Radiogenomic association of deep MR imaging features with genomic profiles and clinical characteristics in breast cancer

Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Biomarker research Ročník 11; číslo 1; s. 9 - 11
Hlavní autoři:	Liu, Qian, Hu, Pingzhao
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London BioMed Central 24.01.2023 BioMed Central Ltd Springer Nature B.V BMC
Témata:	Algorithms Biomedical and Life Sciences Biomedicine Breast cancer Cancer Research Classification Deep learning Denoise autoencoder Disease management Epidermal growth factor ErbB-2 protein Estrogen Estrogen receptors Gene expression Genes Genomics Lymph nodes Magnetic resonance imaging Medical imaging Medical imaging equipment Medical research Medicine, Experimental Metastases Metastasis Patients Phenotypes Precision medicine Progesterone Radiogenomic biomarkers Radiogenomics Radiomics RNA Tumors Canada Deep learning Breast cancer Medical imaging Radiogenomics Denoise autoencoder
ISSN:	2050-7771, 2050-7771
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. Methods A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients’ MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients’ mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). Results Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P -value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. Conclusions The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine.
AbstractList	It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors.BACKGROUNDIt has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors.A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients' MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients' mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status).METHODSA denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients' MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients' mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status).Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs.RESULTSThirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs.The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine.CONCLUSIONSThe deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine. Abstract Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. Methods A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients’ MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients’ mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). Results Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. Conclusions The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine. BackgroundIt has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors.MethodsA denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients’ MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients’ mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status).ResultsThirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs.ConclusionsThe deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine. Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. Methods A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients’ MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients’ mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). Results Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P -value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. Conclusions The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine. It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients' MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients' mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine. Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. Methods A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients' MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients' mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). Results Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. Conclusions The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine. Keywords: Radiogenomics, Deep learning, Breast cancer, Medical imaging, Denoise autoencoder It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients' MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients' mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine.
ArticleNumber	9
Audience	Academic
Author	Hu, Pingzhao Liu, Qian
