Please use this identifier to cite or link to this item:
標題: 子宮頸抹片群聚細胞影像分割
Cluster Cells Segmentation in Pap Smear Image
作者: 何姿儀 
Tzu-I Ho 
關鍵字: 子宮頸癌;細胞切割;影像標記;90% 信賴區間;cervical cancer;cell cutting;Label;90% Confidence interval
引用: [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,

In 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.
Rights: 同意授權瀏覽/列印電子全文服務,2021-11-26起公開。
Appears in Collections:資訊科學與工程學系所

Files in This Item:
File SizeFormat Existing users please Login
nchu-107-7104056059-1.pdf4.1 MBAdobe PDFThis file is only available in the university internal network    Request a copy
Show full item record

Google ScholarTM


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