2D/3D Megavoltage Image Registration Using Convolutional Neural Networks

2D/3D Megavoltage Image Registration Using Convolutional Neural Networks

We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltag...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pinheiro, Hector N. B, Ren, Tsang Ing, Scheib, Stefan, Rosselet, Armel, Thieme-Marti, Stefan
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
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 Pinheiro, Hector N. B
Ren, Tsang Ing
Scheib, Stefan
Rosselet, Armel
Thieme-Marti, Stefan
description We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltage images, the same does not occur for megavoltage images due to the lower image quality. Also, these methods most of the times do not present a good capture range. To deal with this problem, we propose the use of Convolutional Neural Network. The experiments were performed using a dataset of 50 brain images. The results showed to be promising compared to traditional image registration methods.
doi_str_mv 10.48550/arxiv.1811.11816
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1811_11816</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1811_11816</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-1c973faf761473a84b22194889a94e159b56c974185f6d1868b5c63597ca2f3b3</originalsourceid><addsrcrecordid>eNotj8tqwkAYhWfTRbE-QFfOCyT6Z-7LEusFbAui6_AnzoShMSmTqO3bm8RuzoHDx4GPkFdYxFwLsZhj-PXXGDRADH3KZ7JJlnO2pB-2xGtTdVhauj0Pubelb7uAnW9qemx9XdK0qXvmMixY0U97CWN1tyZ8ty_kyWHV2ul_T8hh9X5IN9Hua71N33YRSiUjKIxiDp2SwBVDzfMkAcO1Nmi4BWFyIXuEgxZOnkBLnYtCMmFUgYljOZuQ2eN2VMl-gj9j-MsGpWxUYnfw50VS</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>2D/3D Megavoltage Image Registration Using Convolutional Neural Networks</title><source>arXiv.org</source><creator>Pinheiro, Hector N. B ; Ren, Tsang Ing ; Scheib, Stefan ; Rosselet, Armel ; Thieme-Marti, Stefan</creator><creatorcontrib>Pinheiro, Hector N. B ; Ren, Tsang Ing ; Scheib, Stefan ; Rosselet, Armel ; Thieme-Marti, Stefan</creatorcontrib><description>We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltage images, the same does not occur for megavoltage images due to the lower image quality. Also, these methods most of the times do not present a good capture range. To deal with this problem, we propose the use of Convolutional Neural Network. The experiments were performed using a dataset of 50 brain images. The results showed to be promising compared to traditional image registration methods.</description><identifier>DOI: 10.48550/arxiv.1811.11816</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2018-11</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1811.11816$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1811.11816$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Pinheiro, Hector N. B</creatorcontrib><creatorcontrib>Ren, Tsang Ing</creatorcontrib><creatorcontrib>Scheib, Stefan</creatorcontrib><creatorcontrib>Rosselet, Armel</creatorcontrib><creatorcontrib>Thieme-Marti, Stefan</creatorcontrib><title>2D/3D Megavoltage Image Registration Using Convolutional Neural Networks</title><description>We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltage images, the same does not occur for megavoltage images due to the lower image quality. Also, these methods most of the times do not present a good capture range. To deal with this problem, we propose the use of Convolutional Neural Network. The experiments were performed using a dataset of 50 brain images. The results showed to be promising compared to traditional image registration methods.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwkAYhWfTRbE-QFfOCyT6Z-7LEusFbAui6_AnzoShMSmTqO3bm8RuzoHDx4GPkFdYxFwLsZhj-PXXGDRADH3KZ7JJlnO2pB-2xGtTdVhauj0Pubelb7uAnW9qemx9XdK0qXvmMixY0U97CWN1tyZ8ty_kyWHV2ul_T8hh9X5IN9Hua71N33YRSiUjKIxiDp2SwBVDzfMkAcO1Nmi4BWFyIXuEgxZOnkBLnYtCMmFUgYljOZuQ2eN2VMl-gj9j-MsGpWxUYnfw50VS</recordid><startdate>20181128</startdate><enddate>20181128</enddate><creator>Pinheiro, Hector N. B</creator><creator>Ren, Tsang Ing</creator><creator>Scheib, Stefan</creator><creator>Rosselet, Armel</creator><creator>Thieme-Marti, Stefan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20181128</creationdate><title>2D/3D Megavoltage Image Registration Using Convolutional Neural Networks</title><author>Pinheiro, Hector N. B ; Ren, Tsang Ing ; Scheib, Stefan ; Rosselet, Armel ; Thieme-Marti, Stefan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-1c973faf761473a84b22194889a94e159b56c974185f6d1868b5c63597ca2f3b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Pinheiro, Hector N. B</creatorcontrib><creatorcontrib>Ren, Tsang Ing</creatorcontrib><creatorcontrib>Scheib, Stefan</creatorcontrib><creatorcontrib>Rosselet, Armel</creatorcontrib><creatorcontrib>Thieme-Marti, Stefan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pinheiro, Hector N. B</au><au>Ren, Tsang Ing</au><au>Scheib, Stefan</au><au>Rosselet, Armel</au><au>Thieme-Marti, Stefan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>2D/3D Megavoltage Image Registration Using Convolutional Neural Networks</atitle><date>2018-11-28</date><risdate>2018</risdate><abstract>We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltage images, the same does not occur for megavoltage images due to the lower image quality. Also, these methods most of the times do not present a good capture range. To deal with this problem, we propose the use of Convolutional Neural Network. The experiments were performed using a dataset of 50 brain images. The results showed to be promising compared to traditional image registration methods.</abstract><doi>10.48550/arxiv.1811.11816</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1811.11816
ispartof
issn
language eng
recordid cdi_arxiv_primary_1811_11816
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title 2D/3D Megavoltage Image Registration Using Convolutional Neural Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T08%3A06%3A00IST&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=2D/3D%20Megavoltage%20Image%20Registration%20Using%20Convolutional%20Neural%20Networks&rft.au=Pinheiro,%20Hector%20N.%20B&rft.date=2018-11-28&rft_id=info:doi/10.48550/arxiv.1811.11816&rft_dat=%3Carxiv_GOX%3E1811_11816%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