Please use this identifier to cite or link to this item:
DC FieldValueLanguage
dc.contributorShyr-Shen Yuen_US
dc.contributor.authorTzu-I Hoen_US
dc.identifier.citation[1] Jianwei Zhang,Zhenpeng Hu,Guoqiang Han Xiaozhen He.(2016). Segmentation of overlapping cells in cervical smears based on spatial relationship and Overlapping Translucency Light Transmission Model.60,286-295 [2] 蕃薯藤-yamNews , STARE:健談-106年兩性十大癌症死因|全民愛健康 十大癌症篇16, Retrieved 2018.[Online] Available : [3] World Health Organization (2011). cervical smears. From [4] 臺北市立聯合醫院癌症防治研究發展中心癌症資訊網仁愛院區, STARE:癌症預防與篩檢子宮頸癌簡介, Retrieved 2018.[Online] Available : [5] 衛生福利部國民健康屬, STARE:關心子宮頸癌, Retrieved 2018.[Online] Available : [6] ETtoday健康雲, STARE:何時開始檢查?女性必知的「子宮頸抹片Q&A」, Retrieved 2016.[Online] Available : [7] 衛生福利部國民健康屬, STARE:子宮頸癌篩檢及異常追蹤處置, Retrieved 2017.[Online] Available : [8] 嘉義長庚紀念醫院婦產科, STARE:子宮頸癌, Retrieved 2018.[Online] Available : [9] Classicus Dgical , STARE:HEALTH MANAGEMENT PVT. LTD. , Retrieved 2018.[Online] Available : [10] 460 Image References,RGB_model_0.gif.,[Online] Available : [11] Wikipedia Foundation, Inc.,YcbCr,July. 2018, [12] Zahid Tufail. Khawar Khurshid. Ahmad Salman. Imran Fareed Nizami. Khurram Khurshid. Byeungwoo Jeon.(2018) Improved Dark Channel Prior for Image Defogging Using RGB and YCbCr Color Space. IEEE Access, 32576 - 32587, DOT: 10.1109/ACCESS.2018.2843261 [13] Shuyuan Zhu, Mingyu Li, Chen Chen. Cross-Space. Shuaicheng Liu.Bing Zeng .(2017). Cross-Space Distortion Directed Color Image Compression. IEEE Transactions on Multimedia, 525-538, DOT: 10.1109/TMM.2017.2749162 [14] Hi-Fi Review, STARE:YCBCR / RGB?4:2:0 / 4:4:4 ?到底是什麼來的 ?Retrieved 2013.[Online] Available : [15] Wikipedia Foundation, Inc., Chroma subsampling,July. 2018, [16] Asli Kale, Selim Aksoy. (2010). Segmentation of Cervical Cell Images. 2010 20th International Conference on Pattern Recognition, DOI: 10.1109/ICPR.2010.587 [17] Shys-Fan Yang-Mao, Yung-Kuan Chan, Yen-Ping Chu.(2008). Edge Enhancement Nucleus and Cytoplast Contour Detector of Cervical Smear Images. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 353 – 366, DOT : 10.1109/TSMCB.2007.912940 [18] Ratna Saha, Mariusz Bajger, Gobert Lee. (2017). Circular shape constrained fuzzy clustering (CiscFC) for nucleus segmentation in Pap smear images.Computers in Biology and Medicine.85, 13-23 [19] Pranav Kumar, S L Happy, Swarnadip Chatterjee, Debdoot Sheet, Aurobinda Routray. (2016). An unsupervised approach for overlapping cervical cell cytoplasm segmentation. 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES), DOT : 10.1109/IECBES.2016.7843424 [20] Wikipedia Foundation, Inc., 大津演算法, Sep. 2017, [21] Marina E.Plissitia, Christophoros Nikoua, Antonia Charchantib. (2011). Combining shape, texture and intensity features for cell nuclei extraction in Pap smear images. Pattern Recognition Letters, 32, 6, 838-853 [22] Marina E. Plissiti, Christophoros Nikou, Antonia Charchanti. (2010). Automated Detection of Cell Nuclei in Pap Smear Images Using Morphological Reconstruction and Clustering. IEEE Transactions on Information Technology in Biomedicine, DOI: 10.1109/TITB.2010.2087030 [23] Wikipedia Foundation, Inc., Mathematical morphology, June 2018, [24] STARE:MM.Mathematical morphology [Online] Available : [25] Patrik Malm, Byju N.Balakrishnan, Vilayil K.Sujathan, Rajesh Kumar Ewert, Bengtsson .