請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89994
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 黃升龍 | zh_TW |
dc.contributor.advisor | Sheng-Lung Huang | en |
dc.contributor.author | 李劭允 | zh_TW |
dc.contributor.author | Shao-Yun Lee | en |
dc.date.accessioned | 2023-09-22T16:58:49Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-09-22 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-08-12 | - |
dc.identifier.citation | D. G. Shen, G. R. Wu, and H. Suk, "Deep learning in medical image analysis," in Annual Review of Biomedical Engineering, vol. 19, pp.221—248, 2017.
A. C. Tan, M. Fleckenstein, S. Schmitz-Valckenberg, and F. G. Holz, "Clinical Application of Multicolor Imaging Technology," in Ophthalmologica, vol. 236, pp. 8—18, 2016. Y. T. Hsieh, I H. Ma, and C. M. Yang, "Wide-based foveal pit: a predisposition to idiopathic epiretinal membrane," in Graefes Arch Clin Exp Ophthalmol, vol. 259, pp. 2095—2102, 2021. M. Wagner-Schuman, et al., "Race- and sex-related differences in retinal thickness and foveal pit morphology," in Investigative Ophthalmology & Visual Science, vol. 52, pp. 625—635, 2011. C. A. McCannel, J. L. Ensminger, N. N. Diehl, and D. N. Hodge, "Population-based incidence of macular holes," in Ophthalmology, vol. 116, pp. 1366—1369, 2009. Y. T. Hsieh, I H. Ma, and C. M. Yang, "The correlations of macular structure characteristics with idiopathic epiretinal membrane and its sexual preference—A matched comparison study," in Investigative Ophthalmology & Visual Science, vol. 63 pp. 10, 2022. K. M. Chueh, S. L. Huang, H. H. Chen, Y. T. Hsieh, and I H. Ma, "Identification of sex and age from macular optical coherence tomography and feature analysis using deep learning," in American Journal of Ophthalmology, vol. 235, pp.221—228, 2022. S. J. Park, N. K. Choi, K. H. Park, and S. J. Woo, "Nationwide incidence of clinically diagnosed retinal vein occlusion in Korea, 2008 through 2011: preponderance of women and the impact of aging," in Ophthalmology, vol. 121, pp. 1274—1280, 2014. "Retina" [Online]. Available:https://en.wikipedia.org/wiki/Retina "視網膜介紹" [Online]. Available:https://smallcollation.blogspot.com/2013/06/retina.html#gsc.tab=0 M. Ferrara, et al., "Biomechanical properties of retina and choroid: a comprehensive review of techniques and translational relevance," in Eye, Vol. 35, pp. 1818—1832, 2021. "Macula" [Online]. Available:https://en.wikipedia.org/wiki/Macula "Fovea centralis" [Online]. Available:https://en.wikipedia.org/wiki/Fovea_centralis "The Normal Retina and Choroid" [Online]. Available:https://entokey.com/the-normal-retina-and-choroid "Epiretinal Membrane" [Online]. Available:https://www.eophtha.com/posts/epiretinal-membrane K. Zhang, E. A Aguzzi, and T. Jhonson, "The internal limiting membrane: Roles in retinal development and implications for emerging ocular therapies," in Experimental Eye Research, vol. 10, 2021. S. C. Bu, R. Kuijer, X. R. Li, J. M Hooymans, and L. I Los, " Idiopathic Epiretinal Membrane," in Retina, vol. 12, pp.2317—2335, 2014. D. H. Gubel, and T. N. Wiesel, "Receptive fields of single neurones in the cat's striate cortex," in J Physiol, vol. 148, pp. 574—591, 1959. K. Fukushima, "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position," in Biological Cybernetics, vol. 36, pp.193—202, 1980. "初探卷積神經網路" [Online]. Available:https://chtseng.wordpress.com/2017/09/12/%E5%88%9D%E6%8E%A2%E5%8D%B7%E7%A9%8D%E7%A5%9E%E7%B6%93%E7%B6%B2%E8%B7%AF/ K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in CVPR, pp. 770—778, 2016. "直觀理解ResNet —簡介、觀念及實作(Python Keras)" [Online]. Available:https://medium.com/@rossleecooloh/直觀理解resnet-簡介-觀念及實作-python-keras-8d1e2e057de2 "機器/深度學習: 基礎介紹-損失函數(loss function)" [Online]. Available:https://chih-sheng-huang821.medium.com/機器-深度學習-基礎介紹-損失函數-loss-function-2dcac5ebb6cb "激活函數介紹" [Online]. Available:https://youtu.be/bHcJCp2Fyxs "ML Basics #4: Replace Negatives with Zeros!" [Online]. Available:https://dhruvs.space/posts/ml-basics-issue-4/ "ML Lecture 7: Backpropagation" [Online]. Available:https://youtu.be/ibJpTrp5mcE "Backpropagation 反向傳播算法" [Online]. Available:https://hackmd.io/@kk6333/HJqZGce1s J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, "How transferable are features in deep neural networks," in neural information processing systems, vol. 27, pp. 3320—3328 2014. "ML Lecture 19: Transfer Learning" [Online]. Available:https://youtu.be/qD6iD4TFsdQ H. E Kim, et al., "Transfer learning for medical image classification: a literature review," in BMC Medical Imaging, vol. 69, 2022. Z. Bolei, et al., "Learning Deep Features for Discriminative Localization, " in CVPR, pp. 2921—2929, 2016. "了解 CNN 關注的區域:CAM 與 Grad-CAM 的介紹分享" [Online]. Available:https://medium.com/ai-academy-taiwan/了解-cnn-關注的區域-cam-與-grad-cam-的介紹分享-2206dd1017c8 R. R. Selvaraju, et al., "Grad-CAM: Visual explanations from deep networks via gradient-based localization," in ICCV, pp. 618—626, 2017. J. Tobias., et al., "Striving for simplicity: the all convolutional net," in ICLR, 2015. K. M. Chueh, "Exploration of macular optical coherence tomography characteristics in discriminating sex and age using grad-CAM," M.S. thesis, National Taiwan University, 2020. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89994 | - |
dc.description.abstract | 過去普遍認為視網膜黃斑部的結構差異只是個體上的差別,不具有臨床上的意義,但隨著近年在研究黃斑部具有寬中心凹(wide-based)的眼睛時發現這些具有寬中心凹的眼睛有近83%是女性,這些具有寬中心凹的眼睛雖然其視力與功能皆完全正常,但對側眼卻有大約52%的比例產生黃斑前膜(epiretinal membrane; ERM)。另一個研究在觀察單側黃斑前膜的健康對側眼時發現,發現這些健康對側眼有著寬中心凹,以及相較於正常人有著較薄的中心凹厚度(central foveolar thickness; CFT)、較薄的中心視網膜厚度(central subfield thickness; CST)以及更大的中心凹無血管區(foveal avascular zone; FAZ),而這些健康眼睛的視力與功能也完全正常。另外也有研究利用卷積神經網路分析視網膜黃斑部的光學同調斷層掃描(optical coherence tomography; OCT)可以進行年齡的預測,甚至可以藉由觀察中心凹的輪廓預測性別。這些可能都代表著看似只是個體差異的視網膜黃斑部結構特徵,其實包含著許多資訊與臨床上的意義。
已廣泛應用在影像分類或者影像分割的卷積神經網路(convolution neural network; CNN)近年來也開始用於醫學影像,除了CNN在影像處理上有著強大的性能,CNN具有自動找出影像特徵的能力,並且透過可視化工具呈現特徵,以利分析;而OCT能夠以非侵入式的方式獲得高解析度的樣本影像。本論文結合深度學習以及OCT影像,使用卷積神經路分辨4866組來自2288位病人的健康、黃斑前膜與其他黃斑部結構異常(不包含黃斑前膜)之視網膜黃斑部OCT影像,CNN模型在分辨影像屬於健康、黃斑前膜或者其他黃斑部結構異常(不包含黃斑前膜)時可以取得80%以上的分辨準確率。除此之外,也利用經過OCT影像預訓練之CNN模型分辨1155組810為病患的健康眼睛與單側患有黃斑前膜的健康對側眼睛之OCT影像,再將資料依照性別分類後,CNN模型可以取得66.6±6.1%的分辨健康眼睛與單側患有黃斑前膜的健康對側眼睛的分辨準確率,並根據可視化工具分析特徵位置。希望透過深度學習以及高解析度之OCT影像,除了幫助診斷視網膜黃斑部之病變外,也希望藉由分辨單側患有黃斑前膜的健康對側眼睛,預測未來容易產生黃斑前膜病變之眼睛,以利提早追蹤治療。 | zh_TW |
dc.description.abstract | In the past, structural differences in the macula of the retina were generally regarded as individual variations without clinical significance. However, a recent study has discovered eyes with a wide-based macula that nearly 83% of these eyes with a wide-based macula belong to females. Although these eyes with a wide-based macula exhibit normal visual acuity and functionality, approximately 52% of the contralateral eyes develop epiretinal membranes. Another study observed the contralateral eyes of individuals with unilateral epiretinal membranes and found that, despite their normal visual acuity and functionality, they also had a wide-based macula, thinner central foveolar thickness (CFT), thinner central subfield thickness (CST), and a larger foveal avascular zone (FAZ) compared to normal individuals. These eyes also demonstrated normal visual acuity and functionality. Additionally, there have been studies utilizing convolutional neural networks (CNNs) to analyze optical coherence tomography (OCT) scans of the macula, which can predict age and even infer gender by observing the contour of the central fovea. These findings suggest that seemingly individual variations in the macular structure encompass valuable information and clinical significance.
