FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound

Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Chaoyu, Yang, Xin, Huang, Yuhao, Shi, Wenlong, Cao, Yan, Luo, Mingyuan, Hu, Xindi, Zhue, Lei, Yu, Lequan, Yue, Kejuan, Zhang, Yuanji, Xiong, Yi, Ni, Dong, Huang, Weijun
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Chen, Chaoyu
Yang, Xin
Huang, Yuhao
Shi, Wenlong
Cao, Yan
Luo, Mingyuan
Hu, Xindi
Zhue, Lei
Yu, Lequan
Yue, Kejuan
Zhang, Yuanji
Xiong, Yi
Ni, Dong
Huang, Weijun
description Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements, plane localization, and fetal movement monitoring. However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses. In this study, we propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. Our contribution is three-fold. First, we propose a heuristic scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches, which can enlarge the input image resolution for better results under limited GPU memory. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. It separates the hidden classification task from the landmark localization task and thus progressively eases model learning. Last, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online. Extensive experiments and diverse applications on a large-scale fetal US dataset including 1000 volumes with 22 landmarks per volume demonstrate that our method outperforms other strong competitors.
doi_str_mv 10.48550/arxiv.2310.19293
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2310_19293</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2310_19293</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-bbb2effb43d14c3d716623153a5558a943149bd8a280e66beba65139dc7f8f263</originalsourceid><addsrcrecordid>eNotj7tOwzAYRr0woMIDMNUvkDb2bzs2TFVJL1IRHQpr9Du2RaTgVHGK4O1JL9MnneHTOYQ8sXwmtJT5HPvf5mfGYQTMcAP35GXlh1N6w-Mnf6Zl_MJYe0dHiC3dd8nTMg3NNw5NF2kTKbzSj3boMXWn6B7IXcA2-cfbTshhVR6Wm2z3vt4uF7sMVQGZtZb7EKwAx0QNrmBKjQYSUEqp0QhgwlinkevcK2W9RSUZGFcXQQeuYEKm19uLfXXsR5_-rzpXVJcK-AfAzkC7</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound</title><source>arXiv.org</source><creator>Chen, Chaoyu ; Yang, Xin ; Huang, Yuhao ; Shi, Wenlong ; Cao, Yan ; Luo, Mingyuan ; Hu, Xindi ; Zhue, Lei ; Yu, Lequan ; Yue, Kejuan ; Zhang, Yuanji ; Xiong, Yi ; Ni, Dong ; Huang, Weijun</creator><creatorcontrib>Chen, Chaoyu ; Yang, Xin ; Huang, Yuhao ; Shi, Wenlong ; Cao, Yan ; Luo, Mingyuan ; Hu, Xindi ; Zhue, Lei ; Yu, Lequan ; Yue, Kejuan ; Zhang, Yuanji ; Xiong, Yi ; Ni, Dong ; Huang, Weijun</creatorcontrib><description>Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements, plane localization, and fetal movement monitoring. However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses. In this study, we propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. Our contribution is three-fold. First, we propose a heuristic scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches, which can enlarge the input image resolution for better results under limited GPU memory. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. It separates the hidden classification task from the landmark localization task and thus progressively eases model learning. Last, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online. Extensive experiments and diverse applications on a large-scale fetal US dataset including 1000 volumes with 22 landmarks per volume demonstrate that our method outperforms other strong competitors.</description><identifier>DOI: 10.48550/arxiv.2310.19293</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2023-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2310.19293$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2310.19293$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chen, Chaoyu</creatorcontrib><creatorcontrib>Yang, Xin</creatorcontrib><creatorcontrib>Huang, Yuhao</creatorcontrib><creatorcontrib>Shi, Wenlong</creatorcontrib><creatorcontrib>Cao, Yan</creatorcontrib><creatorcontrib>Luo, Mingyuan</creatorcontrib><creatorcontrib>Hu, Xindi</creatorcontrib><creatorcontrib>Zhue, Lei</creatorcontrib><creatorcontrib>Yu, Lequan</creatorcontrib><creatorcontrib>Yue, Kejuan</creatorcontrib><creatorcontrib>Zhang, Yuanji</creatorcontrib><creatorcontrib>Xiong, Yi</creatorcontrib><creatorcontrib>Ni, Dong</creatorcontrib><creatorcontrib>Huang, Weijun</creatorcontrib><title>FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound</title><description>Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements, plane localization, and fetal movement monitoring. However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses. In this study, we propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. Our contribution is three-fold. First, we propose a heuristic scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches, which can enlarge the input image resolution for better results under limited GPU memory. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. It separates the hidden classification task from the landmark localization task and thus progressively eases model learning. Last, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online. Extensive experiments and diverse applications on a large-scale fetal US dataset including 1000 volumes with 22 landmarks per volume demonstrate that our method outperforms other strong competitors.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tOwzAYRr0woMIDMNUvkDb2bzs2TFVJL1IRHQpr9Du2RaTgVHGK4O1JL9MnneHTOYQ8sXwmtJT5HPvf5mfGYQTMcAP35GXlh1N6w-Mnf6Zl_MJYe0dHiC3dd8nTMg3NNw5NF2kTKbzSj3boMXWn6B7IXcA2-cfbTshhVR6Wm2z3vt4uF7sMVQGZtZb7EKwAx0QNrmBKjQYSUEqp0QhgwlinkevcK2W9RSUZGFcXQQeuYEKm19uLfXXsR5_-rzpXVJcK-AfAzkC7</recordid><startdate>20231030</startdate><enddate>20231030</enddate><creator>Chen, Chaoyu</creator><creator>Yang, Xin</creator><creator>Huang, Yuhao</creator><creator>Shi, Wenlong</creator><creator>Cao, Yan</creator><creator>Luo, Mingyuan</creator><creator>Hu, Xindi</creator><creator>Zhue, Lei</creator><creator>Yu, Lequan</creator><creator>Yue, Kejuan</creator><creator>Zhang, Yuanji</creator><creator>Xiong, Yi</creator><creator>Ni, Dong</creator><creator>Huang, Weijun</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20231030</creationdate><title>FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound</title><author>Chen, Chaoyu ; Yang, Xin ; Huang, Yuhao ; Shi, Wenlong ; Cao, Yan ; Luo, Mingyuan ; Hu, Xindi ; Zhue, Lei ; Yu, Lequan ; Yue, Kejuan ; Zhang, Yuanji ; Xiong, Yi ; Ni, Dong ; Huang, Weijun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-bbb2effb43d14c3d716623153a5558a943149bd8a280e66beba65139dc7f8f263</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Chen, Chaoyu</creatorcontrib><creatorcontrib>Yang, Xin</creatorcontrib><creatorcontrib>Huang, Yuhao</creatorcontrib><creatorcontrib>Shi, Wenlong</creatorcontrib><creatorcontrib>Cao, Yan</creatorcontrib><creatorcontrib>Luo, Mingyuan</creatorcontrib><creatorcontrib>Hu, Xindi</creatorcontrib><creatorcontrib>Zhue, Lei</creatorcontrib><creatorcontrib>Yu, Lequan</creatorcontrib><creatorcontrib>Yue, Kejuan</creatorcontrib><creatorcontrib>Zhang, Yuanji</creatorcontrib><creatorcontrib>Xiong, Yi</creatorcontrib><creatorcontrib>Ni, Dong</creatorcontrib><creatorcontrib>Huang, Weijun</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Chaoyu</au><au>Yang, Xin</au><au>Huang, Yuhao</au><au>Shi, Wenlong</au><au>Cao, Yan</au><au>Luo, Mingyuan</au><au>Hu, Xindi</au><au>Zhue, Lei</au><au>Yu, Lequan</au><au>Yue, Kejuan</au><au>Zhang, Yuanji</au><au>Xiong, Yi</au><au>Ni, Dong</au><au>Huang, Weijun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound</atitle><date>2023-10-30</date><risdate>2023</risdate><abstract>Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal anatomical landmarks. Its primary objective is to provide comprehensive information about the fetus through landmark connections, thus benefiting various critical applications, such as biometric measurements, plane localization, and fetal movement monitoring. However, accurately estimating the 3D fetal pose in US volume has several challenges, including poor image quality, limited GPU memory for tackling high dimensional data, symmetrical or ambiguous anatomical structures, and considerable variations in fetal poses. In this study, we propose a novel 3D fetal pose estimation framework (called FetusMapV2) to overcome the above challenges. Our contribution is three-fold. First, we propose a heuristic scheme that explores the complementary network structure-unconstrained and activation-unreserved GPU memory management approaches, which can enlarge the input image resolution for better results under limited GPU memory. Second, we design a novel Pair Loss to mitigate confusion caused by symmetrical and similar anatomical structures. It separates the hidden classification task from the landmark localization task and thus progressively eases model learning. Last, we propose a shape priors-based self-supervised learning by selecting the relatively stable landmarks to refine the pose online. Extensive experiments and diverse applications on a large-scale fetal US dataset including 1000 volumes with 22 landmarks per volume demonstrate that our method outperforms other strong competitors.</abstract><doi>10.48550/arxiv.2310.19293</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2310.19293
ispartof
issn
language eng
recordid cdi_arxiv_primary_2310_19293
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T06%3A13%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=FetusMapV2:%20Enhanced%20Fetal%20Pose%20Estimation%20in%203D%20Ultrasound&rft.au=Chen,%20Chaoyu&rft.date=2023-10-30&rft_id=info:doi/10.48550/arxiv.2310.19293&rft_dat=%3Carxiv_GOX%3E2310_19293%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true