Multi-task semantic segmentation of CT images for COVID-19 infections using DeepLabV3+ based on dilated residual network

COVID-19 is a deadly outbreak that has been declared a public health emergency of international concern. The massive damage of the disease to public health, social life, and the global economy increases the importance of alternative rapid diagnosis and follow-up methods. RT-PCR assay, which is consi...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Australasian physical & engineering sciences in medicine Ročník 45; číslo 2; s. 443 - 455
Hlavný autor:	Polat, Hasan
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Cham Springer International Publishing 01.06.2022 Springer Nature B.V
Predmet:	Artificial neural networks Biological and Medical Physics Biomedical and Life Sciences Biomedical Engineering and Bioengineering Biomedicine Biophysics Computed tomography Consolidation Coronaviruses COVID-19 COVID-19 - diagnostic imaging Global economy Humans Image Processing, Computer-Assisted - methods Image segmentation Imaging techniques Lungs Medical and Radiation Physics Medical imaging Neural Networks, Computer Public health Scientific Paper Semantic segmentation Semantics Tomography, X-Ray Computed - methods Viral diseases Deep learning Image segmentation Coronavirus (COVID-19) Computed tomography images Image classification
ISSN:	2662-4729, 0158-9938, 2662-4737, 2662-4737, 1879-5447
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	COVID-19 is a deadly outbreak that has been declared a public health emergency of international concern. The massive damage of the disease to public health, social life, and the global economy increases the importance of alternative rapid diagnosis and follow-up methods. RT-PCR assay, which is considered the gold standard in diagnosing the disease, is complicated, expensive, time-consuming, prone to contamination, and may give false-negative results. These drawbacks reinforce the trend toward medical imaging techniques such as computed tomography (CT). Typical visual signs such as ground-glass opacity (GGO) and consolidation of CT images allow for quantitative assessment of the disease. In this context, it is aimed at the segmentation of the infected lung CT images with the residual network-based DeepLabV3+, which is a redesigned convolutional neural network (CNN) model. In order to evaluate the robustness of the proposed model, three different segmentation tasks as Task-1, Task-2, and Task-3 were applied. Task-1 represents binary segmentation as lung (infected and non-infected tissues) and background. Task-2 represents multi-class segmentation as lung (non-infected tissue), COVID (GGO, consolidation, and pleural effusion irregularities are gathered under a single roof), and background. Finally, the segmentation in which each lesion type is considered as a separate class is defined as Task-3. COVID-19 imaging data for each segmentation task consists of 100 CT single-slice scans from over 40 diagnosed patients. The performance of the model was evaluated using Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy by performing five-fold cross-validation. The average DSC performance for three different segmentation tasks was obtained as 0.98, 0.858, and 0.616, respectively. The experimental results demonstrate that the proposed method has robust performance and great potential in evaluating COVID-19 infection.
AbstractList	COVID-19 is a deadly outbreak that has been declared a public health emergency of international concern. The massive damage of the disease to public health, social life, and the global economy increases the importance of alternative rapid diagnosis and follow-up methods. RT-PCR assay, which is considered the gold standard in diagnosing the disease, is complicated, expensive, time-consuming, prone to contamination, and may give false-negative results. These drawbacks reinforce the trend toward medical imaging techniques such as computed tomography (CT). Typical visual signs such as ground-glass opacity (GGO) and consolidation of CT images allow for quantitative assessment of the disease. In this context, it is aimed at the segmentation of the infected lung CT images with the residual network-based DeepLabV3+, which is a redesigned convolutional neural network (CNN) model. In order to evaluate the robustness of the proposed model, three different segmentation tasks as Task-1, Task-2, and Task-3 were applied. Task-1 represents binary segmentation as lung (infected and non-infected tissues) and background. Task-2 represents multi-class segmentation as lung (non-infected tissue), COVID (GGO, consolidation, and pleural effusion irregularities are gathered under a single roof), and background. Finally, the segmentation in which each lesion type is considered as a separate class is defined as Task-3. COVID-19 imaging data for each segmentation task consists of 100 CT single-slice scans from over 40 diagnosed patients. The performance of the model was evaluated using Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy by performing five-fold cross-validation. The average DSC performance for three different segmentation tasks was obtained as 0.98, 0.858, and 0.616, respectively. The experimental results demonstrate that the proposed method has robust performance and great potential in evaluating COVID-19 infection. COVID-19 is a deadly outbreak that has been declared a public health emergency of international concern. The massive damage of the disease to public health, social life, and the global economy increases the importance of alternative rapid diagnosis and follow-up methods. RT-PCR assay, which is considered the gold standard in diagnosing the disease, is complicated, expensive, time-consuming, prone to contamination, and may give false-negative results. These drawbacks reinforce the trend toward medical imaging techniques such as computed tomography (CT). Typical visual signs such as ground-glass opacity (GGO) and consolidation of CT images allow for quantitative assessment of the disease. In this context, it is aimed at the segmentation of the