簡易檢索 / 詳目顯示

研究生: 宋狄恩
Sung, Di-En
論文名稱: 不同深度學習演算法應用於細胞影像分割之比較與大腸桿菌質體分離實例分析
Comparison of Different Deep Learning Algorithms Applied to Cell Image Segmentation and Case Analysis of Plasmid Partition in Escherichia coli
指導教授: 張宜仁
Chang, Yi-Ren
口試委員: 邱顯智
Chiu, Hsiang-Chih
周家復
Chou, Chia-Fu
張宜仁
Chang, Yi-Ren
口試日期: 2022/07/15
學位類別: 碩士
Master
系所名稱: 物理學系
Department of Physics
論文出版年: 2022
畢業學年度: 110
語文別: 中文
論文頁數: 62
中文關鍵詞: 細胞縮時攝影深度學習影像分割多套數質體
英文關鍵詞: live cell time-lapse microscope, image segmentation, deep learning, highcopy number plasmid
研究方法: 實驗設計法
DOI URL: http://doi.org/10.6345/NTNU202201097
論文種類: 學術論文
相關次數: 點閱:110下載:18
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 活體細胞縮時攝影可以產生大量的數據,隨之而來的問題則是如何將影像中的細胞分割出來。在傳統影像處裡方面,Otsu演算法與分水嶺演算法 (Watershed Algorithm)是兩種常見的將影像二值化的方法。對於細胞影像分割,處在細胞較稠密或是緊鄰的狀態下,傳統影像處裡無法達到完美的細胞分割結果。因此,我們將深度學習中的電腦視覺應用於細胞影像分割,選擇了SuperSegger、Unet、Mask R-CNN這三種模型進行細胞分割的比較與分析。在這三種模型中,表現最出色的為Unet,並以此作為實例分析中影像處裡的基礎。
    在大腸桿菌質體分佈實例分析的部分,過去的研究顯示多套數質體並沒有類似低套數質體主動分離的機制,且有可能由轉錄或是轉譯所導致質體群聚的現象,因此多套數質體的穩定維持機制並不明確。我們以螢光抑制操作系統標記多套數的CoE1衍生質體,透過長時間的細胞縮時攝影實驗,搭配影像分割模型Unet,統計在有無抑制轉錄的情況下,子代細胞分配到親代細胞質體的比率。發現在抑制轉錄的情況下,質體分配的比率更集中在成功機率為1/2的二項分布寬度內。我們記錄了不同的養菌條件下,質體數量在細胞中成長的變化情形。盡管細胞在洋菜膠上仍然會分裂,但在細胞中質體數量比較多的情況時,細胞是傾向不消耗能量去複製質體。在細胞極性的統計實驗當中,我們發現新端細胞比舊端細胞有更容易獲得質體的趨勢,這個現象可能來自於細胞中類核在空間上的分布不均勻,且在第二次細胞分裂前,質體的聚集出現在靠近新端附近的頻率可能是比較高的,因此新端細胞會更有機會分配到較多的質體。

    Live cell time-lapse microscope can generate a lot of data, and the problem that comes with it is how to segment the cells in the image. In traditional image processing, Otsu algorithm and Watershed Algorithm are two common methods to binarize images. For cell image segmentation, when the cells are dense or in close, the traditional image processing methods cannot achieve perfect cell segmentation results. Therefore, we applied deep learning to cell image segmentation, and selected three models include SuperSegger, Unet, and Mask R-CNN to compare with each other and analyze their performance on cell segmentation. Among these three models, the best model is Unet, which is used as the basis for image processing in the following case analysis.
    In the part of the case analysis of E. coli plasmid partition, there is evidence that high-copy number plasmid does not have a mechanism similar to the active partition system of low-copy number plasmid. In addition, for high-copy number plasmid, there is an existence of aggregation which may be caused by transcription or translation. The mechanism of plasmid maintenance is still unclear. We labeled high-copy number of CoE1-derivative plasmid with the fluorescent repressor-operator systems. Through Live cell time-lapse microscope experiments, with the cell segmentation model Unet, we recorded the distribution of plasmid inheritance of daughter cells with or without transcription inhibition. It was found that in the case of transcription inhibition, the ratio of plasmid inheritance was more concentrated within the width of the binomial distribution with a success probability of 1/2. We recorded the growth rate of plasmid under different bacterial growth conditions. Although the cells division still occur on agar, when the number of plasmids in the cells is relatively large, the cells tend not to replicate the plasmid. In the section of cell polarity, we found that the new pole cells tend to obtain plasmids more easily than the old pole cells. This phenomenon may be caused by the uneven spatial distribution of nucleoids in the cells and the frequency of plasmid cluster in the new pole may be relatively high. Thus, the new pole cell has a better chance to inherit more plasmids.

