請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82016完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 顏家鈺(Jia-Yush Yen) | |
| dc.contributor.author | Yen-Han Wang | en |
| dc.contributor.author | 汪彥瀚 | zh_TW |
| dc.date.accessioned | 2022-11-25T05:34:08Z | - |
| dc.date.available | 2024-09-01 | |
| dc.date.copyright | 2021-11-09 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-06 | |
| dc.identifier.citation | T. E. o. E. Britannica. (2019, Cell culture. Encyclopedia Britannica. Available: https://www.britannica.com/science/cell-culture T. E. o. E. Britannica. (2015, Tissue culture. Encyclopedia Britannica. Available: https://www.britannica.com/science/tissue-culture A. Hima Bindu and B. Srilatha, 'Potency of various types of stem cells and their transplantation,' J Stem Cell Res Ther, vol. 1, 2011. K. Kalra and P. Tomar, 'Stem cell: basics, classification and applications,' American Journal of Phytomedicine and Clinical Therapeutics, vol. 2, pp. 919-930, 2014. J. Yu, K. Hu, K. Smuga-Otto, S. Tian, R. Stewart, I. I. Slukvin, et al., 'Human induced pluripotent stem cells free of vector and transgene sequences,' Science, vol. 324, pp. 797-801, 2009. A. Ibrayeva, M. Bay, E. Pu, D. J. Jörg, L. Peng, H. Jun, et al., 'Early stem cell aging in the mature brain,' Cell Stem Cell, 2021. D. Kami, K. Watakabe, M. Yamazaki-Inoue, K. Minami, T. Kitani, Y. Itakura, et al., 'Large-scale cell production of stem cells for clinical application using the automated cell processing machine,' BMC biotechnology, vol. 13, p. 102, 2013. S. Konagaya, T. Ando, T. Yamauchi, H. Suemori, and H. Iwata, 'Long-term maintenance of human induced pluripotent stem cells by automated cell culture system,' Scientific reports, vol. 5, pp. 1-9, 2015. M. E. Kempner and R. A. Felder, 'A review of cell culture automation,' JALA: Journal of the Association for Laboratory Automation, vol. 7, pp. 56-62, 2002. BioTek. automated system. Available: https://www.biotek.tw/zh-TW/products/robotics-category/ DENSO. automated cell culture system. Available: https://www.denso-wave.com/ja/robot/katsuyou/medical.html INTEGRA. Pipetting Robots. Available: https://www.integra-biosciences.com/global/en/pipetting-robots S. A. Green, M. Billinghurst, X. Chen, and J. G. Chase, 'Human-robot collaboration: A literature review and augmented reality approach in design,' International journal of advanced robotic systems, vol. 5, p. 1, 2008. A. Ajoudani, A. M. Zanchettin, S. Ivaldi, A. Albu-Schäffer, K. Kosuge, and O. Khatib, 'Progress and prospects of the human–robot collaboration,' Autonomous Robots, vol. 42, pp. 957-975, 2018. Z. Nan and Q. Xu, 'Multiple-cell recognition and path planning for robotic microinjection system,' in 2017 36th Chinese Control Conference (CCC), 2017, pp. 6691-6696. U. Marx, F. Schenk, J. Behrens, U. Meyr, P. Wanek, W. Zang, et al., 'Automatic production of induced pluripotent stem cells,' Procedia CIRP, vol. 5, pp. 2-6, 2013. M. S. Kavitha, T. Kurita, S.-Y. Park, S.-I. Chien, J.-S. Bae, and B.