CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans
Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-decoder architecture and its variants suffer from diminutions of contextual information in pooling/ups...
Uloženo v:
| Vydáno v: | IEEE transactions on artificial intelligence Ročník 2; číslo 3; s. 283 - 297 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.06.2021
|
| Témata: | |
| ISSN: | 2691-4581, 2691-4581 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-decoder architecture and its variants suffer from diminutions of contextual information in pooling/upsampling operations with increased semantic gaps among encoded and decoded feature maps as well as instigate vanishing gradient problems for its sequential gradient propagation that result in suboptimal performance. Moreover, operating with 3-D CT volume poses further limitations due to the exponential increase of computational complexity making the optimization difficult. In this article, an automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet, to overcome these limitations. Additionally, a two-phase training scheme is introduced where a deeper 2-D network is employed for generating region-of-interest (ROI)-enhanced CT volume followed by a shallower 3-D network for further enhancement with more contextual information without increasing computational burden. Along with the traditional vertical expansion of Unet, we have introduced horizontal expansion with multistage encoder-decoder modules for achieving optimum performance. Additionally, multiscale feature maps are integrated into the scale transition process to overcome the loss of contextual information. Moreover, a multiscale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches. The proposed scheme can be easily extended for achieving optimum segmentation performances in a wide variety of applications.
Impact Statement -With lower sensitivity (60-70%), elongated testing time, and a dire shortage of testing kits, traditional RTPCR based COVID-19 diagnostic scheme heavily relies on postCT based manual inspection for further investigation. Hence, automating the process of infected lesions extraction from chestCT volumes will be major progress for faster accurate diagnosis of COVID-19. However, in challenging conditions with diffused, blurred, and varying shaped edges of COVID-19 lesions, conventional approaches fail to provide precise segmentation of lesions that can be deleterious for false estimation and loss of information. The proposed scheme incorporating an efficient neural network architecture (CovSegNet) overcomes the limitations of traditional approaches that provide significant improvement of performance (8.4% in averaged dice measurement scale) over two datasets. Therefore, this scheme can be an effective, economical tool for the physicians for faster infection analysis to greatly reduce the spread and massive death toll of this deadly virus through mass-screening. |
|---|---|
| AbstractList | Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder–decoder architecture and its variants suffer from diminutions of contextual information in pooling/upsampling operations with increased semantic gaps among encoded and decoded feature maps as well as instigate vanishing gradient problems for its sequential gradient propagation that result in suboptimal performance. Moreover, operating with 3-D CT volume poses further limitations due to the exponential increase of computational complexity making the optimization difficult. In this article, an automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet, to overcome these limitations. Additionally, a two-phase training scheme is introduced where a deeper 2-D network is employed for generating region-of-interest (ROI)-enhanced CT volume followed by a shallower 3-D network for further enhancement with more contextual information without increasing computational burden. Along with the traditional vertical expansion of Unet, we have introduced horizontal expansion with multistage encoder–decoder modules for achieving optimum performance. Additionally, multiscale feature maps are integrated into the scale