Radiation hematologic toxicity prediction in rectal cancer: a comparative radiomics-based study on CT image and dose map

Acute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough prediction value for detecting hematologic toxicity (HT) is still unknown. In this study, the pre-treatment CT images and the in-treatment dose map...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in oncology Vol. 15; p. 1516855
Main Authors: Liu, Yingpeng, Guo, Liping, Wang, Yi, Xu, Qingtao, Zhang, Jingfeng, Meng, Xianyun
Format: Journal Article
Language:English
Published: Switzerland Frontiers Media S.A 04.03.2025
Subjects:
ISSN:2234-943X, 2234-943X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Acute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough prediction value for detecting hematologic toxicity (HT) is still unknown. In this study, the pre-treatment CT images and the in-treatment dose map were collected from a discovery dataset of 299 patients and a validation dataset of 65 patients from another center. Then, the radiomic features of the clinical target volume (CTV) in the radiotherapy were extracted, and the least absolute shrinkage and selection operator (LASSO) algorithm was used for feature dimension deduction; three classifiers, that is, support vector machine (SVM) (rbf kernel), random forest, and CatBoost, were used to construct the HT classification model in rectal cancer patients. The model performance was evaluated by both the internal 20% dataset and the external multicenter dataset. The results revealed that CatBoost achieved the best model performance in almost all tasks and that CT images performed similarly with the dose map, although their combination model performed lower. In addition, gender, age, and some radiomic features from the decomposed image space were the most representative features for HT prediction. Our study can confirm that the HT occurrence in locally advanced rectal cancer (LARC) patients was multifactorial, and combining effective features together can classify the high-risk patients with HT, thus timely preventing or detecting HT to improve the subsequent outcome.
AbstractList Acute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough prediction value for detecting hematologic toxicity (HT) is still unknown. In this study, the pre-treatment CT images and the in-treatment dose map were collected from a discovery dataset of 299 patients and a validation dataset of 65 patients from another center. Then, the radiomic features of the clinical target volume (CTV) in the radiotherapy were extracted, and the least absolute shrinkage and selection operator (LASSO) algorithm was used for feature dimension deduction; three classifiers, that is, support vector machine (SVM) (rbf kernel), random forest, and CatBoost, were used to construct the HT classification model in rectal cancer patients. The model performance was evaluated by both the internal 20% dataset and the external multicenter dataset. The results revealed that CatBoost achieved the best model performance in almost all tasks and that CT images performed similarly with the dose map, although their combination model performed lower. In addition, gender, age, and some radiomic features from the decomposed image space were the most representative features for HT prediction. Our study can confirm that the HT occurrence in locally advanced rectal cancer (LARC) patients was multifactorial, and combining effective features together can classify the high-risk patients with HT, thus timely preventing or detecting HT to improve the subsequent outcome.
Acute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough prediction value for detecting hematologic toxicity (HT) is still unknown.Background and objectivesAcute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough prediction value for detecting hematologic toxicity (HT) is still unknown.In this study, the pre-treatment CT images and the in-treatment dose map were collected from a discovery dataset of 299 patients and a validation dataset of 65 patients from another center. Then, the radiomic features of the clinical target volume (CTV) in the radiotherapy were extracted, and the least absolute shrinkage and selection operator (LASSO) algorithm was used for feature dimension deduction; three classifiers, that is, support vector machine (SVM) (rbf kernel), random forest, and CatBoost, were used to construct the HT classification model in rectal cancer patients. The model performance was evaluated by both the internal 20% dataset and the external multicenter dataset.MethodsIn this study, the pre-treatment CT images and the in-treatment dose map were collected from a discovery dataset of 299 patients and a validation dataset of 65 patients from another center. Then, the radiomic features of the clinical target volume (CTV) in the radiotherapy were extracted, and the least absolute shrinkage and selection operator (LASSO) algorithm was used for feature dimension deduction; three classifiers, that is, support vector machine (SVM) (rbf kernel), random forest, and CatBoost, were used to construct the HT classification model in rectal cancer patients. The model performance was evaluated by both the internal 20% dataset and the external multicenter dataset.The results revealed that CatBoost achieved the best model performance in almost all tasks and that CT images performed similarly with the dose map, although their combination model performed lower. In addition, gender, age, and some radiomic features from the decomposed image space were the most representative features for HT prediction.ResultsThe results revealed that CatBoost achieved the best model performance in almost all tasks and that CT images performed similarly with the dose map, although their combination model performed lower. In addition, gender, age, and some radiomic features from the decomposed image space were the most representative features for HT prediction.Our study can confirm that the HT occurrence in locally advanced rectal cancer (LARC) patients was multifactorial, and combining effective features together can classify the high-risk patients with HT, thus timely preventing or detecting HT to improve the subsequent outcome.ConclusionOur study can confirm that the HT occurrence in locally advanced rectal cancer (LARC) patients was multifactorial, and combining effective features together can classify the high-risk patients with HT, thus timely preventing or detecting HT to improve the subsequent outcome.
