An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb
Purpose The objective of this study was to develop a numeric tool to automate the analysis of deformity from lower limb telemetry and assess its accuracy. Our hypothesis was that artificial intelligence (AI) algorithm would be able to determine mechanical and anatomical angles to within 1°. Methods...
Gespeichert in:
Veröffentlicht in: | International orthopaedics 2023-02, Vol.47 (2), p.511-518 |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 518 |
---|---|
container_issue | 2 |
container_start_page | 511 |
container_title | International orthopaedics |
container_volume | 47 |
creator | Bernard de Villeneuve, Florent Jacquet, Christophe El Kadim, Bilal Donnez, Mathias Coue, Olivier Poujade, Thibault Khakha, Raghbir Argenson, Jean-Noel Ollivier, Matthieu |
description | Purpose
The objective of this study was to develop a numeric tool to automate the analysis of deformity from lower limb telemetry and assess its accuracy. Our hypothesis was that artificial intelligence (AI) algorithm would be able to determine mechanical and anatomical angles to within 1°.
Methods
After institutional review board approval, 1175 anonymized patient telemetries were extracted from a database of more than ten thousand telemetries. From this selection, 31 packs of telemetries were composed and sent to 11 orthopaedic surgeons for analysis. Each surgeon had to identify on the telemetries fourteen landmarks allowing determination of the following four angles: hip-knee-ankle angle (HKA), medial proximal tibial angle (MPTA), lateral distal femoral angle (LDFA), and joint line convergence angle (JLCA). An algorithm based on a machine learning process was trained on our database to automatically determine angles. The reliability of the algorithm was evaluated by calculating the difference of determination precision between the surgeons and the algorithm.
Results
The analysis time for obtaining 28 points and 8 angles per image was 48 ± 12 s for the algorithm. The average difference between the angles measured by the surgeons and the algorithm was around 1.9° for all the angles of interest: 1.3° for HKA, 1.6° for MPTA, 2.1° for LDFA, and 2.4° for JLCA. Intraclass correlation was greater than 95% for all angles.
Conclusion
The algorithm showed high accuracy for automated angle measurement, allowing the estimation of limb frontal alignment to the nearest degree. |
doi_str_mv | 10.1007/s00264-022-05634-4 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2739743955</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2739743955</sourcerecordid><originalsourceid>FETCH-LOGICAL-c347t-3efefa059b2f8424ebb2c6ffeb36386b8a530f3a4088cbab8c94a7d1335c5473</originalsourceid><addsrcrecordid>eNp9kD1PHDEQhq0oKHdA_kCKyGWaBX-M96M8nUJAQkpDb9m-MZjs2hd7N4iKvx6HO1JSjWbmmVeah5AvnF1wxrrLwphooWFCNEy1Ehr4QNYcpGgUH9RHsmYSeCPaQa3IaSmPjPGu7fknspIt8B4A1uRlE6nJc_DBBTPSEGccx3CP0SG1puCOpgpQl-KfNC5zSLFSEZf8WuanlH9RM47pqVRqn9GFgtRU6LmEQpOn80Pta2KcMM5vg8pjpmOY7Dk58WYs-PlYz8jd1fe77XVz-_PHzXZz2zgJ3dxI9OgNU4MVvgcBaK1wrfdoZSv71vZGSealAdb3zhrbuwFMt-NSKqegk2fk2yF2n9PvBcusp1BcfdVETEvRopNDB3JQqqLigLqcSsno9T6HyeRnzZn-510fvOvqXb9611CPvh7zFzvh7v_Jm-gKyANQ6ireY9aPacnVU3kv9i-ovpBx</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2739743955</pqid></control><display><type>article</type><title>An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb</title><source>MEDLINE</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>SpringerLink Journals - AutoHoldings</source><creator>Bernard de Villeneuve, Florent ; Jacquet, Christophe ; El Kadim, Bilal ; Donnez, Mathias ; Coue, Olivier ; Poujade, Thibault ; Khakha, Raghbir ; Argenson, Jean-Noel ; Ollivier, Matthieu</creator><creatorcontrib>Bernard de Villeneuve, Florent ; Jacquet, Christophe ; El Kadim, Bilal ; Donnez, Mathias ; Coue, Olivier ; Poujade, Thibault ; Khakha, Raghbir ; Argenson, Jean-Noel ; Ollivier, Matthieu</creatorcontrib><description>Purpose
The objective of this study was to develop a numeric tool to automate the analysis of deformity from lower limb telemetry and assess its accuracy. Our hypothesis was that artificial intelligence (AI) algorithm would be able to determine mechanical and anatomical angles to within 1°.
