請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60849完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 邱奕鵬(Yih-Peng Chiou) | |
| dc.contributor.author | Shih-Wei Fu | en |
| dc.contributor.author | 符世緯 | zh_TW |
| dc.date.accessioned | 2021-06-16T10:33:00Z | - |
| dc.date.available | 2024-02-04 | |
| dc.date.copyright | 2021-02-23 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-02-05 | |
| dc.identifier.citation | 1. A. Rashno, D. Koozekanani, P.M. Drayna, B. Nazari, S. Sadri, H. Rabbani and K.K. Parhi. “Fully-automated segmentation of fluid/cyst regions in optical coherence tomography images with diabetic macular edema using neutrosophic sets and graph algorithms,” IEEE Transactions on Biomedical Engineering, Issue 5, pp.989- 1001. (2017) 2. 4 A2A SD-OCT clinics (Devers eye institute, duke eye center, emory eye center, and national eye Institute) 3. L. Fang, D. Cunefare, C. Wang, R.H. Guymer, S. Li, and S. Farsiu. “Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search,” OSA Biomedical Optics Express, vol.8, Issue 5, pp.2732-2744. (2017) 4. J. Long, E. Shelhamer, T. Darrell, UC Berkeley. “Fully convolutional networks for semantic segmentation,” arXiv Computer Science, 1411.4038[cs.CV]. (2015) 5. S. Albawi, T.A. Mohammed and S. Al-Zawi, “Understanding of a convolutional neural network,” IEEE, 2017 International Conference on Engineering and Technology (ICET), Antalya, 2017, pp.1-6. (2017) 6. N. Kanopoulos, N. Vasanthavada, R.L. Baker. “Design of an image edge detection filter using the sobel operator,” IEEE Journal of Solid-State Circuits, vol. 23, Issue 2, pp.358-367. (1988) 7. K. He, X. Zhang, S. Ren, J. Sun. “Deep residual learning for image recognition,” arXiv Computer Science, 1512.03385[cs.CV]. (2015) 8. J. Hu, S. Li, S. Albanie, G. Sun, E. Wu. “Squeeze-and-excitation networks,” arXiv Computer Science. 1709.01507[cs.CV]. (2017) 9. OpenCV. “Basic thresholding operations,” OpenCV 2.4.13.7 Documentation. https://docs.opencv.org/3.4/db/d8e/tutorial_threshold.html 10. S. Ruder. “An overview of gradient descent optimization algorithms,” arXiv Computer Science, 1609.04747[cs.LG]. (2017) 11. Z. Chen, D. Li, H. Shen, H. Mo , Z. Zi, W. Hao. “Automated segmentation of fluid regions in optical coherence tomography B-scan images of age-related macular degeneration,” ELSEVIER Optics Laser Technology, vol.122:105830. (2020) 12. O. Ronneberger, P. Fischer, and T. Brox. “U-Net: Convolutional networks for biomedical image segmentation,” arXiv Computer Science, 1505.04597[cs.CV]. (2015) 13. S. Wang, “The improved Dijkstra's shortest path algorithm and its application,” ELSEVIER Procedia Engineering, vol.29, pp.1186-1190. (2012) 14. J. Lehtinen, J. Munkberg, J. Hasselgren, S. Laine, T. Karras, M. Aittala, T. Aila. “Noise2Noise: Learning image restoration without clean Data,” arXiv Computer Science, 1803.04189[cs.CV]. (2018) 15. M.W. Wintergerst, T. Schultz, J. Birtel, A.K. Schuster, N. Pfeiffer, S. SchmitzValckenberg, F.G. Holz, R.P. Finger. “Algorithms for the automated