Background and objectivesAcute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough prediction value for detecting hematologic toxicity (HT) is still unknown.MethodsIn this study, the pre-treatment CT images and the in-treatment dose map were collected from a discovery dataset of 299 patients and a validation dataset of 65 patients from another center. Then, the radiomic features of the clinical target volume (CTV) in the radiotherapy were extracted, and the least absolute shrinkage and selection operator (LASSO) algorithm was used for feature dimension deduction; three classifiers, that is, support vector machine (SVM) (rbf kernel), random forest, and CatBoost, were used to construct the HT classification model in rectal cancer patients. The model performance was evaluated by both the internal 20% dataset and the external multicenter dataset.ResultsThe results revealed that CatBoost achieved the best model performance in almost all tasks and that CT images performed similarly with the dose map, although their combination model performed lower. In addition, gender, age, and some radiomic features from the decomposed image space were the most representative features for HT prediction.ConclusionOur study can confirm that the HT occurrence in locally advanced rectal cancer (LARC) patients was multifactorial, and combining effective features together can classify the high-risk patients with HT, thus timely preventing or detecting HT to improve the subsequent outcome.
Author Wang, Yi
Liu, Yingpeng
Meng, Xianyun
Xu, Qingtao
Guo, Liping
Zhang, Jingfeng
AuthorAffiliation 2 Department of Radiotherapy and Chemotherapy, Ningbo No. 2 Hospital , Ningbo , China
3 Cancer Radiochemotherapy Center, First Affiliated Hospital of Ningbo University , Ningbo , China
1 Department of Radiology, Ningbo No. 2 Hospital , Ningbo , China
AuthorAffiliation_xml – name: 1 Department of Radiology, Ningbo No. 2 Hospital , Ningbo , China
– name: 2 Department of Radiotherapy and Chemotherapy, Ningbo No. 2 Hospital , Ningbo , China
– name: 3 Cancer Radiochemotherapy Center, First Affiliated Hospital of Ningbo University , Ningbo , China
Author_xml – sequence: 1
  givenname: Yingpeng
  surname: Liu
  fullname: Liu, Yingpeng
– sequence: 2
  givenname: Liping
  surname: Guo
  fullname: Guo, Liping
– sequence: 3
  givenname: Yi
  surname: Wang
  fullname: Wang, Yi
– sequence: 4
  givenname: Qingtao
  surname: Xu
  fullname: Xu, Qingtao
– sequence: 5
  givenname: Jingfeng
  surname: Zhang
  fullname: Zhang, Jingfeng
– sequence: 6
  givenname: Xianyun
  surname: Meng
  fullname: Meng, Xianyun
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40104506$$D View this record in MEDLINE/PubMed
BookMark eNpVkkFr3DAQhUVJadJtfkAvRcdediNZki33UsqStoFAoKTQmxiPxxsF23Ilb8j--2qz25DoMkLz5nsDeu_ZyRhGYuyjFCulbH3RhRFXhSjMShpZWmPesLOiUHpZa_Xn5MX9lJ2ndC_yKY2QQr1jpzpXbUR5xh5_Qeth9mHkdzTAHPqw8cjn8OjRzzs-RWo9PvX9yCPhDD1HGJHiFw4cwzBBzPMPxGMmhcFjWjaQqOVp3rY7ngfXt9wPsCEOY8vbkIgPMH1gbzvoE50f64L9_n55u_65vL75cbX-dr1EXYh5qUwLaKXtmk422FQSOzKNLUukoqnaihBEUelOQl2rsiiqUlhAJCHAaBCoFuzqwG0D3Lsp5k3izgXw7ukhxI2DOHvsyRlV26rpdAYZbcramqoqDWqQlVWoTWZ9PbCmbTNQizTOEfpX0Ned0d-5TXhwUtZSWV1lwucjIYa_W0qzG3xC6nsYKWyTU9nKKiPyDgv26aXZs8v_v8sCeRBgDClF6p4lUrh9RNw-Im4fEXeMiPoHReOwfA
Cites_doi 10.1186/s13014-015-0454-0
10.3389/fonc.2021.646211
10.1016/j.acra.2024.05.015
10.1016/j.acra.2022.02.007
10.1007/s00330-019-06601-1
10.1016/bs.acr.2022.03.007
10.21873/anticanres.14966
10.1093/jrr/rrad069
10.1148/radiol.222998
10.18632/oncotarget.21646
10.21037/qims-20-734
