[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85442-en":3,"doc-seo-85442-105":30,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85442,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782698725881665579",8,"Research & Report","Segmentation and Classification of Pap Smear Images for Cervical Cancer Detection Using Deep Learning","Cervical cancer remains a major global health threat, and reducing mortality depends on early detection via Pap smear testing. Manual slide review is slow, error-prone, and affected by inter-observer variability. The study presents a deep learning framework combining U-Net-based segmentation with a classification model to improve diagnostic accuracy. Using the Herlev Pap Smear Dataset, segmented-image training was compared with non-segmented training; segmentation yields marginal gains in precision (+0.41%) and F1-score (+1.30%), suggesting limited impact on classification performance while supporting feature extraction.","Proceedings of theIISE Annual Conference & Expo 2025  \nE. Gentry, F. Ju, X. Liu, eds.  \nSegmentation and Classification of Pap Smear Images for Cervical Cancer Detection Using Deep Learning  \nNisreen Albzour and Sarah S. Lam  \nBinghamton University, Binghamton, NY, USA  \nAbstract  \nCervical cancer remains a significant global health concern and a leading cause of cancer-related deaths among women. Early detection through Pap smear tests is essential to reduce mortality rates; however, the manual examination is timeconsuming and prone to human error. This study proposes a deep learning framework that integrates U-Net for segmentation and a classification model to enhance diagnostic performance. The Herlev Pap Smear Dataset, a publicly available cervical cell dataset, was utilized for training and evaluation. The impact of segmentation on classification performance was evaluated by comparing the model trained on segmented images and another trained on non-segmented images. Experimental results showed that the use of segmented images marginally improved the model’s performance on precision (+0.41%) and F1-score (+1.30%), which suggests a slightly more balanced classification performance. While segmentation helps in feature extraction, this research’s results showed that its impact on classification performance appears to be limited. The proposed framework offers a supplemental tool for clinical applications, which aids pathologists in early diagnosis.  \nKeywords  \nCervical cancer, convolutional neural networks, segmentation, deep learning, neural network architecture  \n1. Introduction  \nCervical cancer remains a significant global health challenge, in which over 600,000 new cases and 340,000 deaths are reported annually [1]. The primary strategy to reduce mortality is early detection through Pap smear tests, which enable the identification of precancerous lesions. However, manual analysis of Pap smear slides is time-consuming, prone to human error, and subject to inter-observer variability, which highlights the need for automated diagnostic solutions [2, 3] .  \nDeep Learning (DL), particularly Convolutional Neural Networks (CNNs), has revolutionized medical image analysis by providing efficient and accurate diagnostic tools [4, 5] . CNNs have demonstrated remarkable success in detecting cancerous patterns within medical images, which surpass traditional machine learning methods by automatic extraction of hierarchical features [6, 7] . Automated and hyperautomation-based AI pipelines have further extended these capabilities to other medical-imaging domains, such as hematologic malignancy detection [8, 9] . Additionally, preprocessing techniques such as segmentation enhance CNN performance by isolating diagnostically relevant regions and minimizing background noise [10, 11] . Studies have also shown that data augmentation techniques—such as rotation, flipping, and scaling—help improve model robustness and address class imbalance, which further enhance classification accuracy [12, 13] . Moreover, advanced feature selection methods such as metaheuristic algorithms optimize classification performance, which ensures the model focuses on the most relevant information [14]; such feature-selection strategies have likewise improved predictive performance in other clinical machinelearning applications, including post-stroke rehabilitation outcome prediction [15] .  \nThis study employs the Herlev Pap Smear Dataset to develop a binary classification framework that distinguishes between normal and abnormal cervical cells. To refine segmentation quality, preprocessing techniques—including adaptive thresholding, Gaussian blurring, and morphological transformations—are applied. Furthermore, Class Activation Maps (CAMs) improve model interpretability by highlighting critical regions that influence classification decisions [16] . Explainable AI methods are increasingly being integrated into deep learning frameworks to enhance transparency and clini","cbCaiiFQiGWG2Tle","https://ap.wps.com/l/cbCaiiFQiGWG2Tle","pdf",523604,3,1,6,"English","en",105,"# Introduction\n## Problem background and motivation\n## Deep learning and related approaches\n## Study approach and framework overview\n# Methodology\n## Dataset description","[{\"question\":\"What problem does this research address in cervical cancer screening?\",\"answer\":\"It targets the limitations of manual Pap smear slide examination, including time consumption, human error, and inter-observer variability, by proposing an automated deep learning diagnostic framework.\"},{\"question\":\"How does the proposed framework combine segmentation and classification?\",\"answer\":\"It integrates U-Net for image segmentation with a classification model, then compares performance when training uses segmented images versus non-segmented images.\"},{\"question\":\"What dataset and evaluation method are used, and what is the main result?\",\"answer\":\"The Herlev Pap Smear Dataset is used for training and evaluation. Segmentation improves precision by +0.41% and F1-score by +1.30%, indicating only marginal gains and a limited effect on classification performance.\"}]",1784203550,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"segmentation-and-classification-of-pap-smear-images-for-cervical-cancer-detection-using-deep-learning","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/segmentation-and-classification-of-pap-smear-images-for-cervical-cancer-detection-using-deep-learning/85442/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does this research address in cervical cancer screening?","Question",{"text":75,"@type":76},"It targets the limitations of manual Pap smear slide examination, including time consumption, human error, and inter-observer variability, by proposing an automated deep learning diagnostic framework.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed framework combine segmentation and classification?",{"text":80,"@type":76},"It integrates U-Net for image segmentation with a classification model, then compares performance when training uses segmented images versus non-segmented images.",{"name":82,"@type":73,"acceptedAnswer":83},"What dataset and evaluation method are used, and what is the main result?",{"text":84,"@type":76},"The Herlev Pap Smear Dataset is used for training and evaluation. Segmentation improves precision by +0.41% and F1-score by +1.30%, indicating only marginal gains and a limited effect on classification performance.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]