In recent years, convolutional neural networks (CNNs), widely employed in image classification and segmentation tasks, have also started to be utilized in medical imaging. Apart from their powerful performance in image processing, CNNs possess the ability to automatically extract image features and visualize them using tools for analysis. On the other hand, OCT enables the acquisition of high-resolution sample images in a non-invasive manner. This study combines deep learning with OCT images to classify OCT images of the macula from 4,866 sets of 2,288 patients into healthy, epiretinal membrane, or other macular structural abnormalities. The CNN model achieves an accuracy of over 80% in distinguishing between healthy, epiretinal membrane, and other macular structural abnormalities. Furthermore, using a pre-trained CNN model on OCT images, 1,155 sets of OCT images from 810 patients with healthy eyes and contralateral eyes with unilateral epiretinal membranes are classified after gender stratification. The CNN model achieves a discrimination accuracy of 66.6±6.1% in distinguishing between healthy eyes and contralateral eyes with unilateral epiretinal membranes, considering gender classification, and analyzing feature positions using visualization tools. The objective of this study is to utilize deep learning and high-resolution OCT images not only to aid in diagnosing macular pathologies but also to predict future eyes susceptible to epiretinal membrane development by distinguishing healthy contralateral eyes with unilateral epiretinal membranes, enabling early monitoring and treatment. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-09-22T16:58:49Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-09-22T16:58:49Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 摘要 I
Abstract II 目錄 IV 圖目錄 VI 表目錄 IX 第1章 緒論 1 第2章 光學同調斷層掃描及視網膜介紹 3 2.1 光學同調斷層掃描 3 2.1.1 譜域式與掃頻式光學同調斷層掃描 4 2.1.2 海德堡光學同調斷層掃描顯微儀 6 2.2 視網膜介紹 6 2.2.1 視網膜構造 6 2.2.2 黃斑區與黃斑中心凹 8 2.3 黃斑前膜 8 第3章 卷積神經網路在OCT影像之應用 10 3.1 卷積神經網路用於影像分類 10 3.1.1 卷積神經網路的架構 10 3.1.2 損失函數、激活函數與反向傳播 14 3.2 預訓練模型與遷移學習 20 3.3 卷積神經網路解釋工具 24 3.4 視網膜OCT影像資訊及用於卷積神經網路之預處理 29 3.4.1 影像來源與資訊 29 3.4.2 影像數值預處理及影像裁切 31 3.4.3 影像分類與資料集建立 34 第4章 影像分辨結果與分析 38 4.1 健康與黃斑部結構異常眼睛之視網膜黃斑部光學同調掃描影像分辨結果與分析 39 4.1.1 分辨健康眼睛與黃斑部結構異常眼睛之視網膜黃斑部光學同調掃描影像 40 4.1.2 分辨黃斑前膜眼睛與其他黃斑部結構異常(不包含黃斑前膜)眼睛之視網膜黃斑部光學同調掃描影像 44 4.1.3 分辨黃斑前膜眼睛與健康眼睛之視網膜黃斑部光學同調掃描影像 47 4.2 健康眼睛與亞健康眼睛之視網膜黃斑部光學同調掃描影像分辨結果與分析 50 4.2.1 使用ImageNet影像預訓練ResNet18模型之分辨結果與分析 51 4.2.2 使用OCT影像預訓練ResNet18模型之分辨結果與分析 56 第5章 結論與未來展望 63 5.1 結論 63 5.2 未來展望 65 參考文獻 66 | - |
dc.language.iso | zh_TW | - |
dc.title | 利用卷積神經網路從黃斑部光學同調斷層掃描影像分辨健康及好發黃斑前膜的亞健康眼睛 | zh_TW |
dc.title | Differentiation of Normal Eyes and Sub-healthy Ones Susceptible to Epiretinal Membrane by Macular Optical Coherence Tomography Using Convolutional Neural Networks | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 王一中;謝易庭;馬一心 | zh_TW |
dc.contributor.oralexamcommittee | I-Jong Wang;Yi-Ting Hsieh;I-Hsin Ma | en |
dc.subject.keyword | 卷積神經網路,光學同調斷層掃描,視網膜黃斑部,黃斑前膜,類神經網路可視化, | zh_TW |
dc.subject.keyword | convolutional neural network (CNN),optical coherence tomography (OCT),retinal macular,epiretinal membrane (ERM),neural network visualization, | en |
dc.relation.page | 69 | - |
dc.identifier.doi | 10.6342/NTU202303712 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2023-08-13 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 光電工程學研究所 | - |
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 | |
---|---|---|---|
ntu-111-2.pdf 授權僅限NTU校內IP使用(校園外請利用VPN校外連線服務) | 3.24 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。