    摘要 i Abstract ii 致謝 iv 目錄 v 圖目錄 viii 表目錄 xi 第一章 緒論 1 1.1 研究動機與目的 1 1.2 文章架構 3 第二章 深度學習介紹 4 2.1 神經網路(Neural Network) 4 2.2 卷積神經網路CNN (Convolutional Neural Network) 5 2.2.1 卷積層 (Convolution Layer) 6 2.2.2 池化層 (Pooling Layer) 7 2.2.3 全連接層 (Fully Connected Layer) 8 2.3 反向傳播 (Backpropagation) 8 第三章 文獻回顧與實例分析對象 11 3.1 SuperSegger 11 3.2 Unet & FCN (Fully Convolutional Networks) 12 3.3 R-CNN (Regions with Convolutional Neural Networks) 14 3.4 Fast R-CNN 15 3.5 Faster R-CNN 17 3.6 Mask R-CNN 18 3.7 實例分析對象之質體介紹 20 第四章 實驗設計與原理 22 4.1 質體螢光標記-FROS 22 4.2 抑制設計 23 4.3 類核螢光標記 24 第五章 實驗材料與方法 26 5.1 深度學習模型 26 5.1.1 訓練環境 26 5.1.2 資料集 27 5.1.3 資料增強(Data Augmentation) 28 5.1.4 模型評估方法 29 5.2 實驗樣品制備 31 5.2.1 質體 31 5.2.2 菌株 32 5.3 光學儀器 32 5.4 實驗操作與分析 33 5.4.1 單一質體螢光標記分佈 33 5.4.2 細胞內多套數質體數量分佈 34 5.4.3 抑制轉錄後,細胞內多套數質體數量分佈 35 第六章 實驗結果與討論 37 6.1 深度學習模型評估結果 37 6.2 大腸桿菌質體實例分析 41 6.2.1 單一質體螢光標記分佈 41 6.2.2 多套數質體細胞之子代細胞質體繼承 43 6.2.3 質體在細胞週期內複製情形 44 6.2.4 細胞中的極性 50 第七章 結論 58 參考文獻 60

