Loading…

Boosting Skull-Stripping Performance for Pediatric Brain Images

Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain dev...

Full description

Saved in:

Bibliographic Details
Published in:	2024 IEEE International Symposium on Biomedical Imaging (ISBI) 2024-05, Vol.2024, p.1-5
Main Authors:	Kelley, William, Ngo, Nathan, Dalca, Adrian V., Fischl, Bruce, Zollei, Lilla, Hoffmann, Malte
Format:	Article
Language:	English
Subjects:	Biological system modeling brain extraction Brain modeling Buildings Data acquisition infant machine learning Magnetic resonance imaging newborn pediatric MRI Runtime skull-stripping Sociology toddler
Online Access:	Request full text
Tags:	Add Tag No Tags, Be the first to tag this record!

cited_by
cites
container_end_page	5
container_issue
container_start_page	1
container_title	2024 IEEE International Symposium on Biomedical Imaging (ISBI)
container_volume	2024
creator	Kelley, William Ngo, Nathan Dalca, Adrian V. Fischl, Bruce Zollei, Lilla Hoffmann, Malte
description	Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain development, it is essential to develop robust and well-tested tools ready for the relevant data processing. However, the broad range of neuroanatomical variation in the developing brain, combined with additional challenges such as high motion levels, as well as shoulder and chest signal in the images, leaves many adult-specific tools ill-suited for pediatric skull-stripping. Building on an existing framework for robust and accurate skull-stripping, we propose developmental SynthStrip (d-SynthStrip), a skull-stripping model tailored to pediatric images. This framework exposes networks to highly variable images synthesized from label maps. Our model substantially outperforms pediatric baselines across scan types and age cohorts. In addition, the
doi_str_mv	10.1109/ISBI56570.2024.10635307
format	article
fullrecord	<record><control><sourceid>proquest_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10635307</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10635307</ieee_id><sourcerecordid>3113745844</sourcerecordid><originalsourceid>FETCH-LOGICAL-i1967-e850bbca0e86fe84f8c23c306d844699c5f53ed2410bee6c328143786c0cc40a3</originalsourceid><addsrcrecordid>eNo9kFtLw0AQhVdRbKn9B6J59CV1N7PXJ7HFS6CgUH0Om82krOZmtnnw3xtp67zMOZyPAzOE3DC6YIyau3SzTIUUii4SmvAFoxIEUHVC5kYZDYICAwB9SqbMcBFrLpKzg1Ym0RMyD-GTjqM4B8ovyAQMKMYVTMn9sm3DzjfbaPM1VFW82fW-6_78G_Zl29e2cRiNYvSFt2PqomVvfROltd1iuCTnpa0Czg97Rj6eHt9XL_H69TldPaxjz4xUMWpB89xZilqWqHmpXQIOqCw059IYJ0oBWCSc0RxROkg046C0dNQ5Ti3MyO2-t-vb7wHDLqt9cFhVtsF2CBkwBoqLsW1Erw_okNdYZF3va9v_ZMejR-BqD3hE_I-Pb4VfBQRl6w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3113745844</pqid></control><display><type>article</type><title>Boosting Skull-Stripping Performance for Pediatric Brain Images</title><source>IEEE Xplore All Conference Series</source><creator>Kelley, William ; Ngo, Nathan ; Dalca, Adrian V. ; Fischl, Bruce ; Zollei, Lilla ; Hoffmann, Malte</creator><creatorcontrib>Kelley, William ; Ngo, Nathan ; Dalca, Adrian V. ; Fischl, Bruce ; Zollei, Lilla ; Hoffmann, Malte</creatorcontrib><description>Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain development, it is essential to develop robust and well-tested tools ready for the relevant data processing. However, the broad range of neuroanatomical variation in the developing brain, combined with additional challenges such as high motion levels, as well as shoulder and chest signal in the images, leaves many adult-specific tools ill-suited for pediatric skull-stripping. Building on an existing framework for robust and accurate skull-stripping, we propose developmental SynthStrip (d-SynthStrip), a skull-stripping model tailored to pediatric images. This framework exposes networks to highly variable images synthesized from label maps. Our model substantially outperforms pediatric baselines across scan types and age cohorts. In addition, the <1-minute runtime of our tool compares favorably to the fastest baselines. We distribute our model at https://w3id.org/synthstrip.