[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-352770-105":59,"doc-detail-352770-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","lungnet-leveraging-state-space-models-with-se-enhanced-skip-connections-for-precise-ct-based-lung-lesion-segmentation","LungNet: Leveraging state-space models with SE-enhanced skip connections for precise CT-based lung lesion segmentation","","LungNet presents a deep learning framework for accurate CT-based lung lesion segmentation in the context of lung cancer, a leading cause of mortality worldwide. It targets limitations of CNN receptive fields and the high computational burden of Transformer models on high-resolution CT volumes, while also addressing UNet skip-connection redundancy that can dilute subtle lesion cues. The method combines Mamba state-space modeling with an improved UNet, SE-enhanced skip connections, and auxiliary losses to improve shallow feature preservation and fine-grained detail capture. Experiments on multiple datasets show state-of-the-art accuracy and support for improved early detection, monitoring, and treatment planning.",{"@graph":69,"@context":123},[70,84,106],{"@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":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/lungnet-leveraging-state-space-models-with-se-enhanced-skip-connections-for-precise-ct-based-lung-lesion-segmentation/352770/",{"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/lungnet-leveraging-state-space-models-with-se-enhanced-skip-connections-for-precise-ct-based-lung-lesion-segmentation/352770.png","ImageObject",300,407,{"name":92,"@type":93},"Quinn Holloway","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-19","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does LungNet address in lung lesion segmentation?","Question",{"text":113,"@type":114},"It addresses the difficulty of accurately segmenting heterogeneous lung lesions from CT images, especially the failure modes of common deep learning architectures such as limited long-range dependency capture and redundant noise from UNet skip connections.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does LungNet improve upon conventional UNet skip connections?",{"text":118,"@type":114},"It embeds Squeeze-and-Excitation (SE) networks into skip connections to reduce feature redundancy and better preserve subtle lesion characteristics.",{"name":120,"@type":111,"acceptedAnswer":121},"What benefits does the proposed framework provide according to experimental results?",{"text":122,"@type":114},"Experiments on multiple datasets demonstrate state-of-the-art segmentation accuracy and suggest improved support for early detection, ongoing disease monitoring, and treatment planning in lung cancer patients.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},352770,1790847415,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":36,"preview_page_count":19,"preview_urls":146},2336474466712,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","OPEN ACCESS  \nCitation: Mi F, Xu Y, Mi S (2026) LungNet: Leveraging state-space models with SEenhanced skip connections for precise  \nCT-based lung lesion segmentation. PLoS One 21(4): e0346561. [https://doi.org/10.1371/](https://doi.org/10.1371/)[ ](https://doi.org/10.1371/)[journal.pone.0346561](journal.pone.0346561)  \nEditor: Junhuang Jiang, Jinan University College of Pharmacy, CHINA  \nReceived: October 14, 2025  \nAccepted: March 19, 2026  \nPublished: April 16, 2026  \nCopyright: This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 public domain dedication.  \nData availability statement: The data underlying the results presented in the study are available from third-party sources. Specifically, the CT segmentation dataset is available at [http://medicalsegmentation.com/covid19/](http://medicalsegmentation.com/covid19/), the Segmentation dataset nr.2 is available at [http://](http://)  \nRESEARCH ARTICLE  \nLungNet: Leveraging state-space models with SE-enhanced skip connections for precise CT-based lung lesion segmentation  \nFei Mi1*, Yuan Xu2, Shuanghong Mi2  \n1 Guangdong Medical University, Dongguan, China, 2 Dongguan City University, Dongguan, China  \n* [18676284541@163.com](18676284541@163.com)  \nAbstract  \nLung cancer, which accounted for 2.48 million new cases and 1.82 million deaths worldwide in 2022, continues to be the most lethal cancer across the globe, underscoring the urgent demand for more advanced diagnostic tools. Although computed tomography (CT) imaging has long been central to lung cancer detection, the heterogeneous and complex characteristics of lung lesions make accurate segmentation particularly challenging. Current deep learning methods face a critical bottleneck:  \nconvolutional neural networks (CNNs) often struggle to capture long-range dependencies due to limited receptive fields, while Transformer-based architectures incur prohibitive computational costs when processing high-resolution CT volumes. Furthermore, standard skip connections in traditional UNet models frequently introduce redundant noise, leading to the dilution of subtle lesion features. To address these specific technical gaps, we introduce a novel deep learning framework that integrates Mamba state-space models with an improved UNet architecture. In this design, to mitigate feature redundancy, Squeeze-and-Excitation networks are embedded into skip connections, while auxiliary losses are introduced to address the degradation of shallow features and capture fine-grained lesion features across varied morphologies. Such a framework not only accommodates the intricate differences in lesion size, shape, and spatial distribution but also achieves a balance between global context modeling and linear computational efficiency. By uniting the local feature extraction strengths of convolutional layers with the long-range dependency modeling power of state-space models, our approach achieves more precise delineation of lung lesion boundaries. Extensive experiments conducted on multiple datasets provide compelling evidence of the method’s effectiveness: it attains state-of-theart segmentation accuracy and demonstrates significant promise for enhancing early detection, ongoing disease monitoring, and treatment planning in lung cancer patients. This advancement delivers a robust solution for the inherently complex task of lung lesion segmentation. Moreover, because lung cancer treatment is costly and  \nPLOS One | [https://doi.org/10.1371/journal.pone.0346561](https://doi.org/10.1371/journal.pone.0346561) April 16, 2026 1 / 16  \n[medicalsegmentation.com/covid19/](medicalsegmentation.com/covid19/), the CT-Seg dataset is available at [https://zenodo.org/](https://zenodo.org/)[ ](https://zenodo.org/)[records/3757476/](records/3757476/), and the CC-II segmentation data","cbCaiaY9OBXoQRg2","https://ap.wps.com/l/cbCaiaY9OBXoQRg2","pdf",1164556,16,"English","# Abstract\n# Introduction","[{\"question\":\"What problem does LungNet address in lung lesion segmentation?\",\"answer\":\"It addresses the difficulty of accurately segmenting heterogeneous lung lesions from CT images, especially the failure modes of common deep learning architectures such as limited long-range dependency capture and redundant noise from UNet skip connections.\"},{\"question\":\"How does LungNet improve upon conventional UNet skip connections?\",\"answer\":\"It embeds Squeeze-and-Excitation (SE) networks into skip connections to reduce feature redundancy and better preserve subtle lesion characteristics.\"},{\"question\":\"What benefits does the proposed framework provide according to experimental results?\",\"answer\":\"Experiments on multiple datasets demonstrate state-of-the-art segmentation accuracy and suggest improved support for early detection, ongoing disease monitoring, and treatment planning in lung cancer patients.\"}]","LungNet: Leveraging state-space models with SE-enhanced skip connections for precise CT-based lung lesion segmentation | PDF",1790101292,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2c90851064667a830779003604b2a3b1.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a342aa363cb7f3b8fffc6427194116ec.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4d14a464a3e254e7599e2699caf07d95.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/eb0906dcf545b2c20bdff837b58eed76.webp",980,1268]