infected lung CT images with the residual network-based DeepLabV3+, which is a redesigned convolutional neural network (CNN) model. In order to evaluate the robustness of the proposed model, three different segmentation tasks as Task-1, Task-2, and Task-3 were applied. Task-1 represents binary segmentation as lung (infected and non-infected tissues) and background. Task-2 represents multi-class segmentation as lung (non-infected tissue), COVID (GGO, consolidation, and pleural effusion irregularities are gathered under a single roof), and background. Finally, the segmentation in which each lesion type is considered as a separate class is defined as Task-3. COVID-19 imaging data for each segmentation task consists of 100 CT single-slice scans from over 40 diagnosed patients. The performance of the model was evaluated using Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy by performing five-fold cross-validation. The average DSC performance for three different segmentation tasks was obtained as 0.98, 0.858, and 0.616, respectively. The experimental results demonstrate that the proposed method has robust performance and great potential in evaluating COVID-19 infection.COVID-19 is a deadly outbreak that has been declared a public health emergency of international concern. The massive damage of the disease to public health, social life, and the global economy increases the importance of alternative rapid diagnosis and follow-up methods. RT-PCR assay, which is considered the gold standard in diagnosing the disease, is complicated, expensive, time-consuming, prone to contamination, and may give false-negative results. These drawbacks reinforce the trend toward medical imaging techniques such as computed tomography (CT). Typical visual signs such as ground-glass opacity (GGO) and consolidation of CT images allow for quantitative assessment of the disease. In this context, it is aimed at the segmentation of the infected lung CT images with the residual network-based DeepLabV3+, which is a redesigned convolutional neural network (CNN) model. In order to evaluate the robustness of the proposed model, three different segmentation tasks as Task-1, Task-2, and Task-3 were applied. Task-1 represents binary segmentation as lung (infected and non-infected tissues) and background. Task-2 represents multi-class segmentation as lung (non-infected tissue), COVID (GGO, consolidation, and pleural effusion irregularities are gathered under a single roof), and background. Finally, the segmentation in which each lesion type is considered as a separate class is defined as Task-3. COVID-19 imaging data for each segmentation task consists of 100 CT single-slice scans from over 40 diagnosed patients. The performance of the model was evaluated using Dice similarity coefficient (DSC), intersection over union (IoU), sensitivity, specificity, and accuracy by performing five-fold cross-validation. The average DSC performance for three different segmentation tasks was obtained as 0.98, 0.858, and 0.616, respectively. The experimental results demonstrate that the proposed method has robust performance and great potential in evaluating COVID-19 infection.
Author	Polat, Hasan
Author_xml	– sequence: 1 givenname: Hasan orcidid: 0000-0001-5535-4832 surname: Polat fullname: Polat, Hasan email: hasanpolat@bingol.edu.tr organization: Department of Electrical and Energy, Bingol University
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/35286619$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUtv1DAUhS1UREvpH2CBLLFBQgE_EifeIFVTHpUGdVO6te44N8FtYg92wsC_xyVlgC668pX8neN7fJ6SAx88EvKcszecsfpt4lKUqmBCFIxzzordI3IklBJFWcv6YD8LfUhOUrpmjImK81pVT8ihrESjFNdH5MfneZhcMUG6oQlH8JOzeehH9BNMLngaOrq6pG6EHhPtQqSri6vzs4Jr6nyH9pZJdE7O9_QMcbuGzZV8TTeQsKVZ3roBpjxGTK6dYaAep12IN8_I4w6GhCd35zH58uH95epTsb74eL46XRe2rMupqDvJdKdraJlqdVnKqhJtZ6VE3jaaA7f5mgG0m0oBYFkz5NJWUoBqpNIgj8m7xXc7b0Zsbc4VYTDbmBPFnyaAM__fePfV9OG7ye6aK50NXt0ZxPBtxjSZ0SWLwwAew5yMUFILUbOKZ_TlPfQ6zNHneJlquMrfXspMvfh3o_0qf0rJgFgAG0NKEbs9wpm5Ld8s5ZtcvvldvtllUXNPZN3SYE7lhoelcpGm_I7vMf5d-wHVL5MIw9s
CitedBy_id	crossref_primary_10_1016_j_bspc_2024_106691 crossref_primary_10_1038_s41597_025_04709_2 crossref_primary_10_1007_s42452_024_06264_8 crossref_primary_10_1109_ACCESS_2024_3487784 crossref_primary_10_1016_j_bspc_2024_106866 crossref_primary_10_1038_s41598_024_63538_2 crossref_primary_10_1016_j_bspc_2024_107234 crossref_primary_10_3390_diagnostics15030248 crossref_primary_10_1016_j_dsp_2025_105477 crossref_primary_10_1007_s00521_024_10809_8 crossref_primary_10_1007_s11042_025_20763_9 crossref_primary_10_1002_acm2_14553 crossref_primary_10_1007_s12008_025_02360_0 crossref_primary_10_1016_j_bspc_2023_105824 crossref_primary_10_1007_s13246_023_01250_7 crossref_primary_10_1177_20552076231225853 crossref_primary_10_1016_j_compbiomed_2025_110437
Cites_doi	10.1016/j.measurement.2020.108288 10.1007/978-3-319-24574-4_28 10.1007/978-3-319-10578-9_23 10.1016/j.procs.2021.01.025 10.1016/j.knosys.2021.106849 10.1002/mp.14676 10.1016/j.patrec.2020.07.029 10.33889/IJMEMS.2020.5.4.052 10.1016/j.bbe.2021.05.013 10.1016/j.compbiomed.2020.104037 10.1109/TPAMI.2016.2572683 10.1016/j.bbe.2021.04.006 10.1016/j.compbiomed.2020.103805 10.1016/j.bspc.2021.102987 10.1016/j.iot.2021.100377 10.1016/j.ibmed.2020.100013 10.1016/j.eng.2020.04.010 10.3390/s20113183 10.1186/s12880-020-00529-5 10.1109/TPAMI.2016.2644615 10.1109/ACCESS.2021.3067047 10.1016/j.jrid.2020.04.001 10.1002/ima.22558 10.1109/JAS.2020.1003393 10.1016/j.clinimag.2021.01.019 10.1007/978-3-030-01234-2_49 10.1016/j.patcog.2020.10774 10.1145/3453892.3461322 10.1109/cvprw.2009.5206848 10.31590/ejosat.819409 10.1155/2021/9999368 10.1109/TENCON.2019.8929376 10.1016/j.media.2020.101794 10.1016/j.imu.2021.100681 10.5281/ZENODO.3757476 10.1016/j.cmpb.2020.105532 10.1111/exsy.12742 10.1109/CVPR.2016.90 10.1155/2021/8828404
ContentType	Journal Article
Copyright	Australasian College of Physical Scientists and Engineers in Medicine 2022 2022. Australasian College of Physical Scientists and Engineers in Medicine. Australasian College of Physical Scientists and Engineers in Medicine 2022.
