Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis

Advancements in artificial intelligence and the development of shape models that quantify normal head shape and facial morphology provide frameworks by which the outcomes of craniofacial surgery can be compared. In this work, we will demonstrate the use of the Swap Disentangled Variational Autoencod...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Plastic and reconstructive surgery (1963) 2024-08
Hauptverfasser: Rickart, Alexander J, Foti, Simone, van de Lande, Lara S, Wagner, Connor, Schievano, Silvia, Jeelani, Noor Ul Owase, Clarkson, Matthew J, Ong, Juling, Swanson, Jordan W, Bartlett, Scott P, Taylor, Jesse A, Dunaway, David J
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title Plastic and reconstructive surgery (1963)
container_volume
creator Rickart, Alexander J
Foti, Simone
van de Lande, Lara S
Wagner, Connor
Schievano, Silvia
Jeelani, Noor Ul Owase
Clarkson, Matthew J
Ong, Juling
Swanson, Jordan W
Bartlett, Scott P
Taylor, Jesse A
Dunaway, David J
description Advancements in artificial intelligence and the development of shape models that quantify normal head shape and facial morphology provide frameworks by which the outcomes of craniofacial surgery can be compared. In this work, we will demonstrate the use of the Swap Disentangled Variational Autoencoder (SD-VAE) to objectively assess changes following midfacial surgery. Our model is trained on a dataset of 1405 3D meshes of healthy and syndromic patients which was augmented using a technique based on spectral interpolation. Patients with a diagnosis of Apert and Crouzon syndrome who had undergone sub- or trans-cranial midfacial procedures utilising rigid external distraction were then interpreted using this model as the point of comparison. A total of 56 patients met our inclusion criteria, 20 with Apert and 36 with Crouzon syndrome. By using linear discriminant analysis to project the high-dimensional vectors derived by SD-VAE onto a 2D space, the shape properties of Apert and Crouzon syndrome can be visualised in relation to the healthy population. In this way, we are able to show how surgery elicits global shape changes in each patient. To assess the regional movements achieved during surgery, we use a novel metric derived from the Malahanobis distance to quantify movements through the latent space. Objective outcome evaluation, which encourages in-depth analysis and enhances decision making, is essential for the progression of surgical practice. We have demonstrated how artificial intelligence has the ability to improve our understanding of surgery and its effect on craniofacial morphology.
doi_str_mv 10.1097/PRS.0000000000011686
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3099804896</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3099804896</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1015-4c15123b56bad66eecaa6ef0ebeb978343d01e30d85109f6dcc2f198210015c43</originalsourceid><addsrcrecordid>eNpdkMtOwzAQRS0EgvL4A4S8ZBPwI3bjZVWeElBEYR05zqQYkhg8CSh_TxAvidnczT0zmkPIPmdHnJnp8e3d8oj9Dec602tkwpUwSSpSsU4mjEmRcKbEFtlGfBpLU6nVJtmSRnBhUjUhwwP6dkVn9MQjtJ1tVzWU9Ab6aOsxuvcQn2kX6KJ4Atf5N6gHOkMERNo9Al30nQsNIA0VvfZlZZ0fuWUfVxAH6lu6HNoyhsY7Oo-29QGHNmAX0OMu2ahsjbD3nTvk4ez0fn6RXC3OL-ezq8RxxlWSOq64kIXShS21BnDWaqgYFFCYaSZTWTIOkpWZGrVUunROVNxkgo_vKpfKHXL4tfclhtcesMsbjw7q2rYQeswlMyZjaWb0WE2_qi4GxAhV_hJ9Y-OQc5Z_Ss9H6fl_6SN28H2hLxoof6Efy_IDtEN-bQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3099804896</pqid></control><display><type>article</type><title>Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis</title><source>Journals@Ovid Complete</source><creator>Rickart, Alexander J ; Foti, Simone ; van de Lande, Lara S ; Wagner, Connor ; Schievano, Silvia ; Jeelani, Noor Ul Owase ; Clarkson, Matthew J ; Ong, Juling ; Swanson, Jordan W ; Bartlett, Scott P ; Taylor, Jesse A ; Dunaway, David J</creator><creatorcontrib>Rickart, Alexander J ; Foti, Simone ; van de Lande, Lara S ; Wagner, Connor ; Schievano, Silvia ; Jeelani, Noor Ul Owase ; Clarkson, Matthew J ; Ong, Juling ; Swanson, Jordan W ; Bartlett, Scott P ; Taylor, Jesse A ; Dunaway, David J</creatorcontrib><description>Advancements in artificial intelligence and the development of shape models that quantify normal head shape and facial morphology provide frameworks by which the outcomes of craniofacial surgery can be compared. In this work, we will demonstrate the use of the Swap Disentangled Variational Autoencoder (SD-VAE) to objectively assess changes following midfacial surgery. Our model is trained on a dataset of 1405 3D meshes of healthy and syndromic patients which was augmented using a technique based on spectral interpolation. Patients with a diagnosis of Apert and Crouzon syndrome who had undergone sub- or trans-cranial midfacial procedures utilising rigid external