[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84244-en":3,"doc-seo-84244-105":29,"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":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},84244,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Automatic Echocardiography Segmentation via Transition Probability Correlation for Stable Semantic Extraction","Echocardiography plays a critical role in cardiovascular diagnosis, yet speckle noise and low signal-to-noise ratio produce ambiguous semantic cues and fragmented boundaries that limit deep learning segmentation in complex clinical scenarios. Heart motion further affects recognition of anatomical structures. A STLSF module is introduced with window-matching semantic correction and semantics-guided texture enhancement using local transition probability correlations. A frequency-aware denoising pre-training strategy adapts encoders to ultrasound priors. A convolutional network with locality bias and long-range dependencies achieves 93.87% Dice on CAMUS and 92.62% on EchoNetDynamic with HD95 of 3.29 mm and 2.73 mm.","arXiv :2607 .07580v 1 [ cs .CV] 8 Jul 2026  \nAutomatic Echocardiography Segmentation via Transition Probability Correlation for Stable Semantic Extraction  \nXinran Chen†, Xiyuan Wang†, Guangquan ZhouB , and Chuan ChenB   \nSchool of Biological Science and Medical Engineering, Southeast University, Nanjing,  \nChina  \n[guangquan.zhou@seu.edu.cn](guangquan.zhou@seu.edu.cn) , [chuanchen@seu.edu.cn](chuanchen@seu.edu.cn)  \nAbstract. While echocardiography is essential for cardiovascular diagnosis, inherent speckle noise and low signal-to-noise ratio often lead to ambiguous semantic features and fragmented boundaries. These limitations significantly hinder the segmentation accuracy of deep learning models in complex clinical cases. Moreover, temporal motion of the heart plays a critical role in recognizing anatomical structures. To address these challenges, we designed a STLSF module which comprises a windowmatching-based semantic correction component and a semantics-guided texture enhancement component. By leveraging local transition probability correlations to correct semantics and employing semantics-guided texture enhancement, the STLSF module effectively mitigates texture instability and ambiguous semantic interpretations caused by disadvantaged echocardiography quality. Additionally, to facilitate the encoder’s adaptation to the intrinsic priors of ultrasound-specific imaging patterns, we propose a frequency-aware denoising pre-training method. The entire work builds a convolution-based network with locality inductive bias and long-range dependencies. Extensive experiments confirm our SOTA performance, achieving 93 .87% Dice on CAMUS and 92 .62% on EchoNetDynamic, with respective HD95 values of 3.29mm and 2.73mm.  \nKeywords: Echocardiography Segmentation · Spatio-temporal Consistency.  \n1 Introduction  \nCardiovascular diseases (CVDs) remain the leading cause of death worldwide [22] . Echocardiography is the clinical standard for cardiac assessment due to its non-invasive and real-time nature [8], making accurate left ventricle (LV) segmentation essential for hemodynamic analysis and cardiac function quantification [13,20] . However, manual contouring remains time-consuming, highly expert-dependent, and prone to significant inter-observer variability [23,3] .  \nEarly studies primarily focused on 2D echocardiography segmentation, utilizing attention or pyramid modules [4,17,9,1,29] . However, echocardiogram quality  \n† These authors contributed equally.  \n2 X. Chen et al.  \nis often degraded by inherent speckle noise, blurred anatomical boundaries, and significant inter-individual structural variations, leading to ambiguous spatial semantic information [10,14] . Consequently, networks need to leverage temporal information to obtain more accurate and robust semantic features. Existing methods for modeling spatiotemporal information can generally be divided into two categorizes. The first category performs temporal modeling over entire long videos, either by employing 3D networks or implementing 3D-SVD to extract low-rank motion information [19,16] . However, these global-context-dependent approaches typically demand high computational and memory overhead, resulting in limited flexibility for variable-length or short clips, and reduced adapbility to streaming scenarios. The second category focuses on establishing temporal correlations for spatial features extracted by 2D networks: some studies enhance features through feature matching between adjacent frames or by using memory for temporal information propagation [7,6,27] . Since they rely on simple frame stacking and ignore cardiac motion, semantic errors caused by speckle noise and artifacts accumulate over time, and segmentation precision remains limited by video quality. Meanwhile, lacking intermediate frame annotations makes highperformance semi-supervised spatiotemporal modeling a significant challenge.  \nTo address these challenges, we designed and constructed a backbone net","cbCairf2b023zBNI","https://ap.wps.com/l/cbCairf2b023zBNI","pdf",1915921,1,11,"English","en",105,"# Introduction\n## Background and challenges\n## Related spatiotemporal modeling\n# Main contributions\n# Methodology\n## Overview","[{\"question\":\"What problem does the paper address in echocardiography segmentation?\",\"answer\":\"It addresses ambiguous semantic features and fragmented boundaries caused by speckle noise and low signal-to-noise ratio, which degrade segmentation accuracy in challenging clinical cases.\"},{\"question\":\"How does the STLSF module improve segmentation quality?\",\"answer\":\"STLSF combines window-matching-based semantic correction with semantics-guided texture enhancement, using local transition probability correlations to stabilize semantics and reduce texture instability.\"},{\"question\":\"What is the role of frequency-aware denoising pre-training?\",\"answer\":\"It incorporates ultrasound-specific imaging patterns as priors to help the convolutional, overview-focused encoder learn robust anatomical features from unlabeled data and resist noise.\"}]",1784194326,28,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"automatic-echocardiography-segmentation-via-transition-probability-correlation-for-stable-semantic-extraction","",{"@graph":35,"@context":85},[36,53,68],{"@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/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/automatic-echocardiography-segmentation-via-transition-probability-correlation-for-stable-semantic-extraction/84244/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 the paper address in echocardiography segmentation?","Question",{"text":75,"@type":76},"It addresses ambiguous semantic features and fragmented boundaries caused by speckle noise and low signal-to-noise ratio, which degrade segmentation accuracy in challenging clinical cases.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the STLSF module improve segmentation quality?",{"text":80,"@type":76},"STLSF combines window-matching-based semantic correction with semantics-guided texture enhancement, using local transition probability correlations to stabilize semantics and reduce texture instability.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of frequency-aware denoising pre-training?",{"text":84,"@type":76},"It incorporates ultrasound-specific imaging patterns as priors to help the convolutional, overview-focused encoder learn robust anatomical features from unlabeled data and resist noise.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]