analysis of agerelated macular degeneration biomarkers on optical coherence tomography: A systematic review,” PubMed Transl Vis Sci Technol, vol.6(4):10, eCollection. (2017) 16. S.G. Zadeh, M.W. Wintergerst, V. Wiens, S. Thiele, F.G. Holz, R.P. Finger, T. Schultz. “CNNs enable accurate and fast segment-ation of drusen in optical coherence tomography,” published in: deep learning in medical image analysis and multimodal learning for clinical decision support, pp.65–73. (2017) 17. T. Khalil, M.U. Akram, H. Raja, A. Jameel, I. Basit, “Detection of glaucoma using cup to disc ratio from spectral domain optical coherence tomography images,” IEEE Access, vol.6, pp.4560-4576. (2018) 18. S.M. Waldstein, J. Wright, J. Warburton, P. Margaron, C. Simader, U. SchmidtErfurth, “Predictive value of retinal morphology for visual acuity outcomes of different ranibizumab treatment regimens for neovascular AMD, ophthalmology,” ELSEVIER Ophthalmology, vol. 123, Issue 1, pp.60-69. (2016) 19. S.J. Chiu, J. Stephanie et al, “Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema,” Biomedical Optics Express, vol.6(4), pp.1172-1194. (2015) 20. C.S. Lee et al, “Deep-learning based, automated segmentation of macular edema in optical coherence tomography,” Biomedical optics express, vol.8(7), pp.3440-3448. (2017) 21. G. Liu, J. Si, Y. Hu and S. Li, “Photographic image synthesis with improved U-net,” IEEE 2018 Tenth International Conference on Advanced Computational Intelligence (ICACI), pp. 402-407. (2018) 22. V. Badrinarayanan, A. Kendall and R. Cipolla, “SegNet: A deep convolutional encoder-decoder architecture for image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.39, no.12, pp.2481-2495. (2017) 23. A. Rashno, B. Nazari, D.D. Koozekanani, P.M. Drayna, S. Sadri, H. Rabbani, K.K. Parhi, “Fully-automated segmentation of fluid regions in exudative age-related macular degeneration subjects: kernel graph cut in neutrosophic domain,” PloS one, vol.12:10 e0186949. (2017) 24. C. Shorten, T.M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Springer Journal of Big Data, vol. 6(60). (2019) 25. R. Song, Z. Zhang, H. Liu. “Edge connection based on canny edge detection algorithm,” Springer Pattern Recognition and Image Analysis, vol.27, pp.740–747.(2017) 26. 台灣優爾視護眼協會 顧問 陳瑩山醫師, “診斷黃斑部水腫OCT好犀利,” 視網膜光學斷層掃描。 27. 黃升龍 教授, “光學同調斷層掃描術的臨床應用趨勢與挑戰,” 科儀新知, 224 期, 109.9。 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60849 | - |
| dc.description.abstract | 視網膜黃斑部病變為老年或糖尿病患者的常見症狀。其症狀有視線內盲點，視點歪斜，嚴重可導致失明。醫學上多以光學同調斷層掃描影像，來判斷病人是否為黃斑部病變的患者。在斷層掃描影像上，黃斑部會有積水或是增生組織的產生，需以專業醫生以人工的方式來判斷病變的範圍。
本研究利用機器學習取代傳統人眼辨識。深度學習也稱人工智慧，對於視網膜黃斑部病變範圍訓練一個專屬神經網路。其輸入為病人的視網膜斷層掃描影像，輸出為病變的範圍，實現了自動辨別病變範圍的成果。 其訓練過程主要分4個步驟 一.利用空間相關閾值得到感興趣區域。 二.使用感興趣區域訓練新的ROI判別模型。並且根據感興趣區域遮罩切割原圖。 三.將切割好的視網膜圖片進行訓練。並且和真實病變範圍比較。重複訓練神經網路。 四.訓練好的神經網路，輸入未曾看過的圖片，也能得到正確的病變範圍。實現了自動辨別病變範圍的成果。 本研究使用了新的方式，利用模糊矩陣和空間可調式閾值，取代傳統邊界演算法，達到取特定區域的效果。其特色為快速，簡單，且不需訓練。其結果和先前的論文幾近相同。 在特殊難以判別的區域，本論文也提供深度學習法。利用神經網路強大的特徵判斷力，製作出能夠根據視網膜圖片選取特定區域的模型。經過此模型的遮罩，切割出視網膜圖片的特定區域，再進行黃斑部水腫病變的神經網路，執行病變範圍的判斷。 空間相關閾值的方式也可利用在各種影像處理上，成為任何影像處理的第一步驟。 在沒有醫生人工標籤的情況下，依然能夠使用影像處理方式產生人工標籤，藉此訓練感興趣區域的神經網路。提升黃斑部病變神經網路的辨別能力。 | zh_TW |