</description><identifier>ISSN: 1945-7928</identifier><identifier>EISSN: 1945-8452</identifier><identifier>EISBN: 9798350313338</identifier><identifier>DOI: 10.1109/ISBI56570.2024.10635307</identifier><identifier>PMID: 39371473</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Biological system modeling ; brain extraction ; Brain modeling ; Buildings ; Data acquisition ; infant ; machine learning ; Magnetic resonance imaging ; newborn ; pediatric MRI ; Runtime ; skull-stripping ; Sociology ; toddler</subject><ispartof>2024 IEEE International Symposium on Biomedical Imaging (ISBI), 2024-05, Vol.2024, p.1-5</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10635307$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,776,780,785,786,27900,27901,54529,54906</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10635307$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39371473$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Kelley, William</creatorcontrib><creatorcontrib>Ngo, Nathan</creatorcontrib><creatorcontrib>Dalca, Adrian V.</creatorcontrib><creatorcontrib>Fischl, Bruce</creatorcontrib><creatorcontrib>Zollei, Lilla</creatorcontrib><creatorcontrib>Hoffmann, Malte</creatorcontrib><title>Boosting Skull-Stripping Performance for Pediatric Brain Images</title><title>2024 IEEE International Symposium on Biomedical Imaging (ISBI)</title><addtitle>ISBI</addtitle><addtitle>Proc IEEE Int Symp Biomed Imaging</addtitle><description>Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain development, it is essential to develop robust and well-tested tools ready for the relevant data processing. However, the broad range of neuroanatomical variation in the developing brain, combined with additional challenges such as high motion levels, as well as shoulder and chest signal in the images, leaves many adult-specific tools ill-suited for pediatric skull-stripping. Building on an existing framework for robust and accurate skull-stripping, we propose developmental SynthStrip (d-SynthStrip), a skull-stripping model tailored to pediatric images. This framework exposes networks to highly variable images synthesized from label maps. Our model substantially outperforms pediatric baselines across scan types and age cohorts. In addition, the <1-minute runtime of our tool compares favorably to the fastest baselines. We distribute our model at https://w3id.org/synthstrip.</description><subject>Biological system modeling</subject><subject>brain extraction</subject><subject>Brain modeling</subject><subject>Buildings</subject><subject>Data acquisition</subject><subject>infant</subject><subject>machine learning</subject><subject>Magnetic resonance imaging</subject><subject>newborn</subject><subject>pediatric MRI</subject><subject>Runtime</subject><subject>skull-stripping</subject><subject>Sociology</subject><subject>toddler</subject><issn>1945-7928</issn><issn>1945-8452</issn><isbn>9798350313338</isbn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>6IE</sourceid><recordid>eNo9kFtLw0AQhVdRbKn9B6J59CV1N7PXJ7HFS6CgUH0Om82krOZmtnnw3xtp67zMOZyPAzOE3DC6YIyau3SzTIUUii4SmvAFoxIEUHVC5kYZDYICAwB9SqbMcBFrLpKzg1Ym0RMyD-GTjqM4B8ovyAQMKMYVTMn9sm3DzjfbaPM1VFW82fW-6_78G_Zl29e2cRiNYvSFt2PqomVvfROltd1iuCTnpa0Czg97Rj6eHt9XL_H69TldPaxjz4xUMWpB89xZilqWqHmpXQIOqCw059IYJ0oBWCSc0RxROkg046C0dNQ5Ti3MyO2-t-vb7wHDLqt9cFhVtsF2CBkwBoqLsW1Erw_okNdYZF3va9v_ZMejR-BqD3hE_I-Pb4VfBQRl6w</recordid><startdate>202405</startdate><enddate>202405</enddate><creator>Kelley, William</creator><creator>Ngo, Nathan</creator><creator>Dalca, Adrian V.