Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video

Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video Huu Phong Nguyen, Shekhar Madhav Khairnar, Ganesh Sankaranarayanan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8866826/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Artificial Intelligence (AI) is increasingly being utilized in surgical video analysis for applications such as phase recognition, skill assessment, and workflow optimization. A crucial challenge is the length of surgical recordings, which can range from one to several hours, causing a significant computational burden. Prior work established Kinematics Adaptive Frame Recognition (KAFR) for robotic surgery, demonstrating that tracking tool motion can effectively identify frames associated with relevant surgical activity while filtering redundant content. However, laparoscopic surgery presents additional challenges, including manual camera control, which results in frequent motion artifacts, and image quality that is often inferior to that of robotic systems. This study evaluates whether KAFR generalizes to the more challenging laparoscopic setting on the Cholec80 benchmark, a widely used dataset comprising 80 laparoscopic cholecystectomy procedures annotated for seven surgical phases. Our approach is divided into three main phases: (1) Tracking phase: a fine-tuned YOLO model detects and segments surgical tools; (2) Selection phase: frames are adaptively selected based on tool displacement (Adaptive 1) or velocity variation (Adaptive 2); (3) Classification phase: an X3D model classifies selected frames into surgical phases. The proposed approach achieved a 91.3% F1 score, utilizing only 0.58% of the total frames (a seven-fold reduction in processed frames compared to typical sampling methods), yet the model maintains performance comparable to state-of-the-art models such as LoViT (90.2%) and Trans-SVNet (89.7%). These results demonstrate that the kinematics-based strategy transfers effectively to the challenging laparoscopic environment. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Health sciences/Medical research Kinematics Adaptive Frame Recognition Surgical phase recognition Spatiotemporal learning Laparoscopic surgery Deep learning Full Text Additional Declarations No competing interests reported. Supplementary Files cholec80results.xlsx Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 01 Apr, 2026 Reviews received at journal 25 Mar, 2026 Reviews received at journal 16 Mar, 2026 Reviewers agreed at journal 04 Mar, 2026 Reviewers agreed at journal 23 Feb, 2026 Reviewers invited by journal 19 Feb, 2026 Editor assigned by journal 18 Feb, 2026 Submission checks completed at journal 18 Feb, 2026 First submitted to journal 12 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8866826","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":595478603,"identity":"864ba1ec-9e8a-4994-b528-f5638c21a24b","order_by":0,"name":"Huu Phong Nguyen","email":"data:image/png;base64,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","orcid":"","institution":"The University of Texas Southwestern Medical Center","correspondingAuthor":true,"prefix":"","firstName":"Huu","middleName":"Phong","lastName":"Nguyen","suffix":""},{"id":595478604,"identity":"8e04e14d-d47e-4a13-9a6b-a998007dade9","order_by":1,"name":"Shekhar Madhav Khairnar","email":"","orcid":"","institution":"The University of Texas Southwestern Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Shekhar","middleName":"Madhav","lastName":"Khairnar","suffix":""},{"id":595478605,"identity":"a57e8c7b-3867-4e1c-a205-382c81852674","order_by":2,"name":"Ganesh Sankaranarayanan","email":"","orcid":"","institution":"The University of Texas Southwestern Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Ganesh","middleName":"","lastName":"Sankaranarayanan","suffix":""}],"badges":[],"createdAt":"2026-02-13 03:09:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8866826/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8866826/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104397295,"identity":"71a14751-5903-4bbb-9768-cf2fce2ba19f","added_by":"auto","created_at":"2026-03-11 11:46:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2056299,"visible":true,"origin":"","legend":"","description":"","filename":"KAFR2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8866826/v1_covered_e946b5ac-6fb8-420b-b8ca-08c5b86961ae.pdf"},{"id":103283935,"identity":"3fc2cc44-b630-4d9b-9605-9e5a73d10d68","added_by":"auto","created_at":"2026-02-24 04:07:47","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":30450,"visible":true,"origin":"","legend":"","description":"","filename":"cholec80results.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8866826/v1/99b9e49484dc1436a7faca84.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-digital-surgery","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [npj Digital Surgery](https://www.nature.com/npjdigisurg/)","snPcode":"44484","submissionUrl":"https://submission.springernature.com/new-submission/44484/3?","title":"npj Digital Surgery","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Kinematics Adaptive Frame Recognition, Surgical phase recognition, Spatiotemporal learning, Laparoscopic surgery, Deep learning","lastPublishedDoi":"10.21203/rs.3.rs-8866826/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8866826/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eArtificial Intelligence (AI) is increasingly being utilized in surgical video analysis for applications such as phase recognition, skill assessment, and workflow optimization. A crucial challenge is the length of surgical recordings, which can range from one to several hours, causing a significant computational burden. Prior work established Kinematics Adaptive Frame Recognition (KAFR) for robotic surgery, demonstrating that tracking tool motion can effectively identify frames associated with relevant surgical activity while filtering redundant content. However, laparoscopic surgery presents additional challenges, including manual camera control, which results in frequent motion artifacts, and image quality that is often inferior to that of robotic systems. This study evaluates whether KAFR generalizes to the more challenging laparoscopic setting on the Cholec80 benchmark, a widely used dataset comprising 80 laparoscopic cholecystectomy procedures annotated for seven surgical phases. Our approach is divided into three main phases: (1) Tracking phase: a fine-tuned YOLO model detects and segments surgical tools; (2) Selection phase: frames are adaptively selected based on tool displacement (Adaptive 1) or velocity variation (Adaptive 2); (3) Classification phase: an X3D model classifies selected frames into surgical phases. The proposed approach achieved a 91.3% F1 score, utilizing only 0.58% of the total frames (a seven-fold reduction in processed frames compared to typical sampling methods), yet the model maintains performance comparable to state-of-the-art models such as LoViT (90.2%) and Trans-SVNet (89.7%). These results demonstrate that the kinematics-based strategy transfers effectively to the challenging laparoscopic environment.\u003c/p\u003e","manuscriptTitle":"Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-24 04:07:43","doi":"10.21203/rs.3.rs-8866826/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-01T21:59:03+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-25T18:28:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-16T13:52:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"217773390225864577485165145282651365703","date":"2026-03-04T23:16:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"139280365369116075324880525325869031995","date":"2026-02-23T08:14:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-19T20:24:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-19T03:49:10+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-18T05:03:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Surgery","date":"2026-02-13T03:04:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-surgery","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [npj Digital Surgery](https://www.nature.com/npjdigisurg/)","snPcode":"44484","submissionUrl":"https://submission.springernature.com/new-submission/44484/3?","title":"npj Digital Surgery","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5d74c3ae-7af3-44cd-8759-591c0deb848a","owner":[],"postedDate":"February 24th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":63358676,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":63358677,"name":"Physical sciences/Engineering"},{"id":63358678,"name":"Physical sciences/Mathematics and computing"},{"id":63358679,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-04-01T22:08:38+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-24 04:07:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8866826","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8866826","identity":"rs-8866826","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}