[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85868-en":3,"doc-seo-85868-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85868,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",7,"Healthcare","Geometry-aware Gaussian Prior and Axial Attention for Cervical Cytology Image Classification","Accurate cervical cytology image classification is a key component of automated cervical cancer screening, enabling reliable recognition of normal, precancerous, and cancer-associated cellular patterns from Pap smear images. The task is difficult due to complex cell morphology, subtle intra-class variation, and strong inter-class similarity. Existing CNNs model local texture well but struggle with long-range dependencies, while attention methods lack explicit structural guidance. A geometry-aware framework is proposed using Gaussian expert modules to produce axis-wise structural priors from global semantic information, which are injected into an axial self-attention module to improve long-range modeling and structure-sensitive feature interaction. Experiments on Mendeley liquid-based cytology and SIPaKMeD achieve 99.48% and 96.08% accuracy, respectively.","arXiv :2607 . 10278v1 [ cs .CV] 11 Jul 2026  \nGeometry-aware Gaussian Prior and Axial Attention for Cervical Cytology Image Classification  \nYating Li 1 , Cheng Ye2 , Nenan Lyu3,B, Weidong Chen2,B, Zhendong Mao 1  \n1 School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China  \n2 School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China  \n3 Department of Gynecologic Oncology, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China  \nBCorresponding Author(s): Nenan Lyu, [lyunenan@cicams.ac.cn](lyunenan@cicams.ac.cn)  \nBB Corresponding Author(s): Weidong Chen, [chenweidong@ustc.edu.cn](chenweidong@ustc.edu.cn)  \nGraphical abstract  \nGraphicalAbstract content  \nAbstract  \nAccurate cervical cytology image classification is a key component of automated cervical cancer screening, where reliable recognition of normal, precancerous, and cancer-associated cellular patterns from Pap smear images can improve screening efficiency and diagnostic consistency. However, this task remains challenging because cervical cells exhibit complex morphology, subtle intra-class variations, and strong inter-class similarities. Existing convolution-based models capture local texture well but have limited ability to model long-range relationships, whereas attention-based models provide broader context but often lack explicit structural guidance. To address these limitations, we propose a geometry-aware classification framework for cervical cancer screening-oriented cytology image analysis, incorporating semantic abstraction and structural priors learned from pre-trained vision-language features. The method uses Gaussian expert modules to generate axis-wise priors from global semantic information, capturing structural regularities such as nuclear alignment and  \ncellular spatial organization. These priors are embedded into an axial self-attention module to modulate similarity computation along horizontal and vertical directions, improving long-range dependency modeling and structure-sensitive feature interaction. Experiments on the Mendeley liquid-based cytology and SIPaKMeD datasets show that the proposed method achieves 99.48% accuracy on the former and 96.08% on the latter, with balanced gains in recall, precision, and overall classification performance. Visual analysis further shows that the learned priors highlight diagnostically relevant cellular regions, demonstrating the potential of the proposed framework as a screening-oriented decision-support tool for cervical cytology.  \nKeywords  \nCervical cancer screening; Cervical cytology image classification; Pap smear; Gaussian priors; Axial self-attention; CLIP  \n1 Introduction  \nCervical cancer is one of the most common gynecological malignancies worldwide, with both high incidence and mortality rates, particularly in low-and middle-income countries. According to statistics, there were over 600,000 newly diagnosed cases and more than 300,000 deaths globally in 2020 [1] . At present, diagnosis primarily relies on expert pathologists manually examining Pap smear slides under a microscope. This process is time-consuming, labor-intensive, and subject to inter-observer variability, which increases the risk of misdiagnosis. Consequently, the development of efficient and reliable computer-aided diagnosis (CADx) systems has become an urgent necessity. In this context, automated cervical cytology image classification has attracted significant attention as a key component of computer-assisted cervical cancer screening, since accurate recognition of abnormal cellular morphology can improve screening efficiency, reduce inter-observer variability, and provide reliable decision support for cytological assessment. Compared with conventional computer vision tasks, screening-oriented cervical cytol","cbCais0pUzRKlIHM","https://ap.wps.com/l/cbCais0pUzRKlIHM","pdf",1785041,1,39,"English","en",105,"# Introduction\n## Challenges in cervical cytology image classification\n## Proposed geometry-aware framework","[{\"question\":\"What makes cervical cytology image classification challenging?\",\"answer\":\"Cervical cells show complex morphology, subtle variations within the same class, and strong similarities across different classes, which makes discrimination difficult.\"},{\"question\":\"How does the proposed method incorporate geometry information?\",\"answer\":\"Gaussian expert modules generate axis-wise priors from global semantic features, and these priors are embedded into an axial self-attention module to guide similarity computation along horizontal and vertical directions.\"},{\"question\":\"What performance does the method achieve on public datasets?\",\"answer\":\"On Mendeley liquid-based cytology it reaches 99.48% accuracy, and on SIPaKMeD it achieves 96.08%, with balanced improvements across recall, precision, and overall classification.\"}]",1784206810,98,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"geometry-aware-gaussian-prior-and-axial-attention-for-cervical-cytology-image-classification","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/healthcare/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/geometry-aware-gaussian-prior-and-axial-attention-for-cervical-cytology-image-classification/85868/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What makes cervical cytology image classification challenging?","Question",{"text":74,"@type":75},"Cervical cells show complex morphology, subtle variations within the same class, and strong similarities across different classes, which makes discrimination difficult.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed method incorporate geometry information?",{"text":79,"@type":75},"Gaussian expert modules generate axis-wise priors from global semantic features, and these priors are embedded into an axial self-attention module to guide similarity computation along horizontal and vertical directions.",{"name":81,"@type":72,"acceptedAnswer":82},"What performance does the method achieve on public datasets?",{"text":83,"@type":75},"On Mendeley liquid-based cytology it reaches 99.48% accuracy, and on SIPaKMeD it achieves 96.08%, with balanced improvements across recall, precision, and overall classification.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":115,"slug":116},40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]