transition process to overcome the loss of contextual information. Moreover, a multiscale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches. The proposed scheme can be easily extended for achieving optimum segmentation performances in a wide variety of applications. Impact Statement—With lower sensitivity (60–70%), elongated testing time, and a dire shortage of testing kits, traditional RTPCR based COVID-19 diagnostic scheme heavily relies on postCT based manual inspection for further investigation. Hence, automating the process of infected lesions extraction from chestCT volumes will be major progress for faster accurate diagnosis of COVID-19. However, in challenging conditions with diffused, blurred, and varying shaped edges of COVID-19 lesions, conventional approaches fail to provide precise segmentation of lesions that can be deleterious for false estimation and loss of information. The proposed scheme incorporating an efficient neural network architecture (CovSegNet) overcomes the limitations of traditional approaches that provide significant improvement of performance (8.4% in averaged dice measurement scale) over two datasets. Therefore, this scheme can be an effective, economical tool for the physicians for faster infection analysis to greatly reduce the spread and massive death toll of this deadly virus through mass-screening. Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-decoder architecture and its variants suffer from diminutions of contextual information in pooling/upsampling operations with increased semantic gaps among encoded and decoded feature maps as well as instigate vanishing gradient problems for its sequential gradient propagation that result in suboptimal performance. Moreover, operating with 3-D CT volume poses further limitations due to the exponential increase of computational complexity making the optimization difficult. In this article, an automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet, to overcome these limitations. Additionally, a two-phase training scheme is introduced where a deeper 2-D network is employed for generating region-of-interest (ROI)-enhanced CT volume followed by a shallower 3-D network for further enhancement with more contextual information without increasing computational burden. Along with the traditional vertical expansion of Unet, we have introduced horizontal expansion with multistage encoder-decoder modules for achieving optimum performance. Additionally, multiscale feature maps are integrated into the scale transition process to overcome the loss of contextual information. Moreover, a multiscale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches. The proposed scheme can be easily extended for achieving optimum segmentation performances in a wide variety of applications. Impact Statement-With lower sensitivity (60-70%), elongated testing time, and a dire shortage of testing kits, traditional RTPCR based COVID-19 diagnostic scheme heavily relies on postCT based manual inspection for further investigation. Hence, automating the process of infected lesions extraction from chestCT volumes will be major progress for faster accurate diagnosis of COVID-19. However, in challenging conditions with diffused, blurred, and varying shaped edges of COVID-19 lesions, conventional approaches fail to provide precise segmentation of lesions that can be deleterious for false estimation and loss of information. The proposed scheme incorporating an efficient neural network architecture (CovSegNet) overcomes the limitations of traditional approaches that provide significant improvement of performance (8.4% in averaged dice measurement scale) over two datasets. Therefore, this scheme can be an effective, economical tool for the physicians for faster infection analysis to greatly reduce the spread and massive death toll of this deadly virus through mass-screening.Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-decoder architecture and its variants suffer from diminutions of contextual information in pooling/upsampling operations with increased semantic gaps among encoded and decoded feature maps as well as instigate vanishing gradient problems for its sequential gradient propagation that result in suboptimal performance. Moreover, operating with 3-D CT volume poses further limitations due to the exponential increase of computational complexity making the optimization difficult. In this article, an automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet, to overcome these limitations. Additionally, a two-phase training scheme is introduced where a deeper 2-D network is employed for generating region-of-interest (ROI)-enhanced CT volume followed by a shallower 3-D network for further enhancement with more contextual information without increasing computational burden. Along with the traditional vertical expansion of Unet, we have introduced horizontal expansion with multistage encoder-decoder modules for achieving optimum performance. Additionally, multiscale feature maps are integrated into the scale transition process to overcome the loss of contextual information. Moreover, a multiscale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches. The proposed scheme can be easily extended for achieving optimum segmentation performances in a wide variety of applications. Impact Statement-With lower sensitivity (60-70%), elongated testing time, and a dire shortage of testing kits, traditional RTPCR based COVID-19 diagnostic scheme heavily relies on postCT based manual inspection for further investigation. Hence, automating the process of infected lesions extraction from chestCT volumes will be major progress for faster accurate diagnosis of COVID-19. However, in challenging conditions with diffused, blurred, and varying shaped edges of COVID-19 lesions, conventional approaches fail to provide precise segmentation of lesions that can be deleterious for false estimation and loss of information. The proposed scheme incorporating an efficient neural network architecture (CovSegNet) overcomes the limitations of traditional approaches that provide significant improvement of performance (8.4% in averaged dice measurement scale) over two datasets. Therefore, this scheme can be an effective, economical tool for the physicians for faster infection analysis to greatly reduce the spread and massive death toll of this deadly virus through mass-screening. Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-decoder architecture and its variants suffer from diminutions of contextual information in pooling/upsampling operations with increased semantic gaps among encoded and decoded feature maps as well as instigate vanishing gradient problems for its sequential gradient propagation that result in suboptimal performance. Moreover, operating with 3-D CT volume poses further limitations due to the exponential increase of computational complexity making the optimization difficult. In this article, an automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet, to overcome these limitations. Additionally, a two-phase training scheme is introduced where a deeper 2-D network is employed for generating region-of-interest (ROI)-enhanced CT volume followed by a shallower 3-D network for further enhancement with more contextual information without increasing computational burden. Along with the traditional vertical expansion of Unet, we have introduced horizontal expansion with multistage encoder-decoder modules for achieving optimum performance. Additionally, multiscale feature maps are integrated into the scale transition process to overcome the loss of contextual information. Moreover, a multiscale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches. The proposed scheme can be easily extended for achieving optimum segmentation performances in a wide variety of applications. Impact Statement -With lower sensitivity (60-70%), elongated testing time, and a dire shortage of testing kits, traditional RTPCR based COVID-19 diagnostic scheme heavily relies on postCT based manual inspection for further investigation. Hence, automating the process of infected lesions extraction from chestCT volumes will be major progress for faster accurate diagnosis of COVID-19. However, in challenging conditions with diffused, blurred, and varying shaped edges of COVID-19 lesions, conventional approaches fail to provide precise segmentation of lesions that can be deleterious for false estimation and loss of information. The proposed scheme incorporating an efficient neural network architecture (CovSegNet) overcomes the limitations of traditional approaches that provide significant improvement of performance (8.4% in averaged dice measurement scale) over two datasets. Therefore, this scheme can be an effective, economical tool for the physicians for faster infection analysis to greatly reduce the spread and massive death toll of this deadly virus through mass-screening. |
| Author | Rahman, Md Awsafur Fattah, Shaikh Anowarul Mahmud, Tanvir Kung, Sun-Yuan |
| AuthorAffiliation | Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology 61750 Dhaka 1000 Bangladesh Department of Electrical Engineering Princeton University 6740 Princeton NJ 08544 USA |
| AuthorAffiliation_xml | – name: Department of Electrical Engineering Princeton University 6740 Princeton NJ 08544 USA – name: Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology 61750 Dhaka 1000 Bangladesh |
| Author_xml | – sequence: 1 givenname: Tanvir orcidid: 0000-0003-0529-2826 surname: Mahmud fullname: Mahmud, Tanvir email: tanvirmahmud@eee.buet.ac.bd organization: Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh – sequence: 2 givenname: Md Awsafur orcidid: 0000-0003-0966-8835 surname: Rahman fullname: Rahman, Md Awsafur email: mdawsafurrahman@ug.eee.buet.ac.bd organization: Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh – sequence: 3 givenname: Shaikh Anowarul orcidid: 0000-0001-8090-2327 surname: Fattah fullname: Fattah, Shaikh Anowarul email: fattah@eee.buet.ac.bd organization: Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh – sequence: 4 givenname: Sun-Yuan orcidid: 0000-0002-7314-0720 surname: Kung fullname: Kung, Sun-Yuan email: kung@princeton.edu organization: Department of Electrical Engineering, Princeton University, Princeton, NJ, USA |
| BookMark | eNp9kctvEzEQxi3Uqu87EhcfuWzqxz5sDkjRtrSRAj007dXy2uPGsLsO9m4k_ns2JKDCgdPYmu_7aWa-c3TUhx4QekvJjFIir1fzxYwRRmeclLmk_A06Y6WkWV4IevTqfYquUvpKCGEFZYxVJ-iUV1JQScUZ-laH7SO8fIHhA57jz2M7eHzbm2AhZjfwq-J5NGs_gBnGCNiFiBfdJoYtWLyE5EOPJ0AH_aCH3Sc4XD88L24yKnG9hjTgeoUfje7TJTp2uk1wdagX6OnT7aq-z5YPd4t6vswMJ4JnzuZCAwfgVtrKSFYaZzRtBFjtdEEds0bwkhUgmrypGpNbZx2vjBaO8yLnF-jjnrsZmw6smUaLulWb6Dsdf6igvfq70_u1eglbJYq8ILycAO8PgBi-j9MKqvPJQNvqHsKYFBOSEUpZXkzSci81MaQUwSnj94eYyL5VlKhdWGoKS-3CUoewJiP5x_h7vv9Y3u0tHgD-yCWvRCUk_wkrMqDf |
| CODEN | ITAICB |
| CitedBy_id | crossref_primary_10_1007_s11277_024_11624_z crossref_primary_10_1016_j_bspc_2024_106132 crossref_primary_10_1109_TAI_2023_3346833 crossref_primary_10_1007_s00521_024_10351_7 crossref_primary_10_1007_s42486_025_00203_1 crossref_primary_10_1080_21681163_2023_2219750 crossref_primary_10_1016_j_dsp_2025_105319 crossref_primary_10_1109_LSP_2025_3526745 crossref_primary_10_1109_TAI_2022_3225372 crossref_primary_10_3389_fphys_2023_1296185 crossref_primary_10_1016_j_jrras_2025_101650 crossref_primary_10_1007_s12559_023_10180_1 crossref_primary_10_1109_TAI_2021_3139058 crossref_primary_10_1109_TAI_2024_3452052 crossref_primary_10_1117_1_JEI_34_3_033009 crossref_primary_10_32604_cmc_2023_038059 crossref_primary_10_1109_TAI_2024_3355354 crossref_primary_10_1109_TCSII_2023_3291168 crossref_primary_10_1007_s00432_025_06256_0 crossref_primary_10_1109_TAI_2023_3266742 crossref_primary_10_1007_s11042_024_18131_0 crossref_primary_10_1109_TGRS_2025_3546160 |
| Cites_doi | 10.1109/TMI.2020.2992546 10.1016/S0140-6736(20)30185-9 10.1148/radiol.2020200642 10.1016/j.isprsjprs.2020.01.013 10.1016/j.compbiomed.2020.103869 10.46234/ccdcw2020.032 10.1109/TMI.2020.2989737 10.1148/radiol.2020201343 10.1109/TMI.2020.2996645 10.1109/TMI.2019.2950051 10.1109/ISBI.2019.8759329 10.1016/j.neunet.2019.08.025 10.1109/TMI.2020.2975347 10.1109/ACCESS.2019.2896920 10.1007/978-3-319-67389-9_44 10.1109/3DV.2016.79 10.1109/TMI.2019.2959609 10.1148/radiol.2020200330 10.1056/NEJMoa2002032 10.1016/j.dsx.2020.04.012 10.1148/radiol.2020200905 10.1109/TMI.2020.2983721 10.1109/CVPR.2015.7298965 10.1109/TMI.2020.2993291 |
