[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-339579-105":59,"doc-detail-339579-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","an-improved-approach-for-automated-cervical-cell-segmentation-with-pointrend","An improved approach for automated cervical cell segmentation with PointRend","","Regular cervical cancer screening relies on automated cytology analysis, where accurate cell cytoplasm segmentation remains difficult due to ambiguous boundaries in overlapping cell clumps. This study presents a convolutional neural network combining Mask R-CNN and PointRend to refine candidate boundary pixels using fine-grained and coarse features from multiple maps. On ISBI2014, the method reaches 0.97 DSC, 0.96 TPRp, 0.007 FPRp, and 0.006 FNRo, outperforming prior state-of-the-art approaches, with slightly improved performance on ISBI2015. Results support more reliable cytological evaluation and lesion discovery.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/an-improved-approach-for-automated-cervical-cell-segmentation-with-pointrend/339579/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/an-improved-approach-for-automated-cervical-cell-segmentation-with-pointrend/339579.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is automated cervical cytoplasm segmentation challenging?","Question",{"text":112,"@type":113},"Many boundaries between overlapping cervical cell clumps are difficult to identify or even indistinguishable, making precise segmentation hard.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What does the proposed model combine and how does it improve boundary detection?",{"text":117,"@type":113},"It uses a convolutional neural network based on Mask R-CNN with a PointRend module, concatenating fine-grained and coarse features to fine-tune candidate boundary pixels of cytoplasm.",{"name":119,"@type":110,"acceptedAnswer":120},"How well does the method perform on ISBI datasets?",{"text":121,"@type":113},"On ISBI2014 it achieves 0.97 DSC, 0.96 TPRp, 0.007 FPRp, and 0.006 FNRo, and it is reported to outperform state-of-the-art results; ISBI2015 performance is slightly better than the average of other approaches.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},339579,1790172157,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":41},5909877438554,"https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nAn improved approach for automated cervical cell segmentation with PointRend  \nBaocan Zhang1, Wenfeng Wang2,3*, Wei Zhao1, Xiaolu Jiang1 & Lalit Mohan Patnaik4  \nRegular screening for cervical cancer is one of the best tools to reduce cancer incidence. Automated cell segmentation in screening is an essential task because it can present better understanding of the characteristics of cervical cells. The main challenge of cell cytoplasm segmentation is that many boundaries in cell clumps are extremely difficult to be identified. This paper proposes a new convolutional neural network based on Mask RCNN and PointRend module, to segment overlapping cervical cells. The PointRend head concatenates fine grained features and coarse features extracted from different feature maps to fine-tune the candidate boundary pixels of cell cytoplasm, which are crucial for precise cell segmentation. The proposed model achieves a 0.97 DSC (Dice Similarity Coefficient), 0.96 TPRp (Pixelwise True Positive Rate), 0.007 FPRp (Pixelwise False Positive Rate) and 0.006 FNRo (Object False Negative Rate) on dataset from ISBI2014. Specially, the proposed method outperforms state-of-the-art result by about 􀀞 on DSC, 􀀞 on TPRp and 􀀞􀀝􀀜 on FNRo respectively. The performance metrics of our model on dataset from ISBI2015 are slight better than the average value of other approaches. Those results indicate that the proposed method could be effective in cytological analysis and then help experts correctly discover cervical cell lesions  \nKeywords Cytoplasm segmentation, PointRend, Overlapping cervical cells, Mask RCNN, ISBI  \nGlobally, cervical cancer is the fourth leading cause of death in women1. Cervical cytopathology tests can detect the cervical cancer in its early stage, which is essential for successful treatment. Cervical cancer screening techniques include papanicolaou test (Pap), human papillomavirus (HPV) test and histopathology test. New manual screening techniques such as TCT (Thinprep Cytologic Test) have been widely used nowadays to detect cancer. Traditionally, human experts examine the slides carefully under microscope, to determine the degree of precancerous lesions2. But this process is likely to be affected by many factors such as fatigue of eyes, resulting in misdiagnosis. So more robust automatic cervix type classification3 and cervical cell segmentation techniques are much needed. Cell segmentation can present much more detailed information about cervical cells than cervix type classification, to make it one of the most important techniques in cervical cancer screening.  \nThe detection of morphological features of the nucleus and cytoplasm is the core task of cervical cell pathological examination. Cytoplasmic characteristics have been shown to be critical for identifying abnormal cells4. The precise segmentation of cytoplasm in cervical cytology images is the essential part of cell segmentation. Once the edge of cytoplasm is located, quantitative evaluation such as cell diameter and rate of cell deformation can be calculated. Based on this information, pathologists can determine the degree of cervical cell lesions. Especially accurate segmentation of cytoplasm from cell clumps of high density in real EDF images can clearly present the shape and volume characteristics of cervical cells, which could tremendously improve the effectiveness of examining cervical cell screening clinically.  \nIn recent years, computer-aided diagnosis system has been utilized by pathologists to speed up the process of screening and examining. Generally, actual cervical cytology images often contain mucus, blood or other debris, and the cells in the images sometimes overlap with each other at a very high rate. In some cases, cell boundaries in clumps are extremely difficult to be identified, or even visually indistinguishable. Those facts make it a challenging task to precisely segment every ","cbCailCha9he7ES3","https://ap.wps.com/l/cbCailCha9he7ES3","pdf",5633244,12,"English","# Background and motivation\n## Challenge in cytoplasm segmentation\n## Need for robust automatic screening support\n\n# Proposed method\n## Mask R-CNN with PointRend refinement","[{\"question\":\"Why is automated cervical cytoplasm segmentation challenging?\",\"answer\":\"Many boundaries between overlapping cervical cell clumps are difficult to identify or even indistinguishable, making precise segmentation hard.\"},{\"question\":\"What does the proposed model combine and how does it improve boundary detection?\",\"answer\":\"It uses a convolutional neural network based on Mask R-CNN with a PointRend module, concatenating fine-grained and coarse features to fine-tune candidate boundary pixels of cytoplasm.\"},{\"question\":\"How well does the method perform on ISBI datasets?\",\"answer\":\"On ISBI2014 it achieves 0.97 DSC, 0.96 TPRp, 0.007 FPRp, and 0.006 FNRo, and it is reported to outperform state-of-the-art results; ISBI2015 performance is slightly better than the average of other approaches.\"}]","An improved approach for automated cervical cell segmentation with PointRend | PDF",1790031086]