10.1016/j.radonc.2016.07.017
10.1002/mp.16308
10.1097/JS9.0000000000001239
10.3389/fonc.2024.1365897
ContentType Journal Article
Copyright Copyright © 2025 Liu, Guo, Wang, Xu, Zhang and Meng.
Copyright © 2025 Liu, Guo, Wang, Xu, Zhang and Meng 2025 Liu, Guo, Wang, Xu, Zhang and Meng
Copyright_xml – notice: Copyright © 2025 Liu, Guo, Wang, Xu, Zhang and Meng.
– notice: Copyright © 2025 Liu, Guo, Wang, Xu, Zhang and Meng 2025 Liu, Guo, Wang, Xu, Zhang and Meng
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fonc.2025.1516855
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
Directory of Open Access Journals (DOAJ)
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2234-943X
ExternalDocumentID oai_doaj_org_article_53987bf493654569857765c4a1783c45
PMC11913847
40104506
10_3389_fonc_2025_1516855
Genre Journal Article
GroupedDBID 53G
5VS
9T4
AAFWJ
AAKDD
AAYXX
ACGFO
ACGFS
ADBBV
ADRAZ
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
BCNDV
CITATION
DIK
EBS
EJD
EMOBN
GROUPED_DOAJ
GX1
HYE
KQ8
M~E
OK1
PGMZT
RNS
RPM
ACXDI
IPNFZ
M48
NPM
RIG
7X8
5PM
ID FETCH-LOGICAL-c420t-35dac818fbf1bcb71cfe5b866ce2b7d7eca0274f1a9936227608acce00a54a0c3
IEDL.DBID DOA
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001446385200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2234-943X
IngestDate Fri Oct 03 12:33:01 EDT 2025
Thu Aug 21 18:39:21 EDT 2025
Thu Sep 04 18:43:27 EDT 2025
Fri Mar 21 01:25:59 EDT 2025
Sat Nov 29 08:08:46 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords radiomics
radiation hematologic toxicity
dose map
CatBoost
rectal cancer
Language English
License Copyright © 2025 Liu, Guo, Wang, Xu, Zhang and Meng.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c420t-35dac818fbf1bcb71cfe5b866ce2b7d7eca0274f1a9936227608acce00a54a0c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Edited by: Xiaodong Wu, The University of Iowa, United States
Reviewed by: Corrado Spatola, University of Catania, Italy
These authors have contributed equally to this work
Liviu Bilteanu, Carol Davila University of Medicine and Pharmacy, Romania
OpenAccessLink https://doaj.org/article/53987bf493654569857765c4a1783c45
PMID 40104506
PQID 3178835049
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_53987bf493654569857765c4a1783c45
pubmedcentral_primary_oai_pubmedcentral_nih_gov_11913847
proquest_miscellaneous_3178835049
pubmed_primary_40104506
crossref_primary_10_3389_fonc_2025_1516855
PublicationCentury 2000
PublicationDate 2025-03-04
PublicationDateYYYYMMDD 2025-03-04
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-03-04
  day: 04
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in oncology
PublicationTitleAlternate Front Oncol
PublicationYear 2025
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Yazbeck (B3) 2022; 155
Evrimler (B8) 2022; 29
Amudala Puchakayala (B7) 2023; 307
Wan (B5) 2015; 10
Cui (B14) 2020; 30
Li (B4) 2017; 8
Caravatta (B15) 2021; 41
Liu (B6) 2021; 11
Abbaspour (B12) 2024; 110
Li (B13) 2024; 31
Takeda (B2) 2023; 64
Yue (B9) 2023; 50
Huang (B1) 2021; 11
Yue (B11) 2024; 14
Valentini (B10) 2016; 120
References_xml – volume: 10
  start-page: 162
  year: 2015
  ident: B5
  article-title: Can dosimetric parameters predict acute hematologic toxicity in rectal cancer patients treated with intensity-modulated pelvic radiotherapy
  publication-title: Radiat Oncol
  doi: 10.1186/s13014-015-0454-0
– volume: 11
  year: 2021
  ident: B1
  article-title: Effect of pelvic bone marrow sparing intensity modulated radiation therapy on acute hematologic toxicity in rectal cancer patients undergoing chemo-radiotherapy