(2013). Debris removal in Pap-smear images. Computer Methods and Programs in Biomedicine, 111,1,128-138 [26] Meng-Husiun Tsai, Yung-Kuan Chan, Zhe-Zheng Lin, Shys-Fan Yang-Mao, Po-ChiHuang.(2008). Nucleus and cytoplast contour detector of cervical smear image. Pattern Recognition Letters, 29, 9, 1441-1453 [27] 拿著放大鏡看自己, STARE:影像處理:Component Labeling (標號) , Retrieved 2014.[Online] Available : [28] Marc Wang, STARE:Connected Component Labeling using OpenCV , Retrieved 2016.[Online] Available : [29] 阿摩, STARE:假設有一常態分佈母群體,其平均數為100 , Retrieved 2016.[Online] Available : [30] Wikipedia Foundation, Inc., normal distribution, June. 2018,
dc.description.abstract子宮頸癌在2017年國健署統計為十大女性第六常見的癌症之一。近年來,檢測子宮頸癌的技術提升,全自動分析的技術卻尚未更新,無法自動分割子宮頸細胞以便辨識。 自動分割單細胞須考量細胞核及細胞質,分割的效果都可以得到不錯的結果,然而當遇到多細胞的時候,由於群聚細胞的結構較為複雜,在分割細胞的時 後,較不容易分割,與單細胞分割不同,在分割群聚細胞的時候,只會考慮細胞核。 本研究的目的在於自動分割巴氏塗片-子宮頸抹片之群聚細胞,有助於醫生們之後進行辨識。實驗的影像是從4543張巴氏塗片-子宮頸抹片影像中選取5張影像,在影像中切割出子宮頸影像中雜質、單細胞、群聚細胞,本研究著重於群聚細胞。結果顯示,本研究得到分割的良好的效果。zh_TW
dc.description.abstractIn 2017, cervical cancer is one of the sixth most common cancers among the top ten women in the National Health Service. In recent years, the technology for detecting cervical cancer has improved and the technology of fully automatic analysis has not been updated and it is impossible to automatically segment cervical cells for identification. Automatic segmentation of single cells requires consideration of the nucleus and cytoplasm and the segmentation results can have good results. However, when multiple cells are encountered, the structure of the cluster cells is more complicated and it is less likely to be segmented after dividing the cells. Unlike the single cell segmentation, only the nuclei are considered when dividing the cluster cells. The purpose of this study was to automatically segment the cells of the Pap smear-cervical smear to help the doctors identify later. The experimental image was to select 5 images from 4543 Pap smear images and the impurities, single cells and cluster cells in the cervix image were cut out in the image. The study focused on cluster cells. The results show that this study has a good effect of segmentation.en_US
dc.description.tableofcontents誌謝...i 摘要...ii Abstract...iii 目錄...iv 圖目錄 表目錄...vii 第一章 緒論...1 1.1研究背景...1 1.2 研究動機與目的...4 1.3 論文架構...8 第二章相關文獻探討...9 2.1 RGB to YCbCr Color Space...9 2.2 Gamma equalization 強化對比...13 2.3 Otsu's method...15 2.4 Morphological Image Processing...17 2.4.1 Erosion(侵蝕)...17 2.4.2 dilation(膨脹)...18 2.4.3 Opening(斷開)...20 2.4.4 Closing(閉合)...21 2.5 影像標記Label- Connected Component...22 第三章 子宮頸抹片群聚細胞影像分割...27 3.1 程式架構...28 3.2 RGB to YCbCr...29 3.3 Gamma Equalization 強化對比...30 3.4 Otsu's method + Binary INV...32 3.5 Opening...33 3.6 影像標記(Label)...34 3.6.1 細胞分割...35 3.6.2母體標準差與信賴區間...37 第四章 實驗結果...41 4.1程式環境...41 4.1.1硬體設備...41 4.1.2開發環境...41 4.2 影像來源...42 4.3 實驗影像結果與參數設定...43 第五章 結論與未來展望...74 參考文獻...75zh_TW
dc.subject90% 信賴區間zh_TW
dc.subjectcervical canceren_US
dc.subjectcell cuttingen_US
dc.subject90% Confidence intervalen_US
dc.titleCluster Cells Segmentation in Pap Smear Imageen_US
dc.typethesis and dissertationen_US
Appears in Collections:資訊科學與工程學系所


Show simple item record
TAIR Related Article

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.