Methods
After institutional review board approval, 1175 anonymized patient telemetries were extracted from a database of more than ten thousand telemetries. From this selection, 31 packs of telemetries were composed and sent to 11 orthopaedic surgeons for analysis. Each surgeon had to identify on the telemetries fourteen landmarks allowing determination of the following four angles: hip-knee-ankle angle (HKA), medial proximal tibial angle (MPTA), lateral distal femoral angle (LDFA), and joint line convergence angle (JLCA). An algorithm based on a machine learning process was trained on our database to automatically determine angles. The reliability of the algorithm was evaluated by calculating the difference of determination precision between the surgeons and the algorithm.
Results
The analysis time for obtaining 28 points and 8 angles per image was 48 ± 12 s for the algorithm. The average difference between the angles measured by the surgeons and the algorithm was around 1.9° for all the angles of interest: 1.3° for HKA, 1.6° for MPTA, 2.1° for LDFA, and 2.4° for JLCA. Intraclass correlation was greater than 95% for all angles.
Conclusion
The algorithm showed high accuracy for automated angle measurement, allowing the estimation of limb frontal alignment to the nearest degree.</description><identifier>ISSN: 0341-2695</identifier><identifier>EISSN: 1432-5195</identifier><identifier>DOI: 10.1007/s00264-022-05634-4</identifier><identifier>PMID: 36418444</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Artificial Intelligence ; Humans ; Knee Joint - diagnostic imaging ; Knee Joint - surgery ; Lower Extremity - surgery ; Medicine ; Medicine & Public Health ; Neural Networks, Computer ; Original Paper ; Orthopedics ; Osteoarthritis, Knee - surgery ; Reproducibility of Results ; Retrospective Studies ; Tibia - surgery</subject><ispartof>International orthopaedics, 2023-02, Vol.47 (2), p.511-518</ispartof><rights>The Author(s) under exclusive licence to SICOT aisbl 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2022. The Author(s) under exclusive licence to SICOT aisbl.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c347t-3efefa059b2f8424ebb2c6ffeb36386b8a530f3a4088cbab8c94a7d1335c5473</citedby><cites>FETCH-LOGICAL-c347t-3efefa059b2f8424ebb2c6ffeb36386b8a530f3a4088cbab8c94a7d1335c5473</cites><orcidid>0000-0002-5906-1727</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00264-022-05634-4$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00264-022-05634-4$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27923,27924,41487,42556,51318</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36418444$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Bernard de Villeneuve, Florent</creatorcontrib><creatorcontrib>Jacquet, Christophe</creatorcontrib><creatorcontrib>El Kadim, Bilal</creatorcontrib><creatorcontrib>Donnez, Mathias</creatorcontrib><creatorcontrib>Coue, Olivier</creatorcontrib><creatorcontrib>Poujade, Thibault</creatorcontrib><creatorcontrib>Khakha, Raghbir</creatorcontrib><creatorcontrib>Argenson, Jean-Noel</creatorcontrib><creatorcontrib>Ollivier, Matthieu</creatorcontrib><title>An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb</title><title>International orthopaedics</title><addtitle>International Orthopaedics (SICOT)</addtitle><addtitle>Int Orthop</addtitle><description>Purpose
The objective of this study was to develop a numeric tool to automate the analysis of deformity from lower limb telemetry and assess its accuracy. Our hypothesis was that artificial intelligence (AI) algorithm would be able to determine mechanical and anatomical angles to within 1°.
