File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: FetusMapV2: Enhanced fetal pose estimation in 3D ultrasound

TitleFetusMapV2: Enhanced fetal pose estimation in 3D ultrasound
Authors
Keywords3D ultrasound
GPU memory management
Pair loss
Pose estimation
Self-supervised learning
Issue Date1-Jan-2024
PublisherElsevier
Citation
Medical Image Analysis, 2024, v. 91 How to Cite?
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.


Persistent Identifierhttp://hdl.handle.net/10722/340334
ISSN
2023 Impact Factor: 10.7
2023 SCImago Journal Rankings: 4.112
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorChen, CY-
dc.contributor.authorYang, X-
dc.contributor.authorHuang, YH-
dc.contributor.authorShi, WL-
dc.contributor.authorCao, Y-
dc.contributor.authorLuo, MY-
dc.contributor.authorHu, XD-
dc.contributor.authorZhu, L-
dc.contributor.authorYu, LQ-
dc.contributor.authorYue, KJ-
dc.contributor.authorZhang, YJ-
dc.contributor.authorXiong, Y-
dc.contributor.authorNi, D-
dc.contributor.authorHuang, WJ -
dc.date.accessioned2024-03-11T10:43:22Z-
dc.date.available2024-03-11T10:43:22Z-
dc.date.issued2024-01-01-
dc.identifier.citationMedical Image Analysis, 2024, v. 91-
dc.identifier.issn1361-8415-
dc.identifier.urihttp://hdl.handle.net/10722/340334-
dc.description.abstract<p>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.</p>-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofMedical Image Analysis-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subject3D ultrasound-
dc.subjectGPU memory management-
dc.subjectPair loss-
dc.subjectPose estimation-
dc.subjectSelf-supervised learning-
dc.titleFetusMapV2: Enhanced fetal pose estimation in 3D ultrasound-
dc.typeArticle-
dc.identifier.doi10.1016/j.media.2023.103013-
dc.identifier.scopuseid_2-s2.0-85175082992-
dc.identifier.volume91-
dc.identifier.isiWOS:001104004000001-
dc.publisher.placeAMSTERDAM-
dc.identifier.issnl1361-8415-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats