Evaluation of Diffusion Lesion Volume Measurements in Acute Ischemic Stroke Using Encoder-Decoder Convolutional Network
Background and Purpose- Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent diffusion coefficient (ADC) threshold. Fixed ADC threshold methods may not be accurate because ADC values vary over time after stroke onset. Deep...
Uloženo v:
| Vydáno v: | Stroke (1970) Ročník 50; číslo 6; s. 1444 |
|---|---|
| Hlavní autoři: | , , , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
01.06.2019
|
| Témata: | |
| ISSN: | 1524-4628, 1524-4628 |
| On-line přístup: | Zjistit podrobnosti o přístupu |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Background and Purpose- Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent diffusion coefficient (ADC) threshold. Fixed ADC threshold methods may not be accurate because ADC values vary over time after stroke onset. Deep learning has the potential to improve the accuracy, provided that a large set of correctly annotated lesion data is used for training. The purpose of this study was to evaluate deep learning-based methods and compare them with commercial software in terms of lesion volume measurements. Methods- U-net, an encoder-decoder convolutional neural network, was adopted to train segmentation models. Two U-net models were developed: a U-net (DWI+ADC) model, trained on DWI and ADC data, and a U-net (DWI) model, trained on DWI data only. A total of 296 subjects were used for training and 134 for external validation. An expert neurologist manually delineated the stroke lesions on DWI images, which were used as the ground-truth reference. Lesion volume measurements from the U-net methods were compared against the expert's manual segmentation and Rapid Processing of Perfusion and Diffusion (RAPID; iSchemaView Inc) analysis. Results- In external validation, U-net (DWI+ADC) showed the highest intraclass correlation coefficient with manual segmentation (intraclass correlation coefficient, 1.0; 95% CI, 0.99-1.00) and sufficiently high correlation with the RAPID results (intraclass correlation coefficient, 0.99; 95% CI, 0.98-0.99). U-net (DWI+ADC) and manual segmentation resulted in the smallest 95% Bland-Altman limits of agreement (-5.31 to 4.93 mL) with a mean difference of -0.19 mL. Conclusions- The presented deep learning-based method is fully automatic and shows a high correlation of diffusion lesion volume measurements with manual segmentation and commercial software. The method has the potential to be used in patient selection for endovascular reperfusion therapy in the late time window of acute stroke. |
|---|---|
| AbstractList | Background and Purpose- Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent diffusion coefficient (ADC) threshold. Fixed ADC threshold methods may not be accurate because ADC values vary over time after stroke onset. Deep learning has the potential to improve the accuracy, provided that a large set of correctly annotated lesion data is used for training. The purpose of this study was to evaluate deep learning-based methods and compare them with commercial software in terms of lesion volume measurements. Methods- U-net, an encoder-decoder convolutional neural network, was adopted to train segmentation models. Two U-net models were developed: a U-net (DWI+ADC) model, trained on DWI and ADC data, and a U-net (DWI) model, trained on DWI data only. A total of 296 subjects were used for training and 134 for external validation. An expert neurologist manually delineated the stroke lesions on DWI images, which were used as the