Methods
After institutional review board approval, 1175 anonymized patient telemetries were extracted from a database of more than ten thousand telemetries. From this selection, 31 packs of telemetries were composed and sent to 11 orthopaedic surgeons for analysis. Each surgeon had to identify on the telemetries fourteen landmarks allowing determination of the following four angles: hip-knee-ankle angle (HKA), medial proximal tibial angle (MPTA), lateral distal femoral angle (LDFA), and joint line convergence angle (JLCA). An algorithm based on a machine learning process was trained on our database to automatically determine angles. The reliability of the algorithm was evaluated by calculating the difference of determination precision between the surgeons and the algorithm.
Results
The analysis time for obtaining 28 points and 8 angles per image was 48 ± 12 s for the algorithm. The average difference between the angles measured by the surgeons and the algorithm was around 1.9° for all the angles of interest: 1.3° for HKA, 1.6° for MPTA, 2.1° for LDFA, and 2.4° for JLCA. Intraclass correlation was greater than 95% for all angles.
Conclusion
The algorithm showed high accuracy for automated angle measurement, allowing the estimation of limb frontal alignment to the nearest degree.</description><subject>Artificial Intelligence</subject><subject>Humans</subject><subject>Knee Joint - diagnostic imaging</subject><subject>Knee Joint - surgery</subject><subject>Lower Extremity - surgery</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Neural Networks, Computer</subject><subject>Original Paper</subject><subject>Orthopedics</subject><subject>Osteoarthritis, Knee - surgery</subject><subject>Reproducibility of Results</subject><subject>Retrospective Studies</subject><subject>Tibia - surgery</subject><issn>0341-2695</issn><issn>1432-5195</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kD1PHDEQhq0oKHdA_kCKyGWaBX-M96M8nUJAQkpDb9m-MZjs2hd7N4iKvx6HO1JSjWbmmVeah5AvnF1wxrrLwphooWFCNEy1Ehr4QNYcpGgUH9RHsmYSeCPaQa3IaSmPjPGu7fknspIt8B4A1uRlE6nJc_DBBTPSEGccx3CP0SG1puCOpgpQl-KfNC5zSLFSEZf8WuanlH9RM47pqVRqn9GFgtRU6LmEQpOn80Pta2KcMM5vg8pjpmOY7Dk58WYs-PlYz8jd1fe77XVz-_PHzXZz2zgJ3dxI9OgNU4MVvgcBaK1wrfdoZSv71vZGSealAdb3zhrbuwFMt-NSKqegk2fk2yF2n9PvBcusp1BcfdVETEvRopNDB3JQqqLigLqcSsno9T6HyeRnzZn-510fvOvqXb9611CPvh7zFzvh7v_Jm-gKyANQ6ireY9aPacnVU3kv9i-ovpBx</recordid><startdate>20230201</startdate><enddate>20230201</enddate><creator>Bernard de Villeneuve, Florent</creator><creator>Jacquet, Christophe</creator><creator>El Kadim, Bilal</creator><creator>Donnez, Mathias</creator><creator>Coue, Olivier</creator><creator>Poujade, Thibault</creator><creator>Khakha, Raghbir</creator><creator>Argenson, Jean-Noel</creator><creator>Ollivier, Matthieu</creator><general>Springer Berlin Heidelberg</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-5906-1727</orcidid></search><sort><creationdate>20230201</creationdate><title>An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb</title><author>Bernard de Villeneuve, Florent ; Jacquet, Christophe ; El Kadim, Bilal ; Donnez, Mathias ; Coue, Olivier ; Poujade, Thibault ; Khakha, Raghbir ; Argenson, Jean-Noel ; Ollivier, Matthieu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c347t-3efefa059b2f8424ebb2c6ffeb36386b8a530f3a4088cbab8c94a7d1335c5473</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial Intelligence</topic><topic>Humans</topic><topic>Knee Joint - diagnostic imaging</topic><topic>Knee Joint - surgery</topic><topic>Lower Extremity - surgery</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Neural Networks, Computer</topic><topic>Original Paper</topic><topic>Orthopedics</topic><topic>Osteoarthritis, Knee - surgery</topic><topic>Reproducibility of Results</topic><topic>Retrospective Studies</topic><topic>Tibia - surgery</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bernard de Villeneuve, Florent</creatorcontrib><creatorcontrib>Jacquet, Christophe</creatorcontrib><creatorcontrib>El