    [1] N. Rosenfeld, J. W. Young, U. Alon, P. S. Swain, and M. B. Elowitz, "Gene regulation at the single-cell level," Science, vol. 307, no. 5717, pp. 1962-5, Mar 25 2005, doi: 10.1126/science.1106914.
    [2] F. M. Weinert, R. C. Brewster, M. Rydenfelt, R. Phillips, and W. K. Kegel, "Scaling of gene expression with transcription-factor fugacity," Phys Rev Lett, vol. 113, no. 25, p. 258101, Dec 19 2014, doi: 10.1103/PhysRevLett.113.258101.
    [3] A. Elfwing, Y. LeMarc, J. Baranyi, and A. Ballagi, "Observing growth and division of large numbers of individual bacteria by image analysis," Appl Environ Microbiol, vol. 70, no. 2, pp. 675-8, Feb 2004, doi: 10.1128/AEM.70.2.675-678.2004.
    [4] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979, doi: 10.1109/TSMC.1979.4310076.
    [5] J. B. T. M. Roerdink and A. Meijster, "The Watershed Transform: Definitions, Algorithms and Parallelization Strategies," Fundamenta Informaticae, vol. 41, pp. 187-228, 2000, doi: 10.3233/FI-2000-411207.
    [6] J. C. Caicedo et al., "Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl," Nature Methods, vol. 16, no. 12, pp. 1247-1253, 2019/12/01 2019, doi: 10.1038/s41592-019-0612-7.
    [7] T.-Y. Lin et al., "Microsoft COCO: Common Objects in Context," in Computer Vision – ECCV 2014, Cham, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds., 2014// 2014: Springer International Publishing, pp. 740-755.
    [8] S. Stylianidou, C. Brennan, S. B. Nissen, N. J. Kuwada, and P. A. Wiggins, "SuperSegger: robust image segmentation, analysis and lineage tracking of bacterial cells," Mol Microbiol, vol. 102, no. 4, pp. 690-700, Nov 2016, doi: 10.1111/mmi.13486.
    [9] K. He, G. Gkioxari, P. Dollár, and R. Girshick, "Mask R-CNN," in 2017 IEEE International Conference on Computer Vision (ICCV), 22-29 Oct. 2017 2017, pp. 2980-2988, doi: 10.1109/ICCV.2017.322.
    [10] O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Cham, N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi, Eds., 2015// 2015: Springer International Publishing, pp. 234-241.
    [11] C. Spahn et al., "DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches," Commun Biol, vol. 5, no. 1, p. 688, Jul 9 2022, doi: 10.1038/s42003-022-03634-z.
    [12] S. Yao, A. Toukdarian, and D. R. Helinski, "Inhibition of protein and RNA synthesis in Escherichia coli results in declustering of plasmid RK2," Plasmid, vol. 56, no. 2, pp. 124-32, Sep 2006, doi: 10.1016/j.plasmid.2006.04.003.
    [13] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, vol. 25, 2012.
    [14] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, no. 6088, pp. 533-536, 1986/10/01 1986, doi: 10.1038/323533a0.
    [15] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7-12 June 2015 2015, pp. 3431-3440, doi: 10.1109/CVPR.2015.7298965.
    [16] V. Dumoulin and F. Visin, "A guide to convolution arithmetic for deep learning," arXiv preprint arXiv:1603.07285, 2016.
    [17] R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," in 2014 IEEE Conference on Computer Vision and Pattern Recognition, 23-28 June 2014 2014, pp. 580-587, doi: 10.1109/CVPR.2014.81.
    [18] J. R. Uijlings, K. E. Van De Sande, T. Gevers, and A. W. Smeulders, "Selective search for object recognition," International journal of computer vision, vol. 104, no. 2, pp. 154-171, 2013.
    [19] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, "Support vector machines," IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18-28, 1998, doi: 10.1109/5254.708428.
    [20] R. Girshick, "Fast R-CNN," in 2015 IEEE International Conference on Computer Vision (ICCV), 7-13 Dec. 2015 2015, pp. 1440-1448, doi: 10.1109/ICCV.2015.169.
    [21] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 2017, doi: 10.1109/TPAMI.2016.2577031.
    [22] J. Shi and D. P. Biek, "A versatile low-copy-number cloning vector derived from plasmid F," Gene, vol. 164, no. 1, pp. 55-8, Oct 16 1995, doi: 10.1016/0378-1119(95)00419-7.
    [23] K. Nordstrom, "Plasmid R1--replication and its control," Plasmid, vol. 55, no. 1, pp. 1-26, Jan 2006, doi: 10.1016/j.plasmid.2005.07.002.
    [24] F. Bolivar, M. C. Betlach, H. L. Heyneker, J. Shine, R. L. Rodriguez, and H. W. Boyer, "Origin of replication of pBR345 plasmid DNA," Proc Natl Acad Sci U S A, vol. 74, no. 12, pp. 5265-9, Dec 1977, doi: 10.1073/pnas.74.12.5265.
    [25] J. Vieira and J. Messing, "The pUC plasmids, an M13mp7-derived system for insertion mutagenesis and sequencing with synthetic universal primers," Gene, vol. 19, no. 3, pp. 259-68, Oct 1982, doi: 10.1016/0378-1119(82)90015-4.
    [26] D. L. Coplin, "Plasmids and their role in the evolution of plant pathogenic bacteria," Annual review of phytopathology, vol. 27, pp. 187-212, 1989.
    [27] F. Silva, J. A. Queiroz, and F. C. Domingues, "Evaluating metabolic stress and plasmid stability in plasmid DNA production by Escherichia coli," Biotechnology advances, vol. 30, no. 3, pp. 691-708, 2012.
    [28] J. C. Diaz Ricci and M. E. Hernández, "Plasmid effects on Escherichia coli metabolism," Critical reviews in biotechnology, vol. 20, no. 2, pp. 79-108, 2000.
    [29] A. Fedorec, "Mechanisms for Plasmid Maintenance," 2014.
    [30] S. Yao, D. R. Helinski, and A. Toukdarian, "Localization of the naturally occurring plasmid ColE1 at the cell pole," Journal of bacteriology, vol. 189, no. 5, pp. 1946-1953, 2007.
    [31] A. F. Straight, A. S. Belmont, C. C. Robinett, and A. W. Murray, "GFP tagging of budding yeast chromosomes reveals that protein–protein interactions can mediate sister chromatid cohesion," Current Biology, vol. 6, no. 12, pp. 1599-1608, 1996.
    [32] A. B. Jung et al., imgaug. https://github.com/aleju/imgaug.

    下載圖示
    QR CODE