Copyright_xml	– notice: Australasian College of Physical Scientists and Engineers in Medicine 2022 – notice: 2022. Australasian College of Physical Scientists and Engineers in Medicine. – notice: Australasian College of Physical Scientists and Engineers in Medicine 2022.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88E 88I 8AO 8FE 8FG 8FI 8FJ 8FK ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. M0S M1P M2P P5Z P62 PHGZM PHGZT PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 5PM
DOI	10.1007/s13246-022-01110-w
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest Pharma Collection ProQuest SciTech Collection ProQuest Technology Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Technology collection ProQuest One Community College ProQuest Central Korea Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) Science Database ProQuest advanced technologies & aerospace journals ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Pharma Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) Advanced Technologies & Aerospace Collection ProQuest Science Journals (Alumni Edition) ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection ProQuest Technology Collection Health Research Premium Collection (Alumni) ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) Advanced Technologies & Aerospace Database ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic ProQuest Central Student MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Public Health
EISSN	2662-4737 1879-5447
EndPage	455
ExternalDocumentID	PMC8919169 35286619 10_1007_s13246_022_01110_w
Genre	Journal Article
GroupedDBID	0R~ 406 AACDK AAHNG AAJBT AANZL AASML AATNV AAUYE AAYZH ABAKF ABDZT ABECU ABJNI ABMQK ABSXP ABTEG ABTKH ACAOD ACDTI ACHSB ACMDZ ACOKC ACPIV ACZOJ ADKNI ADTPH ADYFF AEFQL AEMSY AESKC AEVLU AFBBN AFLOW AFQWF AGMZJ AGQEE AGRTI AIAKS AIGIU AILAN ALMA_UNASSIGNED_HOLDINGS AMXSW AMYLF AOCGG BGNMA DDRTE DNIVK DPUIP EBLON EBS EMB EMOBN FERAY FIGPU FNLPD GGCAI IKXTQ IWAJR J-C JZLTJ LLZTM M4Y NPVJJ NQJWS NU0 PT4 ROL RSV SJYHP SNE SNPRN SNX SOHCF SOJ SRMVM SSLCW SV3 UOJIU UTJUX ZMTXR AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC AEZWR AFDZB AFHIU AFOHR AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION KOV CGR CUY CVF ECM EIF NPM ..I 06D 0VY 1N0 203 23N 29~ 2KG 30V 36B 3V. 4.4 408 40D 53G 5GY 67N 7X7 7XB 88E 88I 8AO 8FE 8FG 8FI 8FJ 8FK 8WZ 96X A6W AAIAL AAJKR AARTL AATVU AAWCG AAYIU AAYQN AAZMS ABFTV ABJOX ABKCH ABPLI ABQBU ABTHY ABTMW ABUWG ABXPI ACGFS ACGOD ACKNC ACMLO ADBBV ADHHG ADHIR ADKPE ADRFC ADURQ ADZKW AEGNC AEJHL AEJRE AENEX AEOHA AEPYU AETCA AEXYK AFKRA AFWTZ AFZKB AGAYW AGDGC AGJBK AGQMX AGWZB AGYKE AHAVH AHBYD AHKAY AHMBA AHYZX AIIXL AITGF AJRNO AJZVZ AKMHD ALFXC AMKLP AMYQR ANMIH ARAPS AXYYD AZQEC BENPR BGLVJ BPHCQ BVXVI CCPQU CSCUP DWQXO EIOEI EN4 ESBYG FRRFC FYJPI FYUFA GGRSB GJIRD GNUQQ GQ7 HCIFZ HMJXF HRMNR HZ~ I0C ITM J0Z JBSCW K9. KTM M1P M2P O9- O93 O9I O9J P2P P62 PHGZM PHGZT PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS PROAC PSQYO Q9U R9I RLLFE S27 S3A S3B SBL SHX SISQX SPISZ SSXJD STPWE T13 TSG U2A U9L UG4 UKHRP UZXMN VC2 VFIZW W48 WK8 WOQ Z45 ZOVNA ~A9 7X8 5PM
ID	FETCH-LOGICAL-c474t-7f309f97ad06d9443552dfc33e1d891a1c09f0aadb56aae470e13c532a68369a3
IEDL.DBID	RSV
ISICitedReferencesCount	20
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000768620200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2662-4729 0158-9938 2662-4737
IngestDate	Tue Nov 04 02:04:02 EST 2025 Thu Oct 02 11:54:23 EDT 2025 Wed Nov 05 04:11:18 EST 2025 Thu Apr 03 07:04:34 EDT 2025 Tue Nov 18 22:35:36 EST 2025 Sat Nov 29 04:09:58 EST 2025 Fri Feb 21 02:46:14 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	Deep learning Image segmentation Coronavirus (COVID-19) Computed tomography images Image classification
Language	English
License	2022. Australasian College of Physical Scientists and Engineers in Medicine. This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c474t-7f309f97ad06d9443552dfc33e1d891a1c09f0aadb56aae470e13c532a68369a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-5535-4832
OpenAccessLink	http://dx.doi.org/10.1007/s13246-022-01110-w
PMID	35286619
PQID	2681635243
PQPubID	33672
PageCount	13
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_8919169 proquest_miscellaneous_2639227051 proquest_journals_2681635243 pubmed_primary_35286619 crossref_primary_10_1007_s13246_022_01110_w crossref_citationtrail_10_1007_s13246_022_01110_w springer_journals_10_1007_s13246_022_01110_w