ground-truth reference. Lesion volume measurements from the U-net methods were compared against the expert's manual segmentation and Rapid Processing of Perfusion and Diffusion (RAPID; iSchemaView Inc) analysis. Results- In external validation, U-net (DWI+ADC) showed the highest intraclass correlation coefficient with manual segmentation (intraclass correlation coefficient, 1.0; 95% CI, 0.99-1.00) and sufficiently high correlation with the RAPID results (intraclass correlation coefficient, 0.99; 95% CI, 0.98-0.99). U-net (DWI+ADC) and manual segmentation resulted in the smallest 95% Bland-Altman limits of agreement (-5.31 to 4.93 mL) with a mean difference of -0.19 mL. Conclusions- The presented deep learning-based method is fully automatic and shows a high correlation of diffusion lesion volume measurements with manual segmentation and commercial software. The method has the potential to be used in patient selection for endovascular reperfusion therapy in the late time window of acute stroke. Background and Purpose- Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent diffusion coefficient (ADC) threshold. Fixed ADC threshold methods may not be accurate because ADC values vary over time after stroke onset. Deep learning has the potential to improve the accuracy, provided that a large set of correctly annotated lesion data is used for training. The purpose of this study was to evaluate deep learning-based methods and compare them with commercial software in terms of lesion volume measurements. Methods- U-net, an encoder-decoder convolutional neural network, was adopted to train segmentation models. Two U-net models were developed: a U-net (DWI+ADC) model, trained on DWI and ADC data, and a U-net (DWI) model, trained on DWI data only. A total of 296 subjects were used for training and 134 for external validation. An expert neurologist manually delineated the stroke lesions on DWI images, which were used as the ground-truth reference. Lesion volume measurements from the U-net methods were compared against the expert's manual segmentation and Rapid Processing of Perfusion and Diffusion (RAPID; iSchemaView Inc) analysis. Results- In external validation, U-net (DWI+ADC) showed the highest intraclass correlation coefficient with manual segmentation (intraclass correlation coefficient, 1.0; 95% CI, 0.99-1.00) and sufficiently high correlation with the RAPID results (intraclass correlation coefficient, 0.99; 95% CI, 0.98-0.99). U-net (DWI+ADC) and manual segmentation resulted in the smallest 95% Bland-Altman limits of agreement (-5.31 to 4.93 mL) with a mean difference of -0.19 mL. Conclusions- The presented deep learning-based method is fully automatic and shows a high correlation of diffusion lesion volume measurements with manual segmentation and commercial software. The method has the potential to be used in patient selection for endovascular reperfusion therapy in the late time window of acute stroke.Background and Purpose- Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent diffusion coefficient (ADC) threshold. Fixed ADC threshold methods may not be accurate because ADC values vary over time after stroke onset. Deep learning has the potential to improve the accuracy, provided that a large set of correctly annotated lesion data is used for training. The purpose of this study was to evaluate deep learning-based methods and compare them with commercial software in terms of lesion volume measurements. Methods- U-net, an encoder-decoder convolutional neural network, was adopted to train segmentation models. Two U-net