| ContentType | Journal Article |
| Copyright | 2021 IEEE |
| Copyright_xml | – notice: 2021 IEEE |
| DBID | 97E RIA RIE AAYXX CITATION 7X8 5PM |
| DOI | 10.1109/TAI.2021.3064913 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2691-4581 |
| EndPage | 297 |
| ExternalDocumentID | PMC8545036 10_1109_TAI_2021_3064913 9378789 |
| Genre | orig-research |
| GroupedDBID | 0R~ 97E AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IEDLZ IFIPE JAVBF M~E OCL RIA RIE AAYXX CITATION 7X8 5PM |
| ID | FETCH-LOGICAL-c3083-fd48ae3ee3d9d7c926cfca1b8edafa51f2dc83625e8b4b7bc4dfdf37ca8f33543 |
| IEDL.DBID | RIE |
| ISSN | 2691-4581 |
| IngestDate | Tue Sep 30 17:11:14 EDT 2025 Thu Jul 10 22:55:23 EDT 2025 Sat Nov 29 07:39:14 EST 2025 Tue Nov 18 21:53:43 EST 2025 Wed Aug 27 07:40:20 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-009 https://doi.org/10.15223/policy-001 This article is free to access and download, along with rights for full text and data mining, re-use and analysis. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3083-fd48ae3ee3d9d7c926cfca1b8edafa51f2dc83625e8b4b7bc4dfdf37ca8f33543 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-0529-2826 0000-0003-0966-8835 0000-0002-7314-0720 0000-0001-8090-2327 |
| OpenAccessLink | https://escholarship.org/uc/item/51g6b93g |
| PMID | 37981918 |
| PQID | 2892011245 |
| PQPubID | 23479 |
| PageCount | 15 |
| ParticipantIDs | crossref_citationtrail_10_1109_TAI_2021_3064913 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8545036 ieee_primary_9378789 proquest_miscellaneous_2892011245 crossref_primary_10_1109_TAI_2021_3064913 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-06-01 |
| PublicationDateYYYYMMDD | 2021-06-01 |
| PublicationDate_xml | – month: 06 year: 2021 text: 2021-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | IEEE transactions on artificial intelligence |
| PublicationTitleAbbrev | TAI |
| PublicationYear | 2021 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref12 ref31 müller (ref18) 2020 ref30 ref11 ref32 ref10 ref2 ref19 saeedizadeh (ref13) 2020 ghamdi (ref24) 2020; 39 (ref34) 2020 ai (ref4) 2020; 296 ronneberger (ref22) 2015 mahmud (ref9) 2020; 122 ref23 ref26 ref25 (ref35) 2019 ref20 oktay (ref29) 2018 ref21 ref28 ref27 ref8 zhou (ref14) 2020 ref7 yan (ref15) 2020 ref3 ref6 qiu (ref16) 2020 ref5 (ref33) 2020 surveillances (ref1) 2020; 2 ma (ref17) 2020 |
| References_xml | – ident: ref11 doi: 10.1109/TMI.2020.2992546 – ident: ref2 doi: 10.1016/S0140-6736(20)30185-9 – volume: 296 start-page: 32e year: 2020 ident: ref4 article-title: Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases publication-title: Radiology doi: 10.1148/radiol.2020200642 – ident: ref23 doi: 10.1016/j.isprsjprs.2020.01.013 – volume: 122 year: 2020 ident: ref9 article-title: CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2020.103869 – volume: 2 start-page: 113 year: 2020 ident: ref1 article-title: The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19)-China, 2020 publication-title: China CDC Weekly doi: 10.46234/ccdcw2020.032 – volume: 39 start-page: 3240 year: 2020 ident: ref24 article-title: DU-Net: Convolutional network for the detection of arterial calcifications in mammograms publication-title: IEEE Trans Med Imag doi: 10.1109/TMI.2020.2989737 – start-page: 234 year: 2015 ident: ref22 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput Comput -Assisted Intervention – year: 2020 ident: ref13 article-title: Segmenting COVID-19 chest CT images using connectivity imposed U-net – year: 2020 ident: ref34 publication-title: COVID-19 CT Segmentation Dataset – year: 2019 ident: ref35 publication-title: Semantic drone dataset – year: 2020 ident: ref33 publication-title: COVID-19 CT Lung and Infection Segmentation Dataset – year: 2018 ident: ref29 article-title: Attention U-Net: Learning where to look for the pancreas – ident: ref5 doi: 10.1148/radiol.2020201343 – ident: ref12 doi: 10.1109/TMI.2020.2996645 – year: 2020 ident: ref17 article-title: Towards efficient COVID-19 CT annotation: A benchmark for lung and infection segmentation – ident: ref26 doi: 10.1109/TMI.2019.2950051 – year: 2020 ident: ref14 article-title: An