PublicationCentury	2000
PublicationDate	2022-06-01
PublicationDateYYYYMMDD	2022-06-01
PublicationDate_xml	– month: 06 year: 2022 text: 2022-06-01 day: 01
PublicationDecade	2020
PublicationPlace	Cham
PublicationPlace_xml	– name: Cham – name: Switzerland – name: Dordrecht
PublicationSubtitle	The Official Journal of the Australasian College of Physical Scientists and Engineers in Medicine
PublicationTitle	Australasian physical & engineering sciences in medicine
PublicationTitleAbbrev	Phys Eng Sci Med
PublicationTitleAlternate	Phys Eng Sci Med
PublicationYear	2022
Publisher	Springer International Publishing Springer Nature B.V
Publisher_xml	– name: Springer International Publishing – name: Springer Nature B.V
References	Benameur, Mahmoudi, Zaid (CR12) 2021; 76 Baheti, Innani, Gajre, Talbar (CR14) 2020; 138 Sethy, Behera, Ratha, Biswas (CR16) 2020; 5 Kassania, Kassanib, Wesolowskic (CR20) 2021; 41 Badrinarayanan, Kendall, Cipolla (CR26) 2017; 39 CR17 CR39 CR36 CR35 Khan, Yahya, Alsaih (CR43) 2020; 20 Chen, Zhu, Papandreou (CR15) 2018; 11211 LNCS CR34 CR33 Polat, Özerdem, Ekici, Akpolat (CR18) 2021; 31 CR32 Ronneberger, Fischer, Brox (CR25) 2015; 9351 CR31 CR30 Saood, Hatem (CR13) 2021; 21 Amyar, Modzelewski, Li, Ruan (CR11) 2020; 126 Sarwinda, Paradisa, Bustamam, Anggia (CR37) 2021; 179 Pei, Yang, Liu, Lu (CR42) 2021; 9 CR2 Toğaçar, Ergen, Cömert (CR1) 2020 Desai, Pareek, Lungren (CR9) 2020; 3–4 CR5 CR7 Mishra, Singh, Joshi (CR8) 2021; 41 CR29 Li (CR10) 2020; 7 CR28 Ohata, Bezerra, Chagas, Das (CR21) 2021; 8 Shelhamer, Long, Darrell (CR27) 2017; 39 Loey, Manogaran, Taha, Khalifa (CR4) 2021; 167 Rohila, Gupta, Kaul, Sharma (CR3) 2021; 14 CR23 CR22 He, Zhang, Ren, Sun (CR38) 2014; 8691 LNCS Ma, Wang, An (CR41) 2021; 48 CR44 Xu, Jiang, Ma (CR6) 2020; 6 Li, Yang, Liang, Wu (CR24) 2021; 218 CR40 JavadiMoghaddam, Gholamalinejad (CR19) 2021; 70 A Saood (1110_CR13) 2021; 21 J Ma (1110_CR41) 2021; 48 1110_CR33 1110_CR32 1110_CR31 SH Kassania (1110_CR20) 2021; 41 1110_CR30 H Polat (1110_CR18) 2021; 31 LC Chen (1110_CR15) 2018; 11211 LNCS X Xu (1110_CR6) 2020; 6 M Loey (1110_CR4) 2021; 167 1110_CR17 1110_CR39 1110_CR36 E Shelhamer (1110_CR27) 2017; 39 1110_CR35 1110_CR34 V Badrinarayanan (1110_CR26) 2017; 39 VS Rohila (1110_CR3) 2021; 14 M Toğaçar (1110_CR1) 2020 SM JavadiMoghaddam (1110_CR19) 2021; 70 1110_CR22 1110_CR44 N Benameur (1110_CR12) 2021; 76 1110_CR40 Z Khan (1110_CR43) 2020; 20 SB Desai (1110_CR9) 2020; 3–4 A Amyar (1110_CR11) 2020; 126 C Li (1110_CR24) 2021; 218 1110_CR7 1110_CR29 K He (1110_CR38) 2014; 8691 LNCS B Baheti (1110_CR14) 2020; 138 O Ronneberger (1110_CR25) 2015; 9351 1110_CR28 HY Pei (1110_CR42) 2021; 9 PK Sethy (1110_CR16) 2020; 5 1110_CR23 1110_CR2 D Sarwinda (1110_CR37) 2021; 179 M Li (1110_CR10) 2020; 7 EF Ohata (1110_CR21) 2021; 8 NK Mishra (1110_CR8) 2021; 41 1110_CR5
References_xml	– volume: 167 start-page: 108288 year: 2021 ident: CR4 article-title: A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic publication-title: Meas J Int Meas Confed doi: 10.1016/j.measurement.2020.108288 – ident: CR22 – volume: 9351 start-page: 234 year: 2015 end-page: 241 ident: CR25 article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation publication-title: Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) doi: 10.1007/978-3-319-24574-4_28 – ident: CR39 – ident: CR2 – volume: 8691 LNCS start-page: 346 year: 2014 end-page: 361 ident: CR38 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) doi: 10.1007/978-3-319-10578-9_23 – volume: 179 start-page: 423 year: 2021 end-page: 431 ident: CR37 article-title: Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer publication-title: Procedia Comput Sci doi: 10.1016/j.procs.2021.01.025 – ident: CR30 – ident: CR33 – volume: 218 start-page: 106849 year: 2021 ident: CR24 article-title: Transfer learning for establishment of recognition of COVID-19 on CT imaging using small-sized training datasets[Formula presented] publication-title: Knowledge-Based Syst doi: 10.1016/j.knosys.2021.106849 – ident: CR35 – volume: 48 start-page: 1197 year: 2021 end-page: 1210 ident: CR41 article-title: Toward data-efficient learning: A benchmark for COVID-19 CT lung and infection segmentation publication-title: Med Phys doi: 10.1002/mp.14676 – ident: CR29 – volume: 138 start-page: 223 year: 2020 end-page: 229 ident: CR14 article-title: Semantic scene segmentation in unstructured environment with modified DeepLabV3+ publication-title: Pattern Recognit Lett doi: 10.1016/j.patrec.2020.07.029 – volume: 5 start-page: 643 year: 2020 end-page: 651 ident: CR16 article-title: Detection of coronavirus disease (COVID-19) based on deep features and support vector machine publication-title: Int J Math Eng Manag Sci doi: 10.33889/IJMEMS.2020.5.4.052 – volume: 41 start-page: 867 year: 2021 end-page: 879 ident: CR20 article-title: Automatic Detection of Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning Based Approach publication-title: Biocybern Biomed Eng doi: 10.1016/j.bbe.2021.05.013 – ident: CR40 – volume: 126 start-page: 104037 year: 2020 ident: CR11 article-title: Multi-task deep learning based CT imaging analysis for COVID-19 pneumonia: Classification and segmentation publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2020.104037 – ident: CR23 – volume: 39 start-page: 640 year: 2017 end-page: 651 ident: CR27 article-title: Fully Convolutional Networks for Semantic Segmentation publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2572683 – volume: 41 start-page: 572 year: 2021 end-page: 588 ident: CR8 article-title: Automated detection of COVID-19 from CT scan using convolutional neural network publication-title: Biocybern Biomed Eng doi: 10.1016/j.bbe.2021.04.006 – year: 2020 ident: CR1 article-title: COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2020.103805 – ident: CR44 – volume: 70 start-page: 102987 year: 2021 ident: CR19 article-title: A novel deep learning based method for COVID-19 detection from CT image publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2021.102987 – volume: 14 start-page: 100377 year: 2021 ident: CR3 article-title: Deep learning assisted COVID-19 detection using full CT-scans publication-title: Internet of Things (Netherlands) doi: 10.1016/j.iot.2021.100377 – volume: 3–4 start-page: 100013 year: 2020 ident: CR9 article-title: Deep learning and its role in COVID-19 medical imaging publication-title: Intell Med doi: 10.1016/j.ibmed.2020.100013 – volume: 6 start-page: 1122 year: 2020 end-page: 1129 ident: CR6 article-title: A Deep Learning System to Screen Novel Coronavirus Disease 2019 Pneumonia publication-title: Engineering doi: 10.1016/j.eng.2020.04.010 – volume: 20 start-page: 1 year: 2020 end-page: 17 ident: CR43 article-title: Evaluation of deep neural networks for semantic segmentation of prostate in T2W MRI publication-title: Sens (Switzerland) doi: 10.3390/s20113183 – volume: 21 start-page: 1 year: 2021 end-page: 11 ident: CR13 article-title: COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet publication-title: BMC Med Imaging doi: 10.1186/s12880-020-00529-5 – volume: 39 start-page: 2481 year: 2017 end-page: 2495 ident: CR26 article-title: Segnet: A deep convolutional encoder-decoder architecture for image segmentation publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2644615 – ident: CR17 – volume: 9 start-page: 47144 year: 2021 end-page: 47153 ident: CR42 article-title: MPS-net: Multi-point supervised network for ct image segmentation of covid-19 publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3067047 – volume: 7 start-page: 51 year: 2020 end-page: 54 ident: CR10 article-title: Chest CT features and their role in COVID-19 publication-title: Radiol Infect Dis doi: 10.1016/j.jrid.2020.04.001 – ident: CR31 – volume: 31 start-page: 509 year: 2021 end-page: 524 ident: CR18 article-title: Automatic detection and localization of COVID-19 pneumonia using axial computed tomography images and deep convolutional neural networks publication-title: Int J Imaging Syst Technol doi: 10.1002/ima.22558 – ident: CR32 – ident: CR34 – ident: CR36 – volume: 8 start-page: 239 year: 2021 end-page: 248 ident: CR21 article-title: Automatic detection of COVID-19 infection using chest X-ray images through transfer learning publication-title: IEEE/CAA J Autom Sin doi: 10.1109/JAS.2020.1003393 – ident: CR5 – ident: CR7 – volume: 76 start-page: 6 year: 2021 end-page: 14 ident: CR12 article-title: SARS-CoV-2 diagnosis using medical imaging techniques and artificial intelligence: A review publication-title: Clin Imaging doi: 10.1016/j.clinimag.2021.01.019 – ident: CR28 – volume: 11211 LNCS start-page: 833 year: 2018 end-page: 851 ident: CR15 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation publication-title: Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) doi: 10.1007/978-3-030-01234-2_49 – volume: 167 start-page: 108288 year: 2021 ident: 1110_CR4 publication-title: Meas J Int Meas Confed doi: 10.1016/j.measurement.2020.108288 – ident: 1110_CR7 doi: 10.1016/j.patcog.2020.10774 – volume: 41 start-page: 572 year: 2021 ident: 1110_CR8 publication-title: Biocybern Biomed Eng doi: 10.1016/j.bbe.2021.04.006 – volume: 7 start-page: 51 year: 2020 ident: 1110_CR10 publication-title: Radiol Infect Dis doi: 10.1016/j.jrid.2020.04.001 – volume: 70 start-page: 102987 year: 2021 ident: 1110_CR19 publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2021.102987 – volume: 11211 LNCS start-page: 833 year: 2018 ident: 1110_CR15 publication-title: Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) doi: 10.1007/978-3-030-01234-2_49 – volume: 41 start-page: 867 year: 2021 ident: 1110_CR20 publication-title: Biocybern Biomed Eng doi: 10.1016/j.bbe.2021.05.013 – ident: 1110_CR30 doi: 10.1145/3453892.3461322 – ident: 1110_CR34 doi: 10.1109/cvprw.2009.5206848 – volume: 39 start-page: 640 year: 2017 ident: 1110_CR27 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2572683 – volume: 48 start-page: 1197 year: 2021 ident: 1110_CR41 publication-title: Med Phys doi: 10.1002/mp.14676 – year: 2020 ident: 1110_CR1 publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2020.103805 – volume: 126 start-page: 104037 year: 2020 ident: 1110_CR11 publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2020.104037 – volume: 76 start-page: 6 year: 2021 ident: 1110_CR12 publication-title: Clin Imaging doi: 10.1016/j.clinimag.2021.01.019 – ident: 1110_CR44 doi: 10.31590/ejosat.819409 – ident: 1110_CR33 – volume: 9351 start-page: 234 year: 2015 ident: 1110_CR25 publication-title: Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) doi: 10.1007/978-3-319-24574-4_28 – ident: 1110_CR5 – volume: 8691 LNCS start-page: 346 year: 2014 ident: 1110_CR38 publication-title: Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) doi: 10.1007/978-3-319-10578-9_23 – ident: 1110_CR28 doi: 10.1155/2021/9999368 – ident: 1110_CR39 – ident: 1110_CR35 doi: 10.1109/TENCON.2019.8929376 – volume: 31 start-page: 509 year: 2021 ident: 1110_CR18 publication-title: Int J Imaging Syst Technol doi: 10.1002/ima.22558 – volume: 218 start-page: 106849 year: 2021 ident: 1110_CR24 publication-title: Knowledge-Based Syst doi: 10.1016/j.knosys.2021.106849 – volume: 138 start-page: 223 year: 2020 ident: 1110_CR14 publication-title: Pattern Recognit Lett doi: 10.1016/j.patrec.2020.07.029 – volume: 39 start-page: 2481 year: 2017 ident: 1110_CR26 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2644615 – ident: 1110_CR22 doi: 10.1016/j.media.2020.101794 – volume: 14 start-page: 100377 year: 2021 ident: 1110_CR3 publication-title: Internet of Things (Netherlands) doi: 10.1016/j.iot.2021.100377 – ident: 1110_CR32 doi: 10.1016/j.imu.2021.100681 – volume: 179 start-page: 423 year: 2021 ident: 1110_CR37 publication-title: Procedia Comput Sci doi: 10.1016/j.procs.2021.01.025 – volume: 5 start-page: 643 year: 2020 ident: 1110_CR16 publication-title: Int J Math Eng Manag Sci doi: 10.33889/IJMEMS.2020.5.4.052 – volume: 6 start-page: 1122 year: 2020 ident: 1110_CR6 publication-title: Engineering doi: 10.1016/j.eng.2020.04.010 – ident: 1110_CR40 doi: 10.5281/ZENODO.3757476 – ident: 1110_CR2 doi: 10.1016/j.cmpb.2020.105532 – volume: 3–4 start-page: 100013 year: 2020 ident: 1110_CR9 publication-title: Intell Med doi: 10.1016/j.ibmed.2020.100013 – volume: 8 start-page: 239 year: 2021 ident: 1110_CR21 publication-title: IEEE/CAA J Autom Sin doi: 10.1109/JAS.2020.1003393 – volume: 20 start-page: 1 year: 2020 ident: 1110_CR43 publication-title: Sens (Switzerland) doi: 10.3390/s20113183 – volume: 9 start-page: 47144 year: 2021 ident: 1110_CR42 publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3067047 – ident: 1110_CR31 doi: 10.1111/exsy.12742 – ident: 1110_CR36 doi: 10.1109/CVPR.2016.90 – ident: 1110_CR29 – ident: 1110_CR17 – volume: 21 start-page: 1 year: 2021 ident: 1110_CR13 publication-title: BMC Med Imaging doi: 10.1186/s12880-020-00529-5 – ident: 1110_CR23 doi: 10.1155/2021/8828404
SSID	ssj0002511765 ssj0024368
Score	2.41564
Snippet	COVID-19 is a deadly outbreak that has been declared a public health emergency of international concern. The massive damage of the disease to public health,...