models were developed: a U-net (DWI+ADC) model, trained on DWI and ADC data, and a U-net (DWI) model, trained on DWI data only. A total of 296 subjects were used for training and 134 for external validation. An expert neurologist manually delineated the stroke lesions on DWI images, which were used as the ground-truth reference. Lesion volume measurements from the U-net methods were compared against the expert's manual segmentation and Rapid Processing of Perfusion and Diffusion (RAPID; iSchemaView Inc) analysis. Results- In external validation, U-net (DWI+ADC) showed the highest intraclass correlation coefficient with manual segmentation (intraclass correlation coefficient, 1.0; 95% CI, 0.99-1.00) and sufficiently high correlation with the RAPID results (intraclass correlation coefficient, 0.99; 95% CI, 0.98-0.99). U-net (DWI+ADC) and manual segmentation resulted in the smallest 95% Bland-Altman limits of agreement (-5.31 to 4.93 mL) with a mean difference of -0.19 mL. Conclusions- The presented deep learning-based method is fully automatic and shows a high correlation of diffusion lesion volume measurements with manual segmentation and commercial software. The method has the potential to be used in patient selection for endovascular reperfusion therapy in the late time window of acute stroke. |
| Author | Seong, Joon-Kyung Nam, Hyo Suk Jeong, Han-Gil Bang, Oh Young Chung, Jong-Won Lee, Ji-Eun Kim, Beom Joon Kim, Gyeong-Moon Yu, Inwu Song, Ha-Na Seo, Woo-Keun Kim, Yoon-Chul Baek, In-Young |
| Author_xml | – sequence: 1 givenname: Yoon-Chul surname: Kim fullname: Kim, Yoon-Chul organization: From the Clinical Research Institute (Y.-C.K.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 2 givenname: Ji-Eun surname: Lee fullname: Lee, Ji-Eun organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 3 givenname: Inwu surname: Yu fullname: Yu, Inwu organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 4 givenname: Ha-Na surname: Song fullname: Song, Ha-Na organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 5 givenname: In-Young surname: Baek fullname: Baek, In-Young organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 6 givenname: Joon-Kyung surname: Seong fullname: Seong, Joon-Kyung organization: Department of Biomedical Engineering, Korea University, Seoul (J.-K.S.) – sequence: 7 givenname: Han-Gil surname: Jeong fullname: Jeong, Han-Gil organization: Department of Neurology and Cerebrovascular Center, Seoul National University Bundang Hospital, Seong Nam, Republic of Korea (H.-G.J., B.J.K.) – sequence: 8 givenname: Beom Joon surname: Kim fullname: Kim, Beom Joon organization: Department of Neurology and Cerebrovascular Center, Seoul National University Bundang Hospital, Seong Nam, Republic of Korea (H.-G.J., B.J.K.) – sequence: 9 givenname: Hyo Suk surname: Nam fullname: Nam, Hyo Suk organization: Department of Neurology, Yonsei University, Seoul, Republic of Korea (H.S.N.) – sequence: 10 givenname: Jong-Won surname: Chung fullname: Chung, Jong-Won organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 11 givenname: Oh Young surname: Bang fullname: Bang, Oh Young organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 12 givenname: Gyeong-Moon surname: Kim fullname: Kim, Gyeong-Moon organization: Department of Neurology (J.-E.L., I.Y., H.-N.S., I.-Y.B., J.-W.C., O.Y.B., G.-M.K., W.-K.S.), Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea – sequence: 13 givenname: Woo-Keun surname: Seo fullname: Seo, Woo-Keun organization: Department of Digital Health, SAIHST, Sungkyunkwan University, Seoul, Republic of Korea (W.