-C. Ahn, 'Deep vector-based convolutional neural network approach for automatic recognition of colonies of induced pluripotent stem cells,' PloS one, vol. 12, p. e0189974, 2017. R. Nagasaka, M. Matsumoto, M. Okada, H. Sasaki, K. Kanie, H. Kii, et al., 'Visualization of morphological categories of colonies for monitoring of effect on induced pluripotent stem cell culture status,' Regenerative Therapy, vol. 6, pp. 41-51, 2017. M. Gamarra, E. Zurek, and H. San Juan, 'Cell identification using image analysis: A literature survey,' in 2017 12th Iberian Conference on Information Systems and Technologies (CISTI), 2017, pp. 1-7. J. Chen, S. Banerjee, A. Grama, W. J. Scheirer, and D. Z. Chen, 'Neuron segmentation using deep complete bipartite networks,' in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2017, pp. 21-29. K. Paeng, S. Hwang, S. Park, and M. Kim, 'A unified framework for tumor proliferation score prediction in breast histopathology,' in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, ed: Springer, 2017, pp. 231-239. H. Chen, Q. Dou, X. Wang, J. Qin, and P. A. Heng, 'Mitosis detection in breast cancer histology images via deep cascaded networks,' in Thirtieth AAAI conference on artificial intelligence, 2016. N. Meng, E. Y. Lam, K. K. Tsia, and H. K.-H. So, 'Large-scale multi-class image-based cell classification with deep learning,' IEEE journal of biomedical and health informatics, vol. 23, pp. 2091-2098, 2018. Y. Lu, A.-A. Liu, M. Chen, W.-Z. Nie, and Y.-T. Su, 'Sequential Saliency Guided Deep Neural Network for Joint Mitosis Identification and Localization in Time-Lapse Phase Contrast Microscopy Images,' IEEE Journal of Biomedical and Health Informatics, vol. 24, pp. 1367-1378, 2019. O. Ronneberger, P. Fischer, and T. Brox, 'U-net: Convolutional networks for biomedical image segmentation,' in International Conference on Medical image computing and computer-assisted intervention, 2015, pp. 234-241. T. Falk, D. Mai, R. Bensch, Ö. Çiçek, A. Abdulkadir, Y. Marrakchi, et al., 'U-Net: deep learning for cell counting, detection, and morphometry,' Nature methods, vol. 16, pp. 67-70, 2019. M. Majurski, P. Manescu, S. Padi, N. Schaub, N. Hotaling, C. Simon Jr, et al., 'Cell image segmentation using generative adversarial networks, transfer learning, and augmentations,' in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019, pp. 0-0. G. Patel, H. Tekchandani, and S. Verma, 'Cellular segmentation of bright-field absorbance images using residual u-net,' in 2019 International Conference on Advances in Computing, Communication and Control (ICAC3), 2019, pp. 1-5. T. Piotrowski, O. Rippel, A. Elanzew, B. Nießing, S. Stucken, S. Jung, et al., 'Deep-learning-based multi-class segmentation for automated, non-invasive routine assessment of human pluripotent stem cell culture status,' Computers in Biology and Medicine, vol. 129, p. 104172, 2021. MiSUMi web page. Available: https://us.misumi-ec.com/ J. A. Thomson, J. Itskovitz-Eldor, S. S. Shapiro, M. A. Waknitz, J. J. Swiergiel, V. S. Marshall, et