| dc.description.abstract | Macular degeneration is a common disease occurs in elder or people who have diabetes. Optical coherence tomography (OCT) has been used to diagnosis the Age macular degeneration (AMD), and diabetic macular edema (DME). The fluid regions in retina are the most characteristic of AMD, and it could be observed in retinal OCT imaging by a ophthalmologist. We propose an automatic machine learning method to segment the AMD regions. There are four steps to accomplish the segmentation. 1.Using the spatial adaptive threshold to segment the region of interest (ROI). 2.Cropping the OCT image by the ROI mask. 3.Training the neural network and modified by the manual AMD ground truth. 4.Inputting the raw data to the neural network, and obtain a automatic segmentation of the AMD regions. In the paper, we used a blurring convolution metric and spatial adaptive threshold to obtain the ROI, instead of the previous works using deep learning method, canny, or other edge detector. Spatial adaptive threshold is a simple, fast way comparing with the previous work, and it has same quality. It can also be the first step of all the image processing. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T10:33:00Z (GMT). No. of bitstreams: 1 U0001-0302202117350900.pdf: 3460974 bytes, checksum: bc31b8766b1ae9d40aae67e28e7ef7d5 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 誌 謝 辭 II 中文摘要 III ABSTRACT V 目 錄 VI 圖 目 錄 VIII 式 目 錄 IX 表 目 錄 IX 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 2 1.3 論文概述 3 第二章 神經網路簡介 4 2.1 簡介和梯度下降法 4 2.2 卷積神經網路 7 2.3 U-NET 8 2.4 SE模塊和殘差訓練 10 2.5 模型正確率的相關係數 12 2.6 語意分割影像增強 13 第三章 閾值與感興趣區域(ROI)簡介 15 3.1 ROI與常用濾鏡 15 3.2 常用閾值介紹 17 3.3 空間相關閾值 19 3.4 多中心點空間閾值系統 27 3.5 人工智慧ROI 30 3.6 利用空間相關閾值修正影像處理結果 33 第四章 研究與實驗方法結果 36 4.1 訓練資料與影像處理 37 4.2 模型架構與硬體設備 37 4.3 實驗結果與數據 38 4.3.1 黃斑部水腫結果數據 38 4.3.2 空間閾值相關應用 45 第五章 結論與未來研究 49 參考資料 50 | |
| dc.language.iso | zh-TW | |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 黃斑部水腫 | zh_TW |
| dc.subject | 感興趣區域 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | ROI | en |
| dc.subject | Segmentation | en |
| dc.title | 利用空間相關閾值做深度學習分類以偵測黃斑部 病變之光學同調斷層掃描影像 | zh_TW |
| dc.title | Deep-Learning Segmentation of MD OCT Images Based on Spatial Adaptive Threshold | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 109-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 賴志賢(Chih-Hsien Lai),蕭惠心(Hui-Hsin Hsiao),李翔傑(Hsiang-Chieh Lee) | |
| dc.subject.keyword | 深度學習,黃斑部水腫,感興趣區域, | zh_TW |
| dc.subject.keyword | deep learning,ROI,Segmentation, | en |
| dc.relation.page | 53 | |
| dc.identifier.doi | 10.6342/NTU202100466 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2021-02-05 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 光電工程學研究所 | zh_TW |
| 顯示於系所單位： | 光電工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0302202117350900.pdf 未授權公開取用 | 3.38 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。