CNN-based Landmark Detection in Cardiac CTA Scans

Fast and accurate anatomical landmark detection can benefit many medical image analysis methods. Here, we propose a method to automatically detect anatomical landmarks in medical images. Automatic landmark detection is performed with a patch-based fully convolutional neural network (FCNN) that combi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2018-04
Hauptverfasser: Noothout, Julia M H, de Vos, Bob D, Wolterink, Jelmer M, Leiner, Tim, Išgum, Ivana
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Noothout, Julia M H
de Vos, Bob D
Wolterink, Jelmer M
Leiner, Tim
Išgum, Ivana
description Fast and accurate anatomical landmark detection can benefit many medical image analysis methods. Here, we propose a method to automatically detect anatomical landmarks in medical images. Automatic landmark detection is performed with a patch-based fully convolutional neural network (FCNN) that combines regression and classification. For any given image patch, regression is used to predict the 3D displacement vector from the image patch to the landmark. Simultaneously, classification is used to identify patches that contain the landmark. Under the assumption that patches close to a landmark can determine the landmark location more precisely than patches farther from it, only those patches that contain the landmark according to classification are used to determine the landmark location. The landmark location is obtained by calculating the average landmark location using the computed 3D displacement vectors. The method is evaluated using detection of six clinically relevant landmarks in coronary CT angiography (CCTA) scans: the right and left ostium, the bifurcation of the left main coronary artery (LM) into the left anterior descending and the left circumflex artery, and the origin of the right, non-coronary, and left aortic valve commissure. The proposed method achieved an average Euclidean distance error of 2.19 mm and 2.88 mm for the right and left ostium respectively, 3.78 mm for the bifurcation of the LM, and 1.82 mm, 2.10 mm and 1.89 mm for the origin of the right, non-coronary, and left aortic valve commissure respectively, demonstrating accurate performance. The proposed combination of regression and classification can be used to accurately detect landmarks in CCTA scans.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2072031107</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2072031107</sourcerecordid><originalsourceid>FETCH-proquest_journals_20720311073</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwdPbz001KLE5NUfBJzEvJTSzKVnBJLUlNLsnMz1PIzFNwTixKyUxMVnAOcVQITk7MK-ZhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjA3MjA2NDQwNzY-JUAQDslTHG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2072031107</pqid></control><display><type>article</type><title>CNN-based Landmark Detection in Cardiac CTA Scans</title><source>Free E- Journals</source><creator>Noothout, Julia M H ; de Vos, Bob D ; Wolterink, Jelmer M ; Leiner, Tim ; Išgum, Ivana</creator><creatorcontrib>Noothout, Julia M H ; de Vos, Bob D ; Wolterink, Jelmer M ; Leiner, Tim ; Išgum, Ivana</creatorcontrib><description>Fast and accurate anatomical landmark detection can benefit many medical image analysis methods. Here, we propose a method to automatically detect anatomical landmarks in medical images. Automatic landmark detection is performed with a patch-based fully convolutional neural network (FCNN) that combines regression and classification. For any given image patch, regression is used to predict the 3D displacement vector from the image patch to the landmark. Simultaneously, classification is used to identify patches that contain the landmark. Under the assumption that patches close to a landmark can determine the landmark location more precisely than patches farther from it, only those patches that contain the landmark according to classification are used to determine the landmark location. The landmark location is obtained by calculating the average landmark location using the computed 3D displacement vectors. The method is evaluated using detection of six clinically relevant landmarks in coronary CT angiography (CCTA) scans: the right and left ostium, the bifurcation of the left main coronary artery (LM) into the left anterior descending and the left circumflex artery, and the origin of the right, non-coronary, and left aortic valve commissure. The proposed method achieved an average Euclidean distance error of 2.19 mm and 2.88 mm for the right and left ostium respectively, 3.78 mm for the bifurcation of the LM, and 1.82 mm, 2.10 mm and 1.89 mm for the origin of the right, non-coronary, and left aortic valve commissure respectively, demonstrating accurate performance. The proposed combination of regression and classification can be used to accurately detect landmarks in CCTA scans.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Angiography ; Artificial neural networks ; Bifurcations ; Classification ; Computed tomography ; Euclidean geometry ; Image analysis ; Image classification ; Image detection ; Landmarks ; Medical imaging ; Neural networks ; Patches (structures) ; Regression analysis</subject><ispartof>arXiv.org, 2018-04</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>776,780</link.rule.ids></links><search><creatorcontrib>Noothout, Julia M H</creatorcontrib><creatorcontrib>de Vos, Bob D</creatorcontrib><creatorcontrib>Wolterink, Jelmer M</creatorcontrib><creatorcontrib>Leiner, Tim</creatorcontrib><creatorcontrib>Išgum, Ivana</creatorcontrib><title>CNN-based Landmark Detection in Cardiac CTA Scans</title><title>arXiv.org</title><description>Fast and accurate anatomical landmark detection can benefit many medical image analysis methods. Here, we propose a method to automatically detect anatomical landmarks in medical images. Automatic landmark detection is performed with a patch-based fully convolutional neural network (FCNN) that combines regression and classification. For any given image patch, regression is used to predict the 3D displacement vector from the image patch to the