distraction were then interpreted using this model as the point of comparison. A total of 56 patients met our inclusion criteria, 20 with Apert and 36 with Crouzon syndrome. By using linear discriminant analysis to project the high-dimensional vectors derived by SD-VAE onto a 2D space, the shape properties of Apert and Crouzon syndrome can be visualised in relation to the healthy population. In this way, we are able to show how surgery elicits global shape changes in each patient. To assess the regional movements achieved during surgery, we use a novel metric derived from the Malahanobis distance to quantify movements through the latent space. Objective outcome evaluation, which encourages in-depth analysis and enhances decision making, is essential for the progression of surgical practice. We have demonstrated how artificial intelligence has the ability to improve our understanding of surgery and its effect on craniofacial morphology.</description><identifier>ISSN: 0032-1052</identifier><identifier>ISSN: 1529-4242</identifier><identifier>EISSN: 1529-4242</identifier><identifier>DOI: 10.1097/PRS.0000000000011686</identifier><identifier>PMID: 39212945</identifier><language>eng</language><publisher>United States</publisher><ispartof>Plastic and reconstructive surgery (1963), 2024-08</ispartof><rights>Copyright © 2024 by the American Society of Plastic Surgeons.</rights><rights>Copyright © 2024 The Authors. Published by Wolters Kluwer Health, Inc. on behalf of the American Society of Plastic Surgeons. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,781,785,27925,27926</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39212945$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Rickart, Alexander J</creatorcontrib><creatorcontrib>Foti, Simone</creatorcontrib><creatorcontrib>van de Lande, Lara S</creatorcontrib><creatorcontrib>Wagner, Connor</creatorcontrib><creatorcontrib>Schievano, Silvia</creatorcontrib><creatorcontrib>Jeelani, Noor Ul Owase</creatorcontrib><creatorcontrib>Clarkson, Matthew J</creatorcontrib><creatorcontrib>Ong, Juling</creatorcontrib><creatorcontrib>Swanson, Jordan W</creatorcontrib><creatorcontrib>Bartlett, Scott P</creatorcontrib><creatorcontrib>Taylor, Jesse A</creatorcontrib><creatorcontrib>Dunaway, David J</creatorcontrib><title>Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis</title><title>Plastic and reconstructive surgery (1963)</title><addtitle>Plast Reconstr Surg</addtitle><description>Advancements in artificial intelligence and the development of shape models that quantify normal head shape and facial morphology provide frameworks by which the outcomes of craniofacial surgery can be compared. In this work, we will demonstrate the use of the Swap Disentangled Variational Autoencoder (SD-VAE) to objectively assess changes following midfacial surgery. Our model is trained on a dataset of 1405 3D meshes of healthy and syndromic patients which was augmented using a technique based on spectral interpolation. Patients with a diagnosis of Apert and Crouzon syndrome who had undergone sub- or trans-cranial midfacial procedures utilising rigid external distraction were then interpreted using this model as the point of comparison. A total of 56 patients met our inclusion criteria, 20 with Apert and 36 with Crouzon syndrome. By using linear discriminant analysis to project the high-dimensional vectors derived by SD-VAE onto a 2D space, the shape properties of Apert and Crouzon syndrome can be visualised in relation to the healthy population. In this way, we are able to show how surgery elicits global shape changes in each patient. To assess the regional movements achieved during surgery, we use a novel metric derived from the Malahanobis distance to quantify movements through the latent space. Objective outcome evaluation, which encourages in-depth analysis and enhances decision making, is essential for the progression of surgical practice. We have demonstrated how artificial intelligence has the ability to improve our understanding of surgery and its effect on craniofacial morphology.</description><issn>0032-1052</issn><issn>1529-4242</issn><issn>1529-4242</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNpdkMtOwzAQRS0EgvL4A4S8ZBPwI3bjZVWeElBEYR05zqQYkhg8CSh_TxAvidnczT0zmkPIPmdHnJnp8e3d8oj9Dec602tkwpUwSSpSsU4mjEmRcKbEFtlGfBpLU6nVJtmSRnBhUjUhwwP6dkVn9MQjtJ1tVzWU9Ab6aOsxuvcQn2kX6KJ4Atf5N6gHOkMERNo9Al30nQsNIA0VvfZlZZ0fuWUfVxAH6lu6HNoyhsY7Oo-29QGHNmAX0OMu2ahsjbD3nTvk4ez0fn6RXC3OL-ezq8RxxlWSOq64kIXShS21BnDWaqgYFFCYaSZTWTIOkpWZGrVUunROVNxkgo_vKpfKHXL4tfclhtcesMsbjw7q2rYQeswlMyZjaWb0WE2_qi4GxAhV_hJ9Y-OQc5Z_Ss9H6fl_6SN28H2hLxoof6Efy_IDtEN-bQ</recordid><startdate>20240820</startdate><enddate>20240820</enddate><creator>Rickart, Alexander J</creator><creator>Foti, Simone</creator><creator>van de Lande, Lara