[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-450276-105":59,"doc-detail-450276-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","towards-user-centered-interactive-medical-image-segmentation-in-vr-with-an-assistive-ai-agent","Towards user-centered interactive medical image segmentation in VR with an assistive AI agent","","Crucial for disease analysis and surgical planning, manual segmentation of volumetric medical scans is laborious, error-prone, and difficult to master, while fully automatic methods may benefit from user feedback. The work proposes SAMIRA, a conversational AI agent for medical VR that uses speech interaction to help users localize, segment, and visualize 3D medical concepts, generating masks refined with only a few point prompts. It also provides true-to-scale 3D visualization and evaluates interaction modes (controller, head, eye tracking), reporting high usability (SUS 90.0 ± 9.0) and low task load.",{"@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/towards-user-centered-interactive-medical-image-segmentation-in-vr-with-an-assistive-ai-agent/450276/",{"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/towards-user-centered-interactive-medical-image-segmentation-in-vr-with-an-assistive-ai-agent/450276.png","ImageObject",300,407,{"name":92,"@type":93},"Rowan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-05","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in medical image segmentation?","Question",{"text":112,"@type":113},"The paper targets the difficulty of manual segmentation of 3D medical scans (e.g., MRI/CT), which is laborious and error-prone, while noting that fully automatic methods can be improved by incorporating user feedback.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is SAMIRA and what does it do in VR?",{"text":117,"@type":113},"SAMIRA is a conversational AI agent for medical VR that assists users with localizing, segmenting, and visualizing 3D medical concepts through speech-based interaction. It generates segmentation masks that can be refined with a few point prompts and supports true-to-scale 3D visualization.",{"name":119,"@type":110,"acceptedAnswer":120},"Which VR input modes are compared for refining segmentation masks?",{"text":121,"@type":113},"The study compares VR controller pointing, head pointing, and eye tracking as input modes to determine the optimal interaction paradigm for near-far attention switching in a human-in-the-loop workflow.","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},450276,1791209758,{"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":14,"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":145},1099514067415,"https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502","Virtual Reality (2026) 30:20  \n[https://doi.org/10.1007/s10055-025-01284-0](https://doi.org/10.1007/s10055-025-01284-0)  \nORIGINAL ARTICLE  \nTowards user-centered interactive medical image segmentation in VR with an assistive AI agent  \nPascal Spiegler1 · Arash Harirpoush1 · Yiming Xiao1  \nReceived: 27 May 2025 / Accepted: 23 November 2025 / Published online: 25 December 2025 © The Author(s) 2025  \nAbstract  \nCrucial in disease analysis and surgical planning, manual segmentation of volumetric medical scans (e.g. MRI, CT) is laborious, error-prone, and challenging to master, while fully automatic algorithms can benefit from user feedback. Therefore, with the complementary power of the latest radiological AI foundation models and virtual reality (VR)’s intuitive data interaction, we propose SAMIRA, a novel conversational AI agent for medical VR that assists users with localizing, segmenting, and visualizing 3D medical concepts. Through speech-based interaction, the agent helps users understand radiological features, locate clinical targets, and generate segmentation masks that can be refined with just a few point prompts. The system also supports true-to-scale 3D visualization of segmented pathology to enhance patient-specific anatomical understanding. Furthermore, to determine the optimal interaction paradigm under near-far attention-switching for refining segmentation masks in an immersive, human-in-the-loop workflow, we compare VR controller pointing, head pointing, and eye tracking as input modes. With a user study, evaluations demonstrated a high usability score (SUS = 90.0 ± 9.0), low overall task load, as well as strong support for the proposed VR system’s guidance, training potential, and integration of AI in radiological segmentation tasks.  \nKeywords Medical image segmentation · Virtual reality · Human-in-the-loop · AI agent · Foundation model · Attention switching · Eye tracking · Medical visualization · Clinical decision support  \n1 Introduction  \nMedical image segmentation is a critical task in clinical diagnosis and treatment planning, particularly for identifying and quantifying abnormalities such as tumors, stroke lesions, and other pathological anomalies. The process involves producing segmentation masks that delineate and highlight regions of interest to provide a basis for further analysis, treatment decisions, and longitudinal tracking. However, traditional workflows for medical image segmentation are time-consuming and labor-intensive, typically requiring experts to manually annotate up to hundreds of 2D slices to isolate structures within 3D MRI or CT scans.  \n􀀍 Pascal Spiegler  \npascal.spiegler@mail.concordia.ca  \n􀀍 Yiming Xiao [yiming.xiao@concordia.ca](yiming.xiao@concordia.ca)  \n1 Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada  \nFurthermore, while segmenting pathologies (e.g., tumor) accurately is itself a demanding skill, it often requires extensive hours of supervision and training to develop diagnostic confidence and anatomical precision (Bruno et al. 2015) . Finally, visualizations of these annotations are similarly challenging: clinicians either scroll through superimposed binary masks on 2D slices across the axial, sagittal, and coronal planes, or view 3D reconstructions rendered on flat screens, both of which lack real spatial context and a true sense of scale.  \nWhile virtual reality (VR) can offer more intuitive 3D medical data visualization and interaction, especially under high spatial constraints (e.g., in the clinic) (Hellumet al. 2023, 2024; Spiegler et al. 2024), recent developments in foundation artificial intelligence (AI) models, such as vision-language models (VLMs) have demonstrated early promise to further enhance the efficiency, accuracy, and interactability for tasks in VR in the form of AI agents (Konenkov et al. 2024; Behravan et al. 2025). As an alternative to conventional brush painting-based segmentation paradigms, imag","cbCailxb0N9olNsG","https://ap.wps.com/l/cbCailxb0N9olNsG","pdf",2788745,15,"English","# Abstract\n# Keywords\n# 1 Introduction","[{\"question\":\"What problem does the paper address in medical image segmentation?\",\"answer\":\"The paper targets the difficulty of manual segmentation of 3D medical scans (e.g., MRI/CT), which is laborious and error-prone, while noting that fully automatic methods can be improved by incorporating user feedback.\"},{\"question\":\"What is SAMIRA and what does it do in VR?\",\"answer\":\"SAMIRA is a conversational AI agent for medical VR that assists users with localizing, segmenting, and visualizing 3D medical concepts through speech-based interaction. It generates segmentation masks that can be refined with a few point prompts and supports true-to-scale 3D visualization.\"},{\"question\":\"Which VR input modes are compared for refining segmentation masks?\",\"answer\":\"The study compares VR controller pointing, head pointing, and eye tracking as input modes to determine the optimal interaction paradigm for near-far attention switching in a human-in-the-loop workflow.\"}]","Towards user-centered interactive medical image segmentation in VR with an assistive AI agent | PDF",1790732720,38]