OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN

Ultrasound imaging (US) often suffers from distinct image artifacts from various sources. Classic approaches for solving these problems are usually model-based iterative approaches that have been developed specifically for each type of artifact, which are often computationally intensive. Recently, d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huh, Jaeyoung, Khan, Shujaat, Ye, Jong Chul
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 Huh, Jaeyoung
Khan, Shujaat
Ye, Jong Chul
description Ultrasound imaging (US) often suffers from distinct image artifacts from various sources. Classic approaches for solving these problems are usually model-based iterative approaches that have been developed specifically for each type of artifact, which are often computationally intensive. Recently, deep learning approaches have been proposed as computationally efficient and high performance alternatives. Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type. This poses a fundamental limitation in the practical use of deep learning for US, since large number of models should be stored to deal with various US image artifacts. Inspired by the recent success of multi-domain image transfer, here we propose a novel, unsupervised, deep learning approach in which a single neural network can be used to deal with different types of US artifacts simply by changing a mask vector that switches between different target domains. Our algorithm is rigorously derived using an optimal transport (OT) theory for cascaded probability measures. Experimental results using phantom and in vivo data demonstrate that the proposed method can generate high quality image by removing distinct artifacts, which are comparable to those obtained by separately trained multiple neural networks.
doi_str_mv 10.48550/arxiv.2007.05205
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2007_05205</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2007_05205</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-b0961f9aa0b8904fda952b58fc5a5f7fb9f2d57b24f06e0db6003be95a5844933</originalsourceid><addsrcrecordid>eNotz09LwzAcxvFcPMj0BXgybyD1tzZpm-Oo_wZzA-3AW_llSUYgTUfSFn33zunpe3jggQ8hd0vIeC0EPGD8cnOWA1QZiBzENfnctUxHN5tA3yY_OvY49OgC3Yc0nUycXTKa7v0YMQ1T0HTd49HQVRydxcNI300_zOjplFw4UqQf53hDm-32hlxZ9Mnc_ndB2uentnllm93LulltGJaVYApkubQSEVQtgVuNUuRK1PYgUNjKKmlzLSqVcwulAa1KgEIZeV5rzmVRLMj93-2F1p2i6zF-d7_E7kIsfgDP0kwa</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN</title><source>arXiv.org</source><creator>Huh, Jaeyoung ; Khan, Shujaat ; Ye, Jong Chul</creator><creatorcontrib>Huh, Jaeyoung ; Khan, Shujaat ; Ye, Jong Chul</creatorcontrib><description>Ultrasound imaging (US) often suffers from distinct image artifacts from various sources. Classic approaches for solving these problems are usually model-based iterative approaches that have been developed specifically for each type of artifact, which are often computationally intensive. Recently, deep learning approaches have been proposed as computationally efficient and high performance alternatives. Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type. This poses a fundamental limitation in the practical use of deep learning for US, since large number of models should be stored to deal with various US image artifacts. Inspired by the recent success of multi-domain image transfer, here we propose a novel, unsupervised, deep learning approach in which a single neural network can be used to deal with different types of US artifacts simply by changing a mask vector that switches between different target domains. Our algorithm is rigorously derived using an optimal transport (OT) theory for cascaded probability measures. Experimental results using phantom and in vivo data demonstrate that the proposed method can generate high quality image by removing distinct artifacts, which are comparable to those obtained by separately trained multiple neural networks.</description><identifier>DOI: 10.48550/arxiv.2007.05205</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2020-07</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2007.05205$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2007.05205$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Huh, Jaeyoung</creatorcontrib><creatorcontrib>Khan, Shujaat</creatorcontrib><creatorcontrib>Ye, Jong Chul</creatorcontrib><title>OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN</title><description>Ultrasound imaging (US) often suffers from distinct image artifacts from various sources. Classic approaches for solving these problems are usually model-based iterative approaches that have been developed specifically for each type of artifact, which are often computationally intensive. Recently, deep learning approaches have been proposed as computationally efficient and high performance alternatives. Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type. This poses a fundamental limitation in the practical use of deep learning for US, since large number of models should be stored to deal with various US image artifacts. Inspired by the recent success of multi-domain image transfer, here we propose a novel, unsupervised, deep learning approach in which a single neural network can be used to deal with different types of US artifacts simply by changing a mask vector that switches between different target domains. Our algorithm is rigorously derived using an optimal transport (OT) theory for cascaded probability measures. Experimental results using phantom and in vivo data demonstrate that the proposed method can generate high quality image by removing distinct artifacts, which are comparable to those obtained by separately trained multiple neural networks.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz09LwzAcxvFcPMj0BXgybyD1tzZpm-Oo_wZzA-3AW_llSUYgTUfSFn33zunpe3jggQ8hd0vIeC0EPGD8cnOWA1QZiBzENfnctUxHN5tA3yY_OvY49OgC3Yc0nUycXTKa7v0YMQ1T0HTd49HQVRydxcNI300_zOjplFw4UqQf53hDm-32hlxZ9Mnc_ndB2uentnllm93LulltGJaVYApkubQSEVQtgVuNUuRK1PYgUNjKKmlzLSqVcwulAa1KgEIZeV5rzmVRLMj93-2F1p2i6zF-d7_E7kIsfgDP0kwa</recordid><startdate>20200710</startdate><enddate>20200710</enddate><creator>Huh, Jaeyoung</creator><creator>Khan, Shujaat</creator><creator>Ye, Jong Chul</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20200710</creationdate><title>OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN</title><author>Huh, Jaeyoung ; Khan, Shujaat ; Ye, Jong Chul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-b0961f9aa0b8904fda952b58fc5a5f7fb9f2d57b24f06e0db6003be95a5844933</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Huh, Jaeyoung</creatorcontrib><creatorcontrib>Khan, Shujaat</creatorcontrib><creatorcontrib>Ye, Jong Chul</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Huh, Jaeyoung</au><au>Khan, Shujaat</au><au>Ye, Jong Chul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN</atitle><date>2020-07-10</date><risdate>2020</risdate><abstract>Ultrasound imaging (US) often suffers from distinct image artifacts from various sources. Classic approaches for solving these problems are usually model-based iterative approaches that have been developed specifically for each type of artifact, which are often computationally intensive. Recently, deep learning approaches have been proposed as computationally efficient and high performance alternatives. Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type. This poses a fundamental limitation in the practical use of deep learning for US, since large number of models should be stored to deal with various US image artifacts. Inspired by the recent success of multi-domain image transfer, here we propose a novel, unsupervised, deep learning approach in which a single neural network can be used to deal with different types of US artifacts simply by changing a mask vector that switches between different target domains. Our algorithm is rigorously derived using an optimal transport (OT) theory for cascaded probability measures. Experimental results using phantom and in vivo data demonstrate that the proposed method can generate high quality image by removing distinct artifacts, which are comparable to those obtained by separately trained multiple neural networks.</abstract><doi>10.48550/arxiv.2007.05205</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2007.05205
ispartof
issn
language eng
recordid cdi_arxiv_primary_2007_05205
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Statistics - Machine Learning
title OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A40%3A34IST&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=OT-driven%20Multi-Domain%20Unsupervised%20Ultrasound%20Image%20Artifact%20Removal%20using%20a%20Single%20CNN&rft.au=Huh,%20Jaeyoung&rft.date=2020-07-10&rft_id=info:doi/10.48550/arxiv.2007.05205&rft_dat=%3Carxiv_GOX%3E2007_05205%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