landmark. Simultaneously, classification is used to identify patches that contain the landmark. Under the assumption that patches close to a landmark can determine the landmark location more precisely than patches farther from it, only those patches that contain the landmark according to classification are used to determine the landmark location. The landmark location is obtained by calculating the average landmark location using the computed 3D displacement vectors. The method is evaluated using detection of six clinically relevant landmarks in coronary CT angiography (CCTA) scans: the right and left ostium, the bifurcation of the left main coronary artery (LM) into the left anterior descending and the left circumflex artery, and the origin of the right, non-coronary, and left aortic valve commissure. The proposed method achieved an average Euclidean distance error of 2.19 mm and 2.88 mm for the right and left ostium respectively, 3.78 mm for the bifurcation of the LM, and 1.82 mm, 2.10 mm and 1.89 mm for the origin of the right, non-coronary, and left aortic valve commissure respectively, demonstrating accurate performance. The proposed combination of regression and classification can be used to accurately detect landmarks in CCTA scans.</description><subject>Angiography</subject><subject>Artificial neural networks</subject><subject>Bifurcations</subject><subject>Classification</subject><subject>Computed tomography</subject><subject>Euclidean geometry</subject><subject>Image analysis</subject><subject>Image classification</subject><subject>Image detection</subject><subject>Landmarks</subject><subject>Medical imaging</subject><subject>Neural networks</subject><subject>Patches (structures)</subject><subject>Regression analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwdPbz001KLE5NUfBJzEvJTSzKVnBJLUlNLsnMz1PIzFNwTixKyUxMVnAOcVQITk7MK-ZhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjA3MjA2NDQwNzY-JUAQDslTHG</recordid><startdate>20180413</startdate><enddate>20180413</enddate><creator>Noothout, Julia M H</creator><creator>de Vos, Bob D</creator><creator>Wolterink, Jelmer M</creator><creator>Leiner, Tim</creator><creator>Išgum, Ivana</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20180413</creationdate><title>CNN-based Landmark Detection in Cardiac CTA Scans</title><author>Noothout, Julia M H ; de Vos, Bob D ; Wolterink, Jelmer M ; Leiner, Tim ; Išgum, Ivana</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20720311073</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Angiography</topic><topic>Artificial neural networks</topic><topic>Bifurcations</topic><topic>Classification</topic><topic>Computed tomography</topic><topic>Euclidean geometry</topic><topic>Image analysis</topic><topic>Image classification</topic><topic>Image detection</topic><topic>Landmarks</topic><topic>Medical imaging</topic><topic>Neural networks</topic><topic>Patches (structures)</topic><topic>Regression analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Noothout, Julia M H</creatorcontrib><creatorcontrib>de Vos, Bob D</creatorcontrib><creatorcontrib>Wolterink, Jelmer M</creatorcontrib><creatorcontrib>Leiner, Tim</creatorcontrib><creatorcontrib>Išgum, Ivana</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Noothout, Julia M H</au><au>de Vos, Bob D</au><au>Wolterink, Jelmer M</au><au>Leiner, Tim</au><au>Išgum, Ivana</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>CNN-based Landmark Detection in Cardiac CTA Scans</atitle><jtitle>arXiv.org</jtitle><date>2018-04-13</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Fast and accurate anatomical landmark detection can benefit many medical image analysis methods. Here, we propose a method to automatically detect anatomical landmarks in medical images. Automatic landmark detection is performed with a patch-based fully convolutional neural network (FCNN) that combines regression and classification. For any given image patch, regression is used to predict the 3D displacement vector from the image patch to the landmark. Simultaneously, classification is used to identify patches that contain the landmark. Under the assumption that patches close to a landmark can determine the landmark location more precisely than patches farther from it, only those patches that contain the landmark according to classification are used to determine the landmark location. The landmark location is obtained by calculating the average landmark location using the computed 3D displacement vectors. The method is evaluated using detection of six clinically relevant landmarks in coronary CT angiography (CCTA) scans: the right and left ostium, the bifurcation of the left main coronary artery (LM) into the left anterior descending and the left circumflex artery, and the origin of the right, non-coronary, and left aortic valve commissure. The proposed method achieved an average Euclidean distance error of 2.19 mm and 2.88 mm for the right and left ostium respectively, 3.78 mm for the bifurcation of the LM, and 1.82 mm, 2.10 mm and 1.89 mm for the origin of the right, non-coronary, and left aortic valve commissure respectively, demonstrating accurate performance. The proposed combination of regression and classification can be used to accurately detect landmarks in CCTA scans.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-04
issn 2331-8422
language eng
recordid cdi_proquest_journals_2072031107
source Free E- Journals
subjects Angiography
Artificial neural networks
Bifurcations
Classification
Computed tomography
Euclidean geometry
Image analysis
Image classification
Image detection
Landmarks
Medical imaging
Neural networks
Patches (structures)
Regression analysis
title CNN-based Landmark Detection in Cardiac CTA Scans
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T20%3A06%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=CNN-based%20Landmark%20Detection%20in%20Cardiac%20CTA%20Scans&rft.jtitle=arXiv.org&rft.au=Noothout,%20Julia%20M%20H&rft.date=2018-04-13&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2072031107%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2072031107&rft_id=info:pmid/&rfr_iscdi=true