</creator><creator>Fischl, Bruce</creator><creator>Zollei, Lilla</creator><creator>Hoffmann, Malte</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>NPM</scope><scope>7X8</scope></search><sort><creationdate>202405</creationdate><title>Boosting Skull-Stripping Performance for Pediatric Brain Images</title><author>Kelley, William ; Ngo, Nathan ; Dalca, Adrian V. ; Fischl, Bruce ; Zollei, Lilla ; Hoffmann, Malte</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i1967-e850bbca0e86fe84f8c23c306d844699c5f53ed2410bee6c328143786c0cc40a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Biological system modeling</topic><topic>brain extraction</topic><topic>Brain modeling</topic><topic>Buildings</topic><topic>Data acquisition</topic><topic>infant</topic><topic>machine learning</topic><topic>Magnetic resonance imaging</topic><topic>newborn</topic><topic>pediatric MRI</topic><topic>Runtime</topic><topic>skull-stripping</topic><topic>Sociology</topic><topic>toddler</topic><toplevel>online_resources</toplevel><creatorcontrib>Kelley, William</creatorcontrib><creatorcontrib>Ngo, Nathan</creatorcontrib><creatorcontrib>Dalca, Adrian V.</creatorcontrib><creatorcontrib>Fischl, Bruce</creatorcontrib><creatorcontrib>Zollei, Lilla</creatorcontrib><creatorcontrib>Hoffmann, Malte</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>PubMed</collection><collection>MEDLINE - Academic</collection><jtitle>2024 IEEE International Symposium on Biomedical Imaging (ISBI)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kelley, William</au><au>Ngo, Nathan</au><au>Dalca, Adrian V.</au><au>Fischl, Bruce</au><au>Zollei, Lilla</au><au>Hoffmann, Malte</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Boosting Skull-Stripping Performance for Pediatric Brain Images</atitle><jtitle>2024 IEEE International Symposium on Biomedical Imaging (ISBI)</jtitle><stitle>ISBI</stitle><addtitle>Proc IEEE Int Symp Biomed Imaging</addtitle><date>2024-05</date><risdate>2024</risdate><volume>2024</volume><spage>1</spage><epage>5</epage><pages>1-5</pages><issn>1945-7928</issn><eissn>1945-8452</eissn><eisbn>9798350313338</eisbn><abstract>Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain development, it is essential to develop robust and well-tested tools ready for the relevant data processing. However, the broad range of neuroanatomical variation in the developing brain, combined with additional challenges such as high motion levels, as well as shoulder and chest signal in the images, leaves many adult-specific tools ill-suited for pediatric skull-stripping. Building on an existing framework for robust and accurate skull-stripping, we propose developmental SynthStrip (d-SynthStrip), a skull-stripping model tailored to pediatric images. This framework exposes networks to highly variable images synthesized from label maps. Our model substantially outperforms pediatric baselines across scan types and age cohorts. In addition, the <1-minute runtime of our tool compares favorably to the fastest baselines. We distribute our model at https://w3id.org/synthstrip.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>39371473</pmid><doi>10.1109/ISBI56570.2024.10635307</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	ISSN: 1945-7928
ispartof	2024 IEEE International Symposium on Biomedical Imaging (ISBI), 2024-05, Vol.2024, p.1-5
issn	1945-7928 1945-8452
language	eng
recordid	cdi_ieee_primary_10635307
source	IEEE Xplore All Conference Series
subjects	Biological system modeling brain extraction Brain modeling Buildings Data acquisition infant machine learning Magnetic resonance imaging newborn pediatric MRI Runtime skull-stripping Sociology toddler
title	Boosting Skull-Stripping Performance for Pediatric Brain Images
url	http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-24T14%3A17%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Boosting%20Skull-Stripping%20Performance%20for%20Pediatric%20Brain%20Images&rft.jtitle=2024%20IEEE%20International%20Symposium%20on%20Biomedical%20Imaging%20(ISBI)&rft.au=Kelley,%20William&rft.date=2024-05&rft.volume=2024&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.issn=1945-7928&rft.eissn=1945-8452&rft_id=info:doi/10.1109/ISBI56570.2024.10635307&rft.eisbn=9798350313338&rft_dat=%3Cproquest_CHZPO%3E3113745844%3C/proquest_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i1967-e850bbca0e86fe84f8c23c306d844699c5f53ed2410bee6c328143786c0cc40a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3113745844&rft_id=info:pmid/39371473&rft_ieee_id=10635307&rfr_iscdi=true