Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising

This work highlights the significance of equivariant networks as efficient and high-performance approaches for tomography applications. Our study builds upon the limitations of conventional Convolutional Neural Networks (CNNs), which have shown promise in post-processing various medical imaging syst...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hashemi, Amirreza, Feng, Yuemeng, Sabet, Hamid
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 Hashemi, Amirreza
Feng, Yuemeng
Sabet, Hamid
description This work highlights the significance of equivariant networks as efficient and high-performance approaches for tomography applications. Our study builds upon the limitations of conventional Convolutional Neural Networks (CNNs), which have shown promise in post-processing various medical imaging systems. However, the efficiency of conventional CNNs heavily relies on an undiminished and proper training set. To tackle this issue, in this study, we introduce an equivariant network, aiming to reduce CNN's dependency on specific training sets. We evaluate the efficacy of equivariant spherical CNNs (SCNNs) for 2- and 3- dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in denoising and reconstructing benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observe a significant decrease in computational costs while maintaining the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of this network for broader tomography applications, particularly those requiring omnidirectional representation.
doi_str_mv 10.48550/arxiv.2307.03298
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2307_03298</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307_03298</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-60cab24aac28ffbd3d10a4ef286a30dae16d7979defc2a83515645412ca4e9d33</originalsourceid><addsrcrecordid>eNotj8tOwzAURL1hgQofwAr_QIIfseOwq6IClUpZ0H1060exFBzjpBX8fd2U1dWMZkb3IPRASVkpIcgTpF9_KhkndUk4a9Qtip_xyyavocftdovdkPC7NbNef8PBhwNexthnY_JDGJ-zG4c0QdAWDw6vfo7-BMnP2gfsc8fiZHXOTumoLyUMwWBjw-DHPHeHbhz0o73_vwu0e1nt2rdi8_G6bpebAmStCkk07FkFoJlybm-4oQQq65iSwIkBS6Wpm7ox1mkGigsqZCUqynRONYbzBXq8zs7IXUz5s_TXXdC7GZ2fAQ-5Vi8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising</title><source>arXiv.org</source><creator>Hashemi, Amirreza ; Feng, Yuemeng ; Sabet, Hamid</creator><creatorcontrib>Hashemi, Amirreza ; Feng, Yuemeng ; Sabet, Hamid</creatorcontrib><description>This work highlights the significance of equivariant networks as efficient and high-performance approaches for tomography applications. Our study builds upon the limitations of conventional Convolutional Neural Networks (CNNs), which have shown promise in post-processing various medical imaging systems. However, the efficiency of conventional CNNs heavily relies on an undiminished and proper training set. To tackle this issue, in this study, we introduce an equivariant network, aiming to reduce CNN's dependency on specific training sets. We evaluate the efficacy of equivariant spherical CNNs (SCNNs) for 2- and 3- dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in denoising and reconstructing benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observe a significant decrease in computational costs while maintaining the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of this network for broader tomography applications, particularly those requiring omnidirectional representation.</description><identifier>DOI: 10.48550/arxiv.2307.03298</identifier><language>eng</language><subject>Computer Science - Learning ; Physics - Medical Physics</subject><creationdate>2023-07</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2307.03298$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2307.03298$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hashemi, Amirreza</creatorcontrib><creatorcontrib>Feng, Yuemeng</creatorcontrib><creatorcontrib>Sabet, Hamid</creatorcontrib><title>Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising</title><description>This work highlights the significance of equivariant networks as efficient and high-performance approaches for tomography applications. Our study builds upon the limitations of conventional Convolutional Neural Networks (CNNs), which have shown promise in post-processing various medical imaging systems. However, the efficiency of conventional CNNs heavily relies on an undiminished and proper training set. To tackle this issue, in this study, we introduce an equivariant network, aiming to reduce CNN's dependency on specific training sets. We evaluate the efficacy of equivariant spherical CNNs (SCNNs) for 2- and 3- dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in denoising and reconstructing benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observe a significant decrease in computational costs while maintaining the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of this network for broader tomography applications, particularly those requiring omnidirectional representation.</description><subject>Computer Science - Learning</subject><subject>Physics - Medical Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURL1hgQofwAr_QIIfseOwq6IClUpZ0H1060exFBzjpBX8fd2U1dWMZkb3IPRASVkpIcgTpF9_KhkndUk4a9Qtip_xyyavocftdovdkPC7NbNef8PBhwNexthnY_JDGJ-zG4c0QdAWDw6vfo7-BMnP2gfsc8fiZHXOTumoLyUMwWBjw-DHPHeHbhz0o73_vwu0e1nt2rdi8_G6bpebAmStCkk07FkFoJlybm-4oQQq65iSwIkBS6Wpm7ox1mkGigsqZCUqynRONYbzBXq8zs7IXUz5s_TXXdC7GZ2fAQ-5Vi8</recordid><startdate>20230706</startdate><enddate>20230706</enddate><creator>Hashemi, Amirreza</creator><creator>Feng, Yuemeng</creator><creator>Sabet, Hamid</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230706</creationdate><title>Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising</title><author>Hashemi, Amirreza ; Feng, Yuemeng ; Sabet, Hamid</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-60cab24aac28ffbd3d10a4ef286a30dae16d7979defc2a83515645412ca4e9d33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Physics - Medical Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Hashemi, Amirreza</creatorcontrib><creatorcontrib>Feng, Yuemeng</creatorcontrib><creatorcontrib>Sabet, Hamid</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hashemi, Amirreza</au><au>Feng, Yuemeng</au><au>Sabet, Hamid</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising</atitle><date>2023-07-06</date><risdate>2023</risdate><abstract>This work highlights the significance of equivariant networks as efficient and high-performance approaches for tomography applications. Our study builds upon the limitations of conventional Convolutional Neural Networks (CNNs), which have shown promise in post-processing various medical imaging systems. However, the efficiency of conventional CNNs heavily relies on an undiminished and proper training set. To tackle this issue, in this study, we introduce an equivariant network, aiming to reduce CNN's dependency on specific training sets. We evaluate the efficacy of equivariant spherical CNNs (SCNNs) for 2- and 3- dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in denoising and reconstructing benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observe a significant decrease in computational costs while maintaining the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of this network for broader tomography applications, particularly those requiring omnidirectional representation.</abstract><doi>10.48550/arxiv.2307.03298</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2307.03298
ispartof
issn
language eng
recordid cdi_arxiv_primary_2307_03298
source arXiv.org
subjects Computer Science - Learning
Physics - Medical Physics
title Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T13%3A55%3A12IST&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=Spherical%20CNN%20for%20Medical%20Imaging%20Applications:%20Importance%20of%20Equivariance%20in%20image%20reconstruction%20and%20denoising&rft.au=Hashemi,%20Amirreza&rft.date=2023-07-06&rft_id=info:doi/10.48550/arxiv.2307.03298&rft_dat=%3Carxiv_GOX%3E2307_03298%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