Kadim, Bilal</creatorcontrib><creatorcontrib>Donnez, Mathias</creatorcontrib><creatorcontrib>Coue, Olivier</creatorcontrib><creatorcontrib>Poujade, Thibault</creatorcontrib><creatorcontrib>Khakha, Raghbir</creatorcontrib><creatorcontrib>Argenson, Jean-Noel</creatorcontrib><creatorcontrib>Ollivier, Matthieu</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>International orthopaedics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bernard de Villeneuve, Florent</au><au>Jacquet, Christophe</au><au>El Kadim, Bilal</au><au>Donnez, Mathias</au><au>Coue, Olivier</au><au>Poujade, Thibault</au><au>Khakha, Raghbir</au><au>Argenson, Jean-Noel</au><au>Ollivier, Matthieu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb</atitle><jtitle>International orthopaedics</jtitle><stitle>International Orthopaedics (SICOT)</stitle><addtitle>Int Orthop</addtitle><date>2023-02-01</date><risdate>2023</risdate><volume>47</volume><issue>2</issue><spage>511</spage><epage>518</epage><pages>511-518</pages><issn>0341-2695</issn><eissn>1432-5195</eissn><abstract>Purpose
The objective of this study was to develop a numeric tool to automate the analysis of deformity from lower limb telemetry and assess its accuracy. Our hypothesis was that artificial intelligence (AI) algorithm would be able to determine mechanical and anatomical angles to within 1°.
Methods
After institutional review board approval, 1175 anonymized patient telemetries were extracted from a database of more than ten thousand telemetries. From this selection, 31 packs of telemetries were composed and sent to 11 orthopaedic surgeons for analysis. Each surgeon had to identify on the telemetries fourteen landmarks allowing determination of the following four angles: hip-knee-ankle angle (HKA), medial proximal tibial angle (MPTA), lateral distal femoral angle (LDFA), and joint line convergence angle (JLCA). An algorithm based on a machine learning process was trained on our database to automatically determine angles. The reliability of the algorithm was evaluated by calculating the difference of determination precision between the surgeons and the algorithm.
Results
The analysis time for obtaining 28 points and 8 angles per image was 48 ± 12 s for the algorithm. The average difference between the angles measured by the surgeons and the algorithm was around 1.9° for all the angles of interest: 1.3° for HKA, 1.6° for MPTA, 2.1° for LDFA, and 2.4° for JLCA. Intraclass correlation was greater than 95% for all angles.
Conclusion
The algorithm showed high accuracy for automated angle measurement, allowing the estimation of limb frontal alignment to the nearest degree.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>36418444</pmid><doi>10.1007/s00264-022-05634-4</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-5906-1727</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0341-2695 |
ispartof | International orthopaedics, 2023-02, Vol.47 (2), p.511-518 |
issn | 0341-2695 1432-5195 |
language | eng |
recordid | cdi_proquest_miscellaneous_2739743955 |
source | MEDLINE; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; SpringerLink Journals - AutoHoldings |
subjects | Artificial Intelligence Humans Knee Joint - diagnostic imaging Knee Joint - surgery Lower Extremity - surgery Medicine Medicine & Public Health Neural Networks, Computer Original Paper Orthopedics Osteoarthritis, Knee - surgery Reproducibility of Results Retrospective Studies Tibia - surgery |
title | An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T16%3A47%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20artificial%20intelligence%20based%20on%20a%20convolutional%20neural%20network%20allows%20a%20precise%20analysis%20of%20the%20alignment%20of%20the%20lower%20limb&rft.jtitle=International%20orthopaedics&rft.au=Bernard%20de%20Villeneuve,%20Florent&rft.date=2023-02-01&rft.volume=47&rft.issue=2&rft.spage=511&rft.epage=518&rft.pages=511-518&rft.issn=0341-2695&rft.eissn=1432-5195&rft_id=info:doi/10.1007/s00264-022-05634-4&rft_dat=%3Cproquest_cross%3E2739743955%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2739743955&rft_id=info:pmid/36418444&rfr_iscdi=true |