-K.S.) |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31092169$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkF9PwjAUxRuDkT_6DYzpoy_DtutG97jAFCJKIuDrUrpbnWwtrhvEb-9ATXz63ZOcnJNz-6hjrAGErikZUhrSu-XqZfGYxNO4lWJIGGchPUM9GjDu8ZCJzr-7i_rOfRBCmC-CC9T1KYkYDaMeOiR7WTSyzq3BVuNJrnXjjmIOJ7zaoikBP4F0TQUlmNrh3OBYNTXgmVPvUOYKL-vKbgGvXW7ecGKUzaDyJnAiHluzb1OOFbLAz1AfbLW9ROdaFg6ufjlA6_tkNZ5688XDbBzPPcVDQT3GFMlEQHUkMq21IioCHraz9CYcyU0kI86FZBoIzxgPgCk_45n2_ZGKeBYwNkC3P7m7yn424Oq0zJ2CopAGbONSxnwqeBgJ0lpvfq3NpoQs3VV5Kauv9O9Z7BvJmHCt |
| CitedBy_id | crossref_primary_10_51537_chaos_1605529 crossref_primary_10_3390_jcm12113755 crossref_primary_10_1007_s42058_023_00129_6 crossref_primary_10_1007_s00330_023_09622_z crossref_primary_10_3390_brainsci13111512 crossref_primary_10_1002_ird3_105 crossref_primary_10_3390_jcm11144008 crossref_primary_10_1007_s13369_022_07536_4 crossref_primary_10_1016_j_clinimag_2021_09_015 crossref_primary_10_1002_prca_201900040 crossref_primary_10_1053_j_sult_2022_02_004 crossref_primary_10_1111_1754_9485_13193 crossref_primary_10_3389_fneur_2025_1518477 crossref_primary_10_1016_j_jneumeth_2021_109260 crossref_primary_10_3389_fneur_2022_907151 crossref_primary_10_1007_s12204_021_2273_9 crossref_primary_10_1016_j_neucom_2022_07_005 crossref_primary_10_3389_fneur_2023_1203241 crossref_primary_10_1016_j_jstrokecerebrovasdis_2024_107857 crossref_primary_10_3389_fmedt_2025_1491197 crossref_primary_10_1002_ana_26435 crossref_primary_10_1038_s41598_021_91467_x crossref_primary_10_3390_jcm9061977 crossref_primary_10_3389_fneur_2022_843871 crossref_primary_10_1161_STROKEAHA_119_028101 crossref_primary_10_1016_j_jns_2023_122799 crossref_primary_10_3389_fnins_2023_1263693 crossref_primary_10_1016_j_nic_2020_07_001 crossref_primary_10_3390_diagnostics11091621 crossref_primary_10_1007_s40747_025_01861_5 crossref_primary_10_1038_s41598_025_91032_w crossref_primary_10_3389_fneur_2021_652757 crossref_primary_10_1007_s13311_023_01358_4 crossref_primary_10_1007_s00234_024_03294_2 crossref_primary_10_1007_s00330_022_08633_6 crossref_primary_10_3390_diagnostics10100803 crossref_primary_10_1016_j_compbiomed_2023_107471 crossref_primary_10_4103_jmss_jmss_37_24 crossref_primary_10_1038_s41598_022_06021_0 crossref_primary_10_3389_fneur_2021_692490 crossref_primary_10_1007_s10278_024_01099_6 crossref_primary_10_1109_ACCESS_2022_3204048 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1161/STROKEAHA.118.024261 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| 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: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1524-4628 |
| ExternalDocumentID | 31092169 |
| Genre | Clinical Trial Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | --- .3C .55 .GJ .XZ .Z2 01R 0R~ 123 1J1 2WC 3O- 40H 4Q1 4Q2 4Q3 53G 5RE 5VS 6PF 71W 77Y 7O~ A9M AAAAV AAAXR AAGIX AAHPQ AAIQE AAJCS AAMOA AAMTA AAQKA AAQQT AARTV AASCR AASOK AAUEB AAXQO AAYEP AAYJJ ABASU ABBUW ABDIG ABJNI ABQRW ABVCZ ABXVJ ABZAD ACCJW ACDDN ACEWG ACGFS ACGOD ACIJW ACILI ACLDA ACWDW ACWRI ACXJB ACXNZ ADBBV ADFPA ADGGA ADHPY ADNKB AE3 AE6 AEBDS AEETU AENEX AFDTB AFEXH AFFNX AFSOK AFUWQ AGINI AHMBA AHOMT AHQNM AHRYX AHVBC AIJEX AINUH AJCLO AJIOK AJNWD AJNYG AJZMW AKCTQ AKULP ALKUP ALMA_UNASSIGNED_HOLDINGS ALMTX AMJPA AMKUR AMNEI AOHHW AWKKM AYCSE BAWUL BCGUY BOYCO BQLVK BS7 C45 CGR CS3 CUY CVF DIK DIWNM DU5 DUNZO E.X E3Z EBS ECM EEVPB EIF EJD ERAAH EX3 F2K F2L F2M F2N F5P FCALG FL- FW0 GNXGY GQDEL GX1 H0~ H13 HLJTE HZ~ IKREB IKYAY IN~ IPNFZ J5H JF9 JG8 JK3 JK8 K8S KD2 KMI KQ8 L-C L7B M18 N4W N9A NPM N~7 N~B N~M O9- OAG OAH OB3 OCUKA ODA ODMTH OGROG OHYEH OJAPA OK1 OL1 OLG OLH OLU OLV OLW OLY OLZ OPUJH ORVUJ OUVQU OVD OVDNE OVIDH OVLEI OVOZU OWBYB OWU OWV OWW OWX OWY OWZ OXXIT P-K P2P PQQKQ R58 RAH RHF RIG RLZ S4R S4S T8P TEORI TSPGW V2I VVN W3M W8F WH7 WOQ WOW X3V X3W X7M XXN XYM YCJ YFH YHZ YQJ YYP ZB8 ZGI ZZMQN 7X8 AAFWJ ABPXF ABXYN ABZZY ACDOF ACZKN ADGHP ADKSD ADSXY AFBFQ AFMBP AFNMH AHQVU AOQMC |