al., 'Embryonic stem cell lines derived from human blastocysts,' science, vol. 282, pp. 1145-1147, 1998. CS231n Convolutional Neural Networks for Visual Recognition. Available: https://cs231n.github.io/convolutional-networks/#conv M. Daoust. tf.contrib.layers.conv2d (Tensorflow 1.4.0). Available: https://github.com/tensorflow/docs/blob/r1.4/site/en/api_docs/api_docs/python/tf/contrib/layers/conv2d.md M. Daoust. tf.contrib.layers.max_pool2d (Tensorflow 1.4.0). Available: https://github.com/tensorflow/docs/blob/r1.4/site/en/api_docs/api_docs/python/tf/contrib/layers/max_pool2d.md M. Daoust. tf.contrib.layers.conv2d_transpose (Tensorflow 1.4.0). Available: https://github.com/tensorflow/docs/blob/r1.4/site/en/api_docs/api_docs/python/tf/contrib/layers/conv2d_transpose.md J. Akeret, C. Chang, A. Lucchi, and A. Refregier, 'Radio frequency interference mitigation using deep convolutional neural networks,' Astronomy and computing, vol. 18, pp. 35-39, 2017. J. Akeret. tf_unet. Available: https://github.com/jakeret/tf_unet M. Daoust. Tensorflow 1.4.0. Available: https://github.com/tensorflow/docs/tree/r1.4/site/en/api_docs M. Daoust. tf.nn.softmax_cross_entropy_with_logits (Tensorflow 1.4.0). Available: https://github.com/tensorflow/docs/blob/r1.4/site/en/api_docs/api_docs/python/tf/nn/softmax_cross_entropy_with_logits.md M. Daoust. tf.train.AdamOptimizer (Tensorflow 1.4.0). Available: https://github.com/tensorflow/docs/blob/r1.4/site/en/api_docs/api_docs/python/tf/train/AdamOptimizer.md | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82016 | - |
| dc.description.abstract | 幹細胞及其在醫療用途上之潛能為近幾年來的熱門話題,這是因為它具備了自我更新及分化的特性。自我更新就是可以分裂成它自己,分化就是可以分裂成其他類型的細胞。然而,不同幹細胞的自我更新及分化特性亦不相同,需要科學家深入研究來掌握其特性。本論文藉由觀察專家每日培養幹細胞的流程,發現幹細胞培養是很繁瑣的,培養的人員需要每天不間斷的去照顧它,每日的照顧動作包含了更換培養液與觀察細胞培養之狀態。由於需要每天去照顧幹細胞,以至於細胞培養人員在假日的時候都無法正常休息。因此,如何將培養幹細胞的流程以自動化之設備來實現,是一個值得研究的題目。 藉由觀察專家每日更換細胞培養液的流程,本論文將每日更換培養液的流程拆解成了兩個部分,分別為手動操作移液器更換培養液的部分以及將培養皿放在相位差顯微鏡下觀察細胞培養狀態的部分。在分析了專家手動更換培養液的動作後,可得人類手臂的動作包含了:拿取/放置培養皿、培養皿蓋與移液器;以及操作移液器來進行培養皿的移液動作。本論文選擇了使用六軸之機械手臂來達成前述之動作,亦即使用機器手臂來模擬人類專家每天更換培養液之動作。為使動作可以順利達成,設計了可以同時拿取/放置培養皿、培養皿蓋以及移液器的電磁夾爪;並同時設計了與之搭配的夾治具以及其他相對應之配件來實現自動化更換培養液之流程。機器手臂在經過程式的撰寫後,可以達成所設計之人類手臂每日更換培養液之動作。在此,使用六自由度機械手臂做為細胞培養之平台,可提供更多的姿勢與動作流程的彈性,使系統更能適應實驗室等級的細胞培養數量。 至於人類觀察細胞培養情況之流程,則是使用U-Net為基礎之人工神經網路來對不同的細胞群落區域進行分割。分割的細胞群落區域包含:健康的幹細胞區域、分化的幹細胞區域、不確定的細胞區域與背景區域。而分割出來的結果可用來協助自動化系統判斷細胞培養之狀態。U-Net人工神經網路在五組相位差顯微細胞影像以及其所對應之區域分割遮罩(segmentation mask)的註記下進行訓練。訓練過後之U-Net神經網路對測試之三張相位差顯微細胞影像分別進行了標註,並獲得了不錯的標註結果。 本論文使用了六軸機械手臂來模擬人類手臂進行每日更換細胞培養液的流程;而人類觀察細胞培養之狀態,則使用了U-Net人工神經網路來對細胞群落進行分割。分割之結果可以協助培養系統來判斷細胞培養之狀態,使系統可以進一步決定該繼續培養下去,或者放棄此培養皿所培養之細胞。