automatic COVID-19 CT segmentation network using spatial and channel attention mechanism – ident: ref32 doi: 10.1109/ISBI.2019.8759329 – ident: ref27 doi: 10.1016/j.neunet.2019.08.025 – year: 2020 ident: ref15 article-title: COVID-19 chest CT image segmentation-A deep convolutional neural network solution – ident: ref20 doi: 10.1109/TMI.2020.2975347 – year: 2020 ident: ref16 article-title: MiniSeg: An extremely minimum network for efficient COVID-19 segmentation – ident: ref25 doi: 10.1109/ACCESS.2019.2896920 – ident: ref31 doi: 10.1007/978-3-319-67389-9_44 – ident: ref19 doi: 10.1109/3DV.2016.79 – ident: ref28 doi: 10.1109/TMI.2019.2959609 – ident: ref8 doi: 10.1148/radiol.2020200330 – ident: ref3 doi: 10.1056/NEJMoa2002032 – year: 2020 ident: ref18 article-title: Automated chest CT image segmentation of COVID-19 lung infection based on 3D U-net – ident: ref7 doi: 10.1016/j.dsx.2020.04.012 – ident: ref6 doi: 10.1148/radiol.2020200905 – ident: ref30 doi: 10.1109/TMI.2020.2983721 – ident: ref21 doi: 10.1109/CVPR.2015.7298965 – ident: ref10 doi: 10.1109/TMI.2020.2993291 |
| SSID | ssj0002512227 |
| Score | 2.3061128 |
| Snippet | Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of... |
| SourceID | pubmedcentral proquest crossref ieee |
| SourceType | Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 283 |
| SubjectTerms | Artificial intelligence (AI) biomedical imaging Computed tomography computer aided analysis Computer architecture COVID-19 image segmentation Lesions neural networks Optimization Semantics Three-dimensional displays |
| Title | CovSegNet: A Multi Encoder-Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans |
| URI | https://ieeexplore.ieee.org/document/9378789 https://www.proquest.com/docview/2892011245 https://pubmed.ncbi.nlm.nih.gov/PMC8545036 |
| Volume | 2 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2691-4581 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002512227 issn: 2691-4581 databaseCode: RIE dateStart: 20200101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2691-4581 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002512227 issn: 2691-4581 databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9QwHA_b8MEXN53i6RwRfBHs7pq0TeLb0d3YYJ6C57i3kh_fzKG2crvbo3-736S9soIIg9IW2iaBT9Lvr3y_H0LeAXOGT2SGCylQmOXcJNpYk1ju8V_IUMJFHrKrSzGfy-VSfdkhH_pcGACIm8_gJNzGWL5r7Ca4ysYoSqWQapfsClG0uVq9PyXIacbENhI5UePF9ALtP5aeBCVbpYExhwsVDBQ5EEKRVWWgYA63R96TN2f7DxvpAXnS6ZV02k6Ep2QH6mdkf8vZQLslfEh-lM3dV7iew_ojndKYfktndUhsXyWnEK90ei-4QFGppa3nARy9hOBco9jAry5nqaaNp-Xnq4vTJFW0DOxbtFxgfygCn5NvZ7NFeZ50hAsIDapiiXeZ1MABuFNOWMUK661OjQSnvc5Tz5yVKPFykCYzwtjMeee5sFp6zvOMvyB7dVPDS0Id-JxDwcC7IrM-N4ViTjuFR6ZNoUdkvEWgsl018kCK8bOKVslEVQhfFeCrOvhG5H3_xe-2Esd_3j0MmPTvdXCMyNstyBWuohAa0TU0m9sKzc6gCbEsHxExQL9vI9ThHj6pb77HetwStVBUBF79u9PX5HEYWru97IjsrVcbeEMe2bv1ze3qGKfyUuL505_ZcZzQfwFUJ_Rl |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3ta9QwGH-YU9AvTp3D8zWCXwS7uyZpm_jt6DZ2eJ6C59i3kpcnOjZbud3t7zdJe2UFEYRCC02TwC_p85bn-QG8Q2o1mwjuN1KgMMuYTpQ2OjHM-X8h9RIu8pCdzYvFQpyfy6878KHPhUHEePgMD8NjjOXbxmyCq2zsRakohLwDdzPO6aTN1uo9KkFSU1psY5ETOV5OZ94CpOlhULNlGjhzWCGDiSIGYijyqgxUzOEByVsS52Tv_-b6CB52miWZtkvhMexg_QT2tqwNpNvE-3BZNjff8McC1x_JlMQEXHJch9T2VXKE8U6mt8ILxKu1pPU9oCVzDO414jv41WUt1aRxpPxyNjtKUknKwL9FyqUfzwvBp_D95HhZniYd5YIHxytjibNcKGSIzEpbGElz44xKtUCrnMpSR60RXuZlKDTXhTbcOutYYZRwjGWcHcBu3dT4DIhFlzHMKTqbc-MynUtqlZX-4krnagTjLQKV6eqRB1qMqyraJRNZefiqAF_VwTeC9_0Xv9taHP9oux8w6dt1cIzg7Rbkyu-jEBxRNTab68obnkEXojwbQTFAv-8jVOIevqkvfsaK3MLroV4VeP73Qd_A_dPl53k1ny0-vYAHYZrtYbOXsLtebfAV3DM364vr1eu4oP8ApEL1kw |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=CovSegNet%3A+A+Multi+Encoder%E2%80%93Decoder+Architecture+for+Improved+Lesion+Segmentation+of+COVID-19+Chest+CT+Scans&rft.jtitle=IEEE+transactions+on+artificial+intelligence&rft.date=2021-06-01&rft.pub=IEEE&rft.eissn=2691-4581&rft.volume=2&rft.issue=3&rft.spage=283&rft.epage=297&rft_id=info:doi/10.1109%2FTAI.2021.3064913&rft.externalDocID=PMC8545036 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2691-4581&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2691-4581&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2691-4581&client=summon |