc.description.abstract | "自動乳房超音波(Automated Breast Ultrasound, ABUS)被廣泛應用於乳癌篩檢以進行早期檢測。儘管ABUS的掃描過程非常快捷省時，對放射科醫師來說，查閱數百張二維超音波影像依然非常耗費時間。因此，需要電腦輔助偵測系統(Computer-aided Detection, CADe)來協助放射科醫師。近年來，卷積神經網路在物件檢測領域表現優異，其能夠從影像中學習辨識特徵，因此被廣泛使用於醫學影像領域。本研究提出了一種以三維卷積神經網路為核心的電腦輔助偵測系統以用於乳房腫瘤偵測。該系統由影像縮放、腫瘤檢測和後處理組成。在影像縮放階段，影像被重新採樣使影像間距一致並接著縮放至適合腫瘤偵測模型的大小。接著，利用提出的3-D SAS-YOLOv4腫瘤偵測模型對影像進行腫瘤偵測以產生腫瘤邊界框。鑒於YOLOv4具有出色的高效率和準確率，我們所提出的腫瘤偵測模型採用YOLOv4為基礎。為了進一步強化模型的特徵提取能力，採用ResNeSt強大的分割注意力模塊(Split Attention, SA)作為模型主幹，並提出了注意力平滑機制(Attention Smoothing, AS)來改進分割注意力模塊。此外，本研究提出了多階段訓練策略(Multi-stage Training Strategy)進行偽陽性消除(False Positive Reduction)以增加模型的準確度。最後，在後處理階段，模型產生的預測結果將送入非最大化抑制(Non-maximum Suppression, NMS)演算法消除重疊的邊界框。本研究採用了348張ABUS影像進行實驗，其中包含523個腫瘤。結果顯示出，所提出的模型在達到90%、95%和98%的靈敏度(Sensitivity)時，每個超音波影像平均產生的偽陽性數量(False Positive per Pass)分別為1.71、2.71和5.87，並且該模型對不同大小的腫瘤具有穩健的性能。與YOLOv4相比，所提出的模型準確得多，這些結果指出所提出的修改可以大幅改進檢測模型。" | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-23T08:57:26Z (GMT). No. of bitstreams: 1 U0001-0812202115091600.pdf: 2543591 bytes, checksum: a3dc16e31796649b489d52df8102a595 (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 VI List of Figures VIII List of Tables IX Chapter 1 Introduction 1 Chapter 2 Materials 4 Chapter 3 Methods 7 3.1 Image Resizing 8 3.2 Tumor Detection Model 9 3.2.1 YOLOv4 9 3.2.2 SAS-YOLOv4 12 3.2.3 SA Block 15 3.2.4 Attention Smoothing 17 3.3 Non-maximum Suppression 18 3.4 Model Training 19 3.4.1 Loss Function 20 3.4.2 FP Reduction 20 Chapter 4 Results and Discussion 22 4.1 Experiment Environment 22 4.2 Evaluation 22 4.3 Experiment Results 23 4.3.1 Comparison with Original YOLOv4 23 4.3.2 Detection on Different Sizes 26 4.3.3 Ablation Study 28 4.4 Discussion 29 Chapter 5 Conclusion 33 Reference 34 | |
| dc.language.iso | en | |
| dc.title | YOLOv4模型及多階段困難偽陽性消除應用於乳房自動超音波腫瘤偵測 | zh_TW |
| dc.title | Tumor Detection for Automated Breast Ultrasound Image Using YOLOv4 With Multi-Stage Hard FP Reduction | en |
| dc.date.schoolyear | 110-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 羅崇銘(Hsin-Tsai Liu),陳啟禎(Chih-Yang Tseng) | |
| dc.subject.keyword | 自動乳房超音波,電腦輔助診斷,單階段物件偵測,注意力機制,YOLOv4,偽陽性消除, | zh_TW |
| dc.subject.keyword | ABUS,computer-aided detection,one-stage object detection,attention mechanism,false positive reduction,YOLOv4, | en |
| dc.relation.page | 37 | |
| dc.identifier.doi | 10.6342/NTU202104524 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2021-12-10 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0812202115091600.pdf | 2.48 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。