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-25T05:34:08Z (GMT). No. of bitstreams: 1 U0001-0608202109501400.pdf: 28557860 bytes, checksum: 943a19027d935eead905fb4490dd237d (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 致謝 i 摘要 iii Abstract v Table of Contents ix List of Figures xii List of Tables xvi Chapter 1 Introduction 1 1.1 Motivations 1 1.1.1 History of Cell Culture 1 1.1.2 Stem Cells 2 1.1.3 Automated Cell Culturing System 3 1.1.4 Motivations of Dissertation 4 1.2 Research Method and Objective 5 1.3 Literature Review 6 1.3.1 Automated Cell Culturing Systems 6 1.3.2 Cell Identification 7 1.4 Dissertation Structure 9 Chapter 2 Robotic Cell Culture System 11 2.1 Everyday Stem Cell Culture Procedure 11 2.2 Automatic Cell Culture System Structure 13 2.3 Robotic Arm 16 2.4 End Effector and Jig Pairs 18 2.4.1 Electromagnetic Gripper Design 18 2.4.2 First Design of Jig Pairs 20 2.4.3 Second Design of Jig Pairs 23 2.4.4 Third Design of Jig Pairs 27 2.5 Other Components 29 2.5.1 Pipette 29 2.5.2 Petri Dish Place Position and Base of Petri Dish Cover 33 2.5.3 Base 35 2.6 Robotic Arm Programming 36 2.7 Experimental Results 43 Chapter 3 Machine Vision via Artificial Intelligence 45 3.1 U-Net Structure 46 3.2 U-Net Input-Output Relation 47 3.3 Training Process 48 3.3.1 Training Images 48 3.3.2 Cropping of the Training Image 51 3.3.3 U-Net Training 52 3.4 Evaluation Process 54 3.4.1 Evaluation Data 54 3.4.2 Evaluation Results 57 3.5 Testing Process 62 3.5.1 Testing Data 62 3.5.2 Testing Results 64 3.6 Consumption of the U-Net Labeling Time 75 3.7 Application to the Segmentation of Large Area Stem Cell Colonies 77 3.7.1 Research Devices and Method 77 3.7.2 Images Stitching 78 3.7.3 Cell Images 81 3.7.4 Large Area Stem Cell Colonies Segmentation Process and Results 83 Chapter 4 Conclusions and Future Works 89 4.1 Conclusions 89 4.2 Future Works 90 References 93 Appendix A Details of the U-Net 97 Appendix B Details of the U-Net Input Mismatch 101 | |
| dc.language.iso | en | |
| dc.subject | 人工神經網路 | zh_TW |
| dc.subject | 細胞培養 | zh_TW |
| dc.subject | 幹細胞 | zh_TW |
| dc.subject | 誘導性多能幹細胞 | zh_TW |
| dc.subject | 自動化 | zh_TW |
| dc.subject | 影像分割 | zh_TW |
| dc.subject | segmentation | en |
| dc.subject | artificial neural network | en |
| dc.subject | cell culture | en |
| dc.subject | stem cell | en |
| dc.subject | induced Pluripotent Stem Cell (iPSC) | en |
| dc.subject | automation | en |
| dc.title | 人工智能機械手臂應用於人類幹細胞培養系統之設計 | zh_TW |
| dc.title | The Design of an Artificial Intelligence Robotic Human Stem Cell Culturing System | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 博士 | |
| dc.contributor.oralexamcommittee | 陳晉興(Hsin-Tsai Liu),陳佑宗(Chih-Yang Tseng),王富正,劉書宏 | |
| dc.subject.keyword | 細胞培養,幹細胞,誘導性多能幹細胞,自動化,影像分割,人工神經網路, | zh_TW |
| dc.subject.keyword | cell culture,stem cell,induced Pluripotent Stem Cell (iPSC),automation,segmentation,artificial neural network, | en |
| dc.relation.page | 103 | |
| dc.identifier.doi | 10.6342/NTU202102138 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-08-06 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 機械工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2024-09-01 | - |
| 顯示於系所單位: | 機械工程學系 | |
文件中的檔案:
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0608202109501400.pdf 授權僅限NTU校內IP使用(校園外請利用VPN校外連線服務) | 27.89 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。