S</creator><creator>Wagner, Connor</creator><creator>Schievano, Silvia</creator><creator>Jeelani, Noor Ul Owase</creator><creator>Clarkson, Matthew J</creator><creator>Ong, Juling</creator><creator>Swanson, Jordan W</creator><creator>Bartlett, Scott P</creator><creator>Taylor, Jesse A</creator><creator>Dunaway, David J</creator><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20240820</creationdate><title>Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis</title><author>Rickart, Alexander J ; Foti, Simone ; van de Lande, Lara S ; Wagner, Connor ; Schievano, Silvia ; Jeelani, Noor Ul Owase ; Clarkson, Matthew J ; Ong, Juling ; Swanson, Jordan W ; Bartlett, Scott P ; Taylor, Jesse A ; Dunaway, David J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1015-4c15123b56bad66eecaa6ef0ebeb978343d01e30d85109f6dcc2f198210015c43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rickart, Alexander J</creatorcontrib><creatorcontrib>Foti, Simone</creatorcontrib><creatorcontrib>van de Lande, Lara S</creatorcontrib><creatorcontrib>Wagner, Connor</creatorcontrib><creatorcontrib>Schievano, Silvia</creatorcontrib><creatorcontrib>Jeelani, Noor Ul Owase</creatorcontrib><creatorcontrib>Clarkson, Matthew J</creatorcontrib><creatorcontrib>Ong, Juling</creatorcontrib><creatorcontrib>Swanson, Jordan W</creatorcontrib><creatorcontrib>Bartlett, Scott P</creatorcontrib><creatorcontrib>Taylor, Jesse A</creatorcontrib><creatorcontrib>Dunaway, David J</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Plastic and reconstructive surgery (1963)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rickart, Alexander J</au><au>Foti, Simone</au><au>van de Lande, Lara S</au><au>Wagner, Connor</au><au>Schievano, Silvia</au><au>Jeelani, Noor Ul Owase</au><au>Clarkson, Matthew J</au><au>Ong, Juling</au><au>Swanson, Jordan W</au><au>Bartlett, Scott P</au><au>Taylor, Jesse A</au><au>Dunaway, David J</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis</atitle><jtitle>Plastic and reconstructive surgery (1963)</jtitle><addtitle>Plast Reconstr Surg</addtitle><date>2024-08-20</date><risdate>2024</risdate><issn>0032-1052</issn><issn>1529-4242</issn><eissn>1529-4242</eissn><abstract>Advancements in artificial intelligence and the development of shape models that quantify normal head shape and facial morphology provide frameworks by which the outcomes of craniofacial surgery can be compared. In this work, we will demonstrate the use of the Swap Disentangled Variational Autoencoder (SD-VAE) to objectively assess changes following midfacial surgery. Our model is trained on a dataset of 1405 3D meshes of healthy and syndromic patients which was augmented using a technique based on spectral interpolation. Patients with a diagnosis of Apert and Crouzon syndrome who had undergone sub- or trans-cranial midfacial procedures utilising rigid external distraction were then interpreted using this model as the point of comparison. A total of 56 patients met our inclusion criteria, 20 with Apert and 36 with Crouzon syndrome. By using linear discriminant analysis to project the high-dimensional vectors derived by SD-VAE onto a 2D space, the shape properties of Apert and Crouzon syndrome can be visualised in relation to the healthy population. In this way, we are able to show how surgery elicits global shape changes in each patient. To assess the regional movements achieved during surgery, we use a novel metric derived from the Malahanobis distance to quantify movements through the latent space. Objective outcome evaluation, which encourages in-depth analysis and enhances decision making, is essential for the progression of surgical practice. We have demonstrated how artificial intelligence has the ability to improve our understanding of surgery and its effect on craniofacial morphology.</abstract><cop>United States</cop><pmid>39212945</pmid><doi>10.1097/PRS.0000000000011686</doi></addata></record>
fulltext fulltext
identifier ISSN: 0032-1052
ispartof Plastic and reconstructive surgery (1963), 2024-08
issn 0032-1052
1529-4242
1529-4242
language eng
recordid cdi_proquest_miscellaneous_3099804896
source Journals@Ovid Complete
title Using A Disentangled Neural Network to Objectively Assess the Outcomes of Midfacial Surgery in Syndromic Craniosynostosis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T13%3A49%3A36IST&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=Using%20A%20Disentangled%20Neural%20Network%20to%20Objectively%20Assess%20the%20Outcomes%20of%20Midfacial%20Surgery%20in%20Syndromic%20Craniosynostosis&rft.jtitle=Plastic%20and%20reconstructive%20surgery%20(1963)&rft.au=Rickart,%20Alexander%20J&rft.date=2024-08-20&rft.issn=0032-1052&rft.eissn=1529-4242&rft_id=info:doi/10.1097/PRS.0000000000011686&rft_dat=%3Cproquest_cross%3E3099804896%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=3099804896&rft_id=info:pmid/39212945&rfr_iscdi=true