  publication-title: Front Oncol
  doi: 10.3389/fonc.2021.646211
– volume: 31
  year: 2024
  ident: B13
  article-title: Development and validation of a nomogram based on DCE-MRI radiomics for predicting hypoxia-inducible factor 1alpha expression in locally advanced rectal cancer
  publication-title: Acad Radiol
  doi: 10.1016/j.acra.2024.05.015
– volume: 29
  year: 2022
  ident: B8
  article-title: Bladder urothelial carcinoma: machine learning-based computed tomography radiomics for prediction of histological variant
  publication-title: Acad Radiol
  doi: 10.1016/j.acra.2022.02.007
– volume: 30
  year: 2020
  ident: B14
  article-title: Predicting the ISUP grade of clear cell renal cell carcinoma with multiparametric MR and multiphase CT radiomics
  publication-title: Eur Radiol
  doi: 10.1007/s00330-019-06601-1
– volume: 155
  start-page: 1
  year: 2022
  ident: B3
  article-title: An overview of chemotoxicity and radiation toxicity in cancer therapy
  publication-title: Adv Cancer Res
  doi: 10.1016/bs.acr.2022.03.007
– volume: 41
  year: 2021
  ident: B15
  article-title: A. Gastrointestinal study group of, treatment volume, dose prescription and delivery techniques for dose-intensification in rectal cancer: A national survey
  publication-title: Anticancer Res
  doi: 10.21873/anticanres.14966
– volume: 64
  year: 2023
  ident: B2
  article-title: Acute hematologic toxicity of radiation therapy - a comprehensive analysis and predictive nomogram
  publication-title: J Radiat Res
  doi: 10.1093/jrr/rrad069
– volume: 307
  year: 2023
  ident: B7
  article-title: Radiomics for improved detection of chronic obstructive pulmonary disease in low-dose and standard-dose chest CT scans
  publication-title: Radiology
  doi: 10.1148/radiol.222998
– volume: 8
  year: 2017
  ident: B4
  article-title: Association between dose-volume parameters and acute bone marrow suppression in rectal cancer patients treated with concurrent chemoradiotherapy
  publication-title: Oncotarget
  doi: 10.18632/oncotarget.21646
– volume: 11
  year: 2021
  ident: B6
  article-title: Identifying the histologic subtypes of non-small cell lung cancer with computed tomography imaging: a comparative study of capsule net, convolutional neural network, and radiomics
  publication-title: Quant Imaging Med Surg
  doi: 10.21037/qims-20-734
– volume: 120
  start-page: 195
  year: 2016
  ident: B10
  article-title: International consensus guidelines on Clinical Target Volume delineation in rectal cancer
  publication-title: Radiother Oncol
  doi: 10.1016/j.radonc.2016.07.017
– volume: 50
  start-page: 4993
  year: 2023
  ident: B9
  article-title: Radiation hematologic toxicity prediction for locally advanced rectal cancer using dosimetric and radiomics features
  publication-title: Med Phys
  doi: 10.1002/mp.16308
– volume: 110
  year: 2024
  ident: B12
  article-title: Application of radiomics for preoperative prediction of lymph node metastasis in colorectal cancer: a systematic review and meta-analysis
  publication-title: Int J Surg
  doi: 10.1097/JS9.0000000000001239
– volume: 14
  year: 2024
  ident: B11
  article-title: Acute hematologic toxicity prediction using dosimetric and radiomics features in patients with cervical cancer: does the treatment regimen matter
  publication-title: Front Oncol
  doi: 10.3389/fonc.2024.1365897
SSID ssj0000650103
Score 2.370997
Snippet Acute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the dose map has enough...
