Sex estimation from coxal bones using deep learning in a population balanced by sex and age
In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age a...
Gespeichert in:
Veröffentlicht in: | International journal of legal medicine 2024-11, Vol.138 (6), p.2617-2623 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 2623 |
---|---|
container_issue | 6 |
container_start_page | 2617 |
container_title | International journal of legal medicine |
container_volume | 138 |
creator | Epain, Marie Valette, Sébastien Zou, Kaifeng Faisan, Sylvain Heitz, Fabrice Croisille, Pierre Fracasso, Tony Fanton, Laurent |
description | In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (C
recon
). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + C
recon
showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology. |
doi_str_mv | 10.1007/s00414-024-03268-2 |
format | Article |
fullrecord | <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_04609128v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3118389647</sourcerecordid><originalsourceid>FETCH-LOGICAL-c290t-335598911b4dd767e241efcfb155fb65e6148e8d15bd0090045d753c87e116cb3</originalsourceid><addsrcrecordid>eNp9kUFvFSEUhYnR2Gf1D7gwJG50McqFgYFl06g1eYkL68oFgeHOc5p5MMIb0_778jq1Ji66IHDhu4d7cgh5DewDMNZ9LIy10DaM1yW40g1_QjbQiq4BadRTsmGmno3m3Ql5UcoVY9CpTj4nJ0JrxTVnG_LzO15TLIdx7w5jinTIaU_7dO0m6lPEQpcyxh0NiDOd0OV4rMZIHZ3TvExrk3eTiz0G6m9oqXouBup2-JI8G9xU8NX9fkp-fP50eX7RbL99-Xp-tm16btihEUJKow2Ab0OoAyJvAYd-8CDl4JVEBa1GHUD6wJippmXopOh1hwCq9-KUvF91f7nJzrlayTc2udFenG3t8Y61ihng-g9U9t3Kzjn9Xqpxux9Lj1M1gGkpVgBowQQIWdG3_6FXacmxOlkpbVTbVYqvVJ9TKRmHhwmA2WNMdo3J1pjsXUyW16Y399KL32N4aPmbSwXECpT6FHeY__39iOwtyPeaww</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3118389647</pqid></control><display><type>article</type><title>Sex estimation from coxal bones using deep learning in a population balanced by sex and age</title><source>Springer Online Journals Complete</source><creator>Epain, Marie ; Valette, Sébastien ; Zou, Kaifeng ; Faisan, Sylvain ; Heitz, Fabrice ; Croisille, Pierre ; Fracasso, Tony ; Fanton, Laurent</creator><creatorcontrib>Epain, Marie ; Valette, Sébastien ; Zou, Kaifeng ; Faisan, Sylvain ; Heitz, Fabrice ; Croisille, Pierre ; Fracasso, Tony ; Fanton, Laurent</creatorcontrib><description>In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (C
recon
). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + C
recon
showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology.</description><identifier>ISSN: 0937-9827</identifier><identifier>ISSN: 1437-1596</identifier><identifier>EISSN: 1437-1596</identifier><identifier>DOI: 10.1007/s00414-024-03268-2</identifier><identifier>PMID: 38862820</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Algorithms ; Anthropology ; Artificial neural networks ; Automation ; Bioengineering ; Bones ; Chronology ; Computed tomography ; Computer Science ; Deep learning ; Forensic anthropology ; Forensic computing ; Forensic Medicine ; Human remains ; Imaging ; Life Sciences ; Machine Learning ; Medical imaging ; Medical Law ; Medicine ; Medicine & Public Health ; Original Article ; Sex</subject><ispartof>International journal of legal medicine, 2024-11, Vol.138 (6), p.2617-2623</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. 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>2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c290t-335598911b4dd767e241efcfb155fb65e6148e8d15bd0090045d753c87e116cb3</cites><orcidid>0000-0001-9651-9023 ; 0000-0001-7549-4808</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/s00414-024-03268-2$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00414-024-03268-2$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>230,315,781,785,886,27929,27930,41493,42562,51324</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38862820$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://hal.science/hal-04609128$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Epain, Marie</creatorcontrib><creatorcontrib>Valette, Sébastien</creatorcontrib><creatorcontrib>Zou, Kaifeng</creatorcontrib><creatorcontrib>Faisan, Sylvain</creatorcontrib><creatorcontrib>Heitz, Fabrice</creatorcontrib><creatorcontrib>Croisille, Pierre</creatorcontrib><creatorcontrib>Fracasso, Tony</creatorcontrib><creatorcontrib>Fanton, Laurent</creatorcontrib><title>Sex estimation from coxal bones using deep learning in a population balanced by sex and age</title><title>International journal of legal medicine</title><addtitle>Int J Legal Med</addtitle><addtitle>Int J Legal Med</addtitle><description>In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (C
recon
). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + C
recon
showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology.</description><subject>Algorithms</subject><subject>Anthropology</subject><subject>Artificial neural networks</subject><subject>Automation</subject><subject>Bioengineering</subject><subject>Bones</subject><subject>Chronology</subject><subject>Computed tomography</subject><subject>Computer Science</subject><subject>Deep learning</subject><subject>Forensic anthropology</subject><subject>Forensic computing</subject><subject>Forensic Medicine</subject><subject>Human remains</subject><subject>Imaging</subject><subject>Life Sciences</subject><subject>Machine Learning</subject><subject>Medical imaging</subject><subject>Medical Law</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Original Article</subject><subject>Sex</subject><issn>0937-9827</issn><issn>1437-1596</issn><issn>1437-1596</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kUFvFSEUhYnR2Gf1D7gwJG50McqFgYFl06g1eYkL68oFgeHOc5p5MMIb0_778jq1Ji66IHDhu4d7cgh5DewDMNZ9LIy10DaM1yW40g1_QjbQiq4BadRTsmGmno3m3Ql5UcoVY9CpTj4nJ0JrxTVnG_LzO15TLIdx7w5jinTIaU_7dO0m6lPEQpcyxh0NiDOd0OV4rMZIHZ3TvExrk3eTiz0G6m9oqXouBup2-JI8G9xU8NX9fkp-fP50eX7RbL99-Xp-tm16btihEUJKow2Ab0OoAyJvAYd-8CDl4JVEBa1GHUD6wJippmXopOh1hwCq9-KUvF91f7nJzrlayTc2udFenG3t8Y61ihng-g9U9t3Kzjn9Xqpxux9Lj1M1gGkpVgBowQQIWdG3_6FXacmxOlkpbVTbVYqvVJ9TKRmHhwmA2WNMdo3J1pjsXUyW16Y399KL32N4aPmbSwXECpT6FHeY__39iOwtyPeaww</recordid><startdate>20241101</startdate><enddate>20241101</enddate><creator>Epain, Marie</creator><creator>Valette, Sébastien</creator><creator>Zou, Kaifeng</creator><creator>Faisan, Sylvain</creator><creator>Heitz, Fabrice</creator><creator>Croisille, Pierre</creator><creator>Fracasso, Tony</creator><creator>Fanton, Laurent</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><general>Springer</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>K7.</scope><scope>K9.</scope><scope>7X8</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0001-9651-9023</orcidid><orcidid>https://orcid.org/0000-0001-7549-4808</orcidid></search><sort><creationdate>20241101</creationdate><title>Sex estimation from coxal bones using deep learning in a population balanced by sex and age</title><author>Epain, Marie ; Valette, Sébastien ; Zou, Kaifeng ; Faisan, Sylvain ; Heitz, Fabrice ; Croisille, Pierre ; Fracasso, Tony ; Fanton, Laurent</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c290t-335598911b4dd767e241efcfb155fb65e6148e8d15bd0090045d753c87e116cb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Anthropology</topic><topic>Artificial neural networks</topic><topic>Automation</topic><topic>Bioengineering</topic><topic>Bones</topic><topic>Chronology</topic><topic>Computed tomography</topic><topic>Computer Science</topic><topic>Deep learning</topic><topic>Forensic anthropology</topic><topic>Forensic computing</topic><topic>Forensic Medicine</topic><topic>Human remains</topic><topic>Imaging</topic><topic>Life Sciences</topic><topic>Machine Learning</topic><topic>Medical imaging</topic><topic>Medical Law</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Original Article</topic><topic>Sex</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Epain, Marie</creatorcontrib><creatorcontrib>Valette, Sébastien</creatorcontrib><creatorcontrib>Zou, Kaifeng</creatorcontrib><creatorcontrib>Faisan, Sylvain</creatorcontrib><creatorcontrib>Heitz, Fabrice</creatorcontrib><creatorcontrib>Croisille, Pierre</creatorcontrib><creatorcontrib>Fracasso, Tony</creatorcontrib><creatorcontrib>Fanton, Laurent</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Criminal Justice (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>International journal of legal medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Epain, Marie</au><au>Valette, Sébastien</au><au>Zou, Kaifeng</au><au>Faisan, Sylvain</au><au>Heitz, Fabrice</au><au>Croisille, Pierre</au><au>Fracasso, Tony</au><au>Fanton, Laurent</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sex estimation from coxal bones using deep learning in a population balanced by sex and age</atitle><jtitle>International journal of legal medicine</jtitle><stitle>Int J Legal Med</stitle><addtitle>Int J Legal Med</addtitle><date>2024-11-01</date><risdate>2024</risdate><volume>138</volume><issue>6</issue><spage>2617</spage><epage>2623</epage><pages>2617-2623</pages><issn>0937-9827</issn><issn>1437-1596</issn><eissn>1437-1596</eissn><abstract>In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (C
recon
). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + C
recon
showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>38862820</pmid><doi>10.1007/s00414-024-03268-2</doi><tpages>7</tpages><orcidid>https://orcid.org/0000-0001-9651-9023</orcidid><orcidid>https://orcid.org/0000-0001-7549-4808</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0937-9827 |
ispartof | International journal of legal medicine, 2024-11, Vol.138 (6), p.2617-2623 |
issn | 0937-9827 1437-1596 1437-1596 |
language | eng |
recordid | cdi_hal_primary_oai_HAL_hal_04609128v1 |
source | Springer Online Journals Complete |
subjects | Algorithms Anthropology Artificial neural networks Automation Bioengineering Bones Chronology Computed tomography Computer Science Deep learning Forensic anthropology Forensic computing Forensic Medicine Human remains Imaging Life Sciences Machine Learning Medical imaging Medical Law Medicine Medicine & Public Health Original Article Sex |
title | Sex estimation from coxal bones using deep learning in a population balanced by sex and age |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-14T05%3A26%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sex%20estimation%20from%20coxal%20bones%20using%20deep%20learning%20in%20a%20population%20balanced%20by%20sex%20and%20age&rft.jtitle=International%20journal%20of%20legal%20medicine&rft.au=Epain,%20Marie&rft.date=2024-11-01&rft.volume=138&rft.issue=6&rft.spage=2617&rft.epage=2623&rft.pages=2617-2623&rft.issn=0937-9827&rft.eissn=1437-1596&rft_id=info:doi/10.1007/s00414-024-03268-2&rft_dat=%3Cproquest_hal_p%3E3118389647%3C/proquest_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3118389647&rft_id=info:pmid/38862820&rfr_iscdi=true |