SourceID	pubmedcentral proquest pubmed crossref springer
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	443
SubjectTerms	Artificial neural networks Biological and Medical Physics Biomedical and Life Sciences Biomedical Engineering and Bioengineering Biomedicine Biophysics Computed tomography Consolidation Coronaviruses COVID-19 COVID-19 - diagnostic imaging Global economy Humans Image Processing, Computer-Assisted - methods Image segmentation Imaging techniques Lungs Medical and Radiation Physics Medical imaging Neural Networks, Computer Public health Scientific Paper Semantic segmentation Semantics Tomography, X-Ray Computed - methods Viral diseases
SummonAdditionalLinks	– databaseName: Science Database dbid: M2P link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB5B4QBCPMorUJCRuBWrSZw48QmhLRVIpfRQqt4iv1JWdLPLekv5-YwdZ7dLRS-cbSdxZsbzaTzzDcBbZhHUa5XRWnIfrRIVFbUqqGpTkyqL9qcDiet-dXBQn5yIwxhwczGtcjgTw0FtptrHyHdyXiN0KPOCvZ_9pL5rlL9djS00bsItRDaZT-n6kh9e4toLpXDo8dCoBatj0UxfOodIwqff-sQEdIH0Yt0xXUGbV5Mm_7o5DQ5p78H_buUh3I9QlHzodecR3LDdJty9RFC4Cff6qB7pi5Uew-9Qr0sX0v0gzk5QKjjo7OkkVjB1ZNqS0REZT_CYcgQBMRl9Pf68SzNBhrSvzhGfbH9Kdq2d7Ut1zLaJ96WG4HIzPkPwa8jculAlRro-Tf0JfNv7eDT6RGPvBqqLqljQqmWpaEUlTcqNKBCUlblpNWM2M7XIZKZxOJXSqJJLaYsqtRnTJctRZRgXkj2FjW7a2edAtEjLWvG6zbgqrFSS40MsPk1ZXipWJJANgmt0JDb3_TXOmhUlsxd2g8JugrCbiwS2l2tmPa3HtbO3BkE20cRds5JiAm-Ww2ic_sZFdnZ67ucg_MwrPPgSeNarz_J1nlYHwZFIoFpTrOUET_y9PtKNvwcCcPyBiOpx5btBBVef9e9dvLh-Fy_hTh7MwUeYtmBjMT-3r-C2_rUYu_nrYFh_AE09KV4 priority: 102 providerName: ProQuest
Title	Multi-task semantic segmentation of CT images for COVID-19 infections using DeepLabV3+ based on dilated residual network
URI	https://link.springer.com/article/10.1007/s13246-022-01110-w https://www.ncbi.nlm.nih.gov/pubmed/35286619 https://www.proquest.com/docview/2681635243 https://www.proquest.com/docview/2639227051 https://pubmed.ncbi.nlm.nih.gov/PMC8919169
Volume	45
WOSCitedRecordID	wos000768620200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAVX databaseName: SpringerLink Journals customDbUrl: eissn: 2662-4737 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511765 issn: 2662-4729 databaseCode: RSV dateStart: 20010301 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwED-xjQd4GJ9jgVEZibdhKYmdOH6EbhNIo1RjVBUvke04I2JNp6Vj_Pmc3SSlDJDgJUrksxOfz75f7PsAeMksgnqjI5qp1O1WSUFlpjnVZViE2uL8Mz6I67EYjbLpVI5bp7Cms3bvjiT9Sr1ydkPd7wxmnSkBKi16vQFbqO4yl7Dh5OOk31lxoFn4HJKofGLKET623jK_b2ZdI92AmTetJX85MvWa6Oje__XhPmy3yJO8XorKA7hl64dw96d4hI_gu3fHpQvVfCWNnSHTK4M3Z7PWQakm85IMT0k1w1WoIYh3yfDD5N0BjSTprLrqhjhb-jNyYO3FsdITtk-cqiwIVi-qc8S2BcF_fO8ERuqlFfpj-HR0eDp8S9vUDNRwwRdUlCyUpRSqCNNCcsRcSVyUhjEbFZmMVGSwOFSq0EmqlOUitBEzCYtRIlgqFduBzXpe210gRoZJptOsjFLNrdIqxUYstqZtmmjGA4i64clNG7fcpc84z1cRlx1Xc-Rq7rmaXwew39e5WEbt-Cv1XjfqeTuDmzxOM4SqScxZAC_6Ypx77kBF1XZ-5WgQXcYC17UAniyFpH-di5qD2EcGINbEpydwcb3XS-rqi4_vjQxE0I41X3VCtPqsP_fi6b-RP4M7sZdDt6G0B5uLyyv7HG6bb4uquRzAhpgKf80GsPXmcDQ-waf38Riv4-TzwM-4H96OIPA