| ID | FETCH-LOGICAL-c4681-22c0d851f98dfffc0c9e46524fb67ab9a9448a2fe04d245e2c3d4df337c94d522 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 45 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000470074200042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1524-4628 |
| IngestDate | Sat Sep 27 18:37:37 EDT 2025 Wed Feb 19 02:31:07 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Keywords | deep learning diffusion cerebral infarction neurologist ischemia |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4681-22c0d851f98dfffc0c9e46524fb67ab9a9448a2fe04d245e2c3d4df337c94d522 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| OpenAccessLink | https://www.ahajournals.org/doi/pdf/10.1161/STROKEAHA.118.024261 |
| PMID | 31092169 |
| PQID | 2231846980 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2231846980 pubmed_primary_31092169 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-June |
| PublicationDateYYYYMMDD | 2019-06-01 |
| PublicationDate_xml | – month: 06 year: 2019 text: 2019-June |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Stroke (1970) |
| PublicationTitleAlternate | Stroke |
| PublicationYear | 2019 |
| SSID | ssj0002385 |
| Score | 2.5129955 |
| Snippet | Background and Purpose- Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 1444 |
| SubjectTerms | Aged Cerebral Infarction - diagnostic imaging Diffusion Magnetic Resonance Imaging Female Humans Male Middle Aged Neural Networks, Computer Registries Software Stroke - diagnostic imaging |
| Title | Evaluation of Diffusion Lesion Volume Measurements in Acute Ischemic Stroke Using Encoder-Decoder Convolutional Network |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/31092169 https://www.proquest.com/docview/2231846980 |
| Volume | 50 |
| WOSCitedRecordID | wos000470074200042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JS8NAFB7UinhxX-rGCF6jWSbLnCS0KRXbWGyV3kIyCxQhqU1b_75vJqk9CYKXDIEJDG9e5n1vme8hdJdZTuBmzDdSloKDAl6QkaUubIgjOAOTDxhZs-v3_DgOxmM6qANuZV1WuToT9UHNC6Zi5A9gxsAZ8WhgPk4_DdU1SmVX6xYam6jhAJRRWu2P12zhYI5czZdqE0PdwayvzgHIeRiOXl-eo7Abwmtwrw2V9TvI1Mams__fZR6gvRpm4rDSi0O0IfIjtNOvE-nH6Cv6YfnGhcTtiZQLFTfDPaGHd31o4f46gljiSY5DtpgL_AQesaqpx8P5rPgQWJcd4ChX1-NnRlvoEbeKfFnrNawkrsrNT9BbJxq1ukbdg8FgxAssw7aZyQGVSRpwKSUzGRXEA4HKzPPTjKYU_LvUlsIk3CausJnDCZeO4zNKOIC7U7SVF7k4R5i6juJ-h3mmJD4nmcsD6govpQC7uGs10e1KpAnouEpcpLkoFmWyFmoTnVX7kkwrMo5EMZvalkcv_vD1JdoFvEOrSq8r1JDwh4trtM2W80k5u9HKA8940P8GiMLO6Q |
| linkProvider | ProQuest |
| 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=Evaluation+of+Diffusion+Lesion+Volume+Measurements+in+Acute+Ischemic+Stroke+Using+Encoder-Decoder+Convolutional+Network&rft.jtitle=Stroke+%281970%29&rft.au=Kim%2C+Yoon-Chul&rft.au=Lee%2C+Ji-Eun&rft.au=Yu%2C+Inwu&rft.au=Song%2C+Ha-Na&rft.date=2019-06-01&rft.eissn=1524-4628&rft.volume=50&rft.issue=6&rft.spage=1444&rft_id=info:doi/10.1161%2FSTROKEAHA.118.024261&rft_id=info%3Apmid%2F31092169&rft_id=info%3Apmid%2F31092169&rft.externalDocID=31092169 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-4628&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-4628&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-4628&client=summon |