Background and objectivesAcute radiation hematologic toxicity may disturb the radiotherapy plan and thus decrease the treatment outcome. However, whether the...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
StartPage 1516855
SubjectTerms CatBoost
dose map
Oncology
radiation hematologic toxicity
radiomics
rectal cancer
Title Radiation hematologic toxicity prediction in rectal cancer: a comparative radiomics-based study on CT image and dose map
URI https://www.ncbi.nlm.nih.gov/pubmed/40104506
https://www.proquest.com/docview/3178835049
https://pubmed.ncbi.nlm.nih.gov/PMC11913847
https://doaj.org/article/53987bf493654569857765c4a1783c45
Volume 15
WOSCitedRecordID wos001446385200001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2234-943X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000650103
  issn: 2234-943X
  databaseCode: DOA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2234-943X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000650103
  issn: 2234-943X
  databaseCode: M~E
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELWgQogLonw1QCsjcUIKTeLPcIOqFZdWCBVpb5EztsUemqyyKSoXfjszTlp2UaVeuOSQOI7lN5mZJ9tvGHuHUcyDrkVeQRVzGQvIHQSb-9bpoILwGmQqNmHOzuxiUX_dKPVFe8ImeeBp4g6VQFbcRlkLTcG-tsoYrUC60lgBMqmXYtazQaYmH6yogMG0jIksrD6MfUeKhZX6gDFOWzratxGIkl7_bUnmv3slN4LPyRP2eM4a-adptLvsXuiesoen87r4M3b1jSQGaI55EmGdPBof-ytsMP7iq4GapufLjpOTw96AAB8-csfhrwQ4H7AnOqm8zinAeZ70Zzm-eHTOlxfofbjrPPf9OvALt3rOvp8cnx99yeeaCjnIqhhzobwDDNKxjWULrSkhBtVaTYXBWuNNAEdENZYOExddVUYX1gGEonBKugLEC7bT9V3YY7wSIoKPJWiDNCtE64PRobKAvShwdcbeX09ws5qkMxqkHIRGQ2g0hEYzo5GxzwTBTUNSvU430Baa2Raau2whY2-vAWzwL6GlD9eF_nLdYJZkMddEOpSxlxOgN5-SRElVoTNmt6DeGsv2k275IylxkzqewPj-6n-M_jV7RDOSNrjJN2xnHC7DPnsAP8flejhg983CHiQrx-vp7-M_bGcCvw
linkProvider Directory of Open Access Journals
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=Radiation+hematologic+toxicity+prediction+in+rectal+cancer%3A+a+comparative+radiomics-based+study+on+CT+image+and+dose+map&rft.jtitle=Frontiers+in+oncology&rft.au=Liu%2C+Yingpeng&rft.au=Guo%2C+Liping&rft.au=Wang%2C+Yi&rft.au=Xu%2C+Qingtao&rft.date=2025-03-04&rft.pub=Frontiers+Media+S.A&rft.eissn=2234-943X&rft.volume=15&rft_id=info:doi/10.3389%2Ffonc.2025.1516855&rft.externalDocID=PMC11913847
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2234-943X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2234-943X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2234-943X&client=summon