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFD4aAwkQ4jIGFAYYCZ6GtSTOzQ8IoZZp1UrZQ5n2lvmWUbGmpeko_Cl-I8dO0q5M7G0PPPuS2PnO8Rf7nM8Ar5lBUq-kT1MR290qnlCeypDK3NOeNGh_yom49pJ-Pz064gdr8LvJhbFhlY1PdI5aj5XdI98J4hSpQxSE7P3kO7W3RtnT1eYKjQoW--bXHH_ZynfdDn7fN0Gw-3HQ3qP1rQJUhUk4o0nOPJ7zRGgv1jxEuhAFOleMGV-n3Be-wmJPCC2jWAgTJp7xmYpYgINhMRcM-70G10OrLGZDBYODc9p-LvUOV1h0IpyldZJOlaqHzMWG-9pACFxy6Xx1IbzAbi8Gaf51UusWwN17_9vU3Ye7NdUmHyrbeABrptiA2-cEGDfgTrVrSapkrIfw0-Uj05kov5HSjBB1WFiak1GdoVWQcU7aAzIcoRsuCRJ-0v582O1Qn5MmrK0oiU0mOCEdYyY9IQ_ZNrFcQRNsroenSO41mZrSZcGRogrD34QvVzIVj2C9GBfmCRDFvSiVcZr7sQyNkCLGTgz2Jk0cSRa2wG-AkqlauN3eH3KaLSWnLbgyBFfmwJXNW7C9aDOpZEsurb3VACerXViZLVHTgleLYnQ-9kRJFGZ8ZusgvQ4SdOwteFzBdfE4KxuE5I-3IFkB8qKCFTZfLSmGX53AOU4g_rVgy7cN5Jev9e9RPL18FC_h5t7gUy_rdfv7z-BW4EzR7qZtwfpsemaeww31YzYspy-cURM4vmpT-ANtn4Xs
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LbxMxEB6VghAI8SivQAEjwalY3V3vyweEUEJE1CjkUKqql8WvLRHNJmRTAn-NX8fYu5s0VPTWA2c_Enu_GX-25xsDvGIGSb2SPk1FbE-reEJ5KkMqc0970qD9KZfEtZ8MBunhIR9uwO9GC2PDKhuf6By1nih7Rr4bxClShygI2W5eh0UMO9130-_UviBlb1qb5zQqiOyZXwvcvpVvex381q-DoPthv_2R1i8MUBUm4ZwmOfN4zhOhvVjzEKlDFOhcMWZ8nXJf-AqLPSG0jGIhTJh4xmcqYgEOjMVcMOz3ClxNcI9pwwmH0dGZPH9OhoerLToUztJasFPJ9pDF2NBfGxSByy9drC-K55ju-YDNv25t3WLYvfM_T-NduF1TcPK-spl7sGGKLbh5JjHjFtyqTjNJJdK6Dz-dTpnORfmNlGaMaMTC0hyPa-VWQSY5ae-T0Rjdc0lwI0Danw56Hepz0oS7FSWxIoNj0jFm2hfygO0QyyE0weZ6dIKkX5OZKZ06jhRVeP4D-HwpU_EQNotJYR4DUdyLUhmnuR_L0AgpYuzEYG_SxJFkYQv8BjSZqhO623dFTrJVKmoLtAyBljmgZYsW7CzbTKt0JhfW3m5AlNWurcxWCGrBy2UxOiV70yQKMzm1dZB2Bwk6_BY8qqC7_DmbTghJIW9BsgbqZQWb8Hy9pBh9dYnPcQJxN4Mt3zTwX_2tf4_iycWjeAHX0QKyfm-w9xRuBM4q7SHbNmzOZ6fmGVxTP-ajcvbc2TeBL5dtCX8AZr6O2A
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=Multi-task+semantic+segmentation+of+CT+images+for+COVID-19+infections+using+DeepLabV3%2B+based+on+dilated+residual+network&rft.jtitle=Physical+and+engineering+sciences+in+medicine&rft.au=Polat%2C+Hasan&rft.date=2022-06-01&rft.issn=2662-4737&rft.eissn=2662-4737&rft.volume=45&rft.issue=2&rft.spage=443&rft_id=info:doi/10.1007%2Fs13246-022-01110-w&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2662-4729&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2662-4729&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2662-4729&client=summon