Author_xml	– sequence: 1 givenname: Qian surname: Liu fullname: Liu, Qian organization: Department of Biochemistry and Medical Genetics, University of Manitoba, Department of Computer Science, University of Manitoba, Department of Statistics, University of Manitoba – sequence: 2 givenname: Pingzhao surname: Hu fullname: Hu, Pingzhao email: phu49@uwo.ca organization: Department of Biochemistry and Medical Genetics, University of Manitoba, Department of Computer Science, University of Manitoba, CancerCare Manitoba Research Institute, Department of Biochemistry, Western University
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/36694221$$D View this record in MEDLINE/PubMed
BookMark	eNp9kl9v0zAUxSM0xEbZF-ABWeIFHjJsx42dF6Rp4k-lIaQCz5bjXKeuUrvYzli_PW67snVCcx5iOb9z4nvveVmcOO-gKF4TfEGIqD9EhqualZhWJcZsOi03z4oziqe45JyTkwf70-I8xiXOSwhGSPOiOK3qumGUkrPidq4663twfmU1UjF6bVWy3iFvUAewRt_myK5Ub12PDKg0Bojoj00LdBCtgzd2yKfKdUgP1lmtBqQXKiidINiYrI7IOtQGUDEhrZyG8Kp4btQQ4fzuPSl-ff708-pref39y-zq8rrUNSOpbHXX1g1tO9IK0TQYGqppy7jhGBSjjc6laGF4oynuwGijGK-1Np1oK6BcVJNitvftvFrKdci1hI30ysrdgQ-9VCHfcAAJumPTVmFB6poZwRSrKaEdZ4YzaGuSvT7uvdZju4JOg0tBDUemx1-cXcje38hGcMpolQ3e3RkE_3uEmOTKRg3DoBz4MUrK62baUJ6nOinePkKXfgwutypTeQmcB3xP9SoXYJ3x-b96ayovecWmVYMZy9TFf6j8dJAHmHO1nd-x4P2RIDMJblOvxhjl7Mf8mH3zsCn_unHIWAbEHtDBxxjASG3TLmP5FnaQBMttouU-0TLXLneJlpsspY-kB_cnRdVeFDPsegj3nXtC9RdesgjB
CitedBy_id	crossref_primary_10_1002_advs_202503925 crossref_primary_10_1186_s12880_024_01255_y crossref_primary_10_2217_pme_2022_0093 crossref_primary_10_1177_03008916251356446 crossref_primary_10_1007_s12530_024_09619_z crossref_primary_10_1016_j_heliyon_2024_e31816 crossref_primary_10_1016_j_clbc_2025_08_014 crossref_primary_10_1186_s12967_025_06641_w crossref_primary_10_1186_s12885_025_14247_0 crossref_primary_10_3389_fgene_2024_1383284
Cites_doi	10.1038/nature08460 10.1056/NEJM198510313131802 10.48550/arXiv.1701.05936 10.1083/jcb.200508196 10.1186/s13058-015-0514-2 10.1038/s41598-017-05848-2 10.1186/S13059-016-1028-7 10.1093/bioinformatics/19.2.185 10.2307/2346101 10.1016/j.molonc.2008.04.001 10.1007/s10278-013-9622-7 10.1201/9780203745502 10.1200/JCO.2008.18.1370 10.1145/1390156.1390294 10.1093/hmg/5.5.659 10.1007/s11306-009-0178-y 10.1038/srep17787 10.1007/s10479-011-0841-3 10.1038/nature11412 10.1016/j.ejso.2006.06.009 10.3390/cancers12051076 10.1038/s41467-018-03411-9 10.1093/bioinformatics/btv693 10.1042/bj3360213 10.1002/cncr.29791 10.1117/1.JMI.2.4.041007 10.18632/oncotarget.5500 10.1038/s41467-020-18703-2 10.1155/2014/986048 10.1038/s41588-018-0132-x
ContentType	Journal Article
Copyright	The Author(s) 2023 2023. The Author(s). COPYRIGHT 2023 BioMed Central Ltd. 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2023 – notice: 2023. The Author(s). – notice: COPYRIGHT 2023 BioMed Central Ltd. – notice: 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION NPM ISR 8FE 8FH ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO GNUQQ HCIFZ LK8 M7P PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI 7X8 5PM DOA
DOI	10.1186/s40364-023-00455-y
DatabaseName	Springer Nature OA Free Journals CrossRef PubMed Gale In Context: Science ProQuest SciTech Collection ProQuest Natural Science Collection ProQuest Central (Alumni Edition) ProQuest Central UK/Ireland ProQuest Central Essentials Biological Science Collection ProQuest Central Natural Science Collection ProQuest One Community College ProQuest Central Korea ProQuest Central Student SciTech Premium ProQuest Biological Science Collection Biological Science Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef PubMed Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Biological Science Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection Biological Science Database ProQuest SciTech Collection ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition Natural Science Collection ProQuest Central Korea Biological Science Collection ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Publicly Available Content Database PubMed
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals - NZ 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: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	2050-7771
EndPage	11
ExternalDocumentID	oai_doaj_org_article_ecd45ba081664f84a46212d74f74eb61 PMC9872423 A734539044 36694221 10_1186_s40364_023_00455_y
Genre	Journal Article
GeographicLocations	Canada
GeographicLocations_xml	– name: Canada
GrantInformation_xml	– fundername: Manitoba Medical Service Foundation funderid: http://dx.doi.org/10.13039/100008795 – fundername: Canada Research Chairs Tier II Program – fundername: CancerCare Manitoba Foundation funderid: http://dx.doi.org/10.13039/100009395 – fundername: ;
GroupedDBID	0R~ 53G 5VS 8FE 8FH AAFWJ AAJSJ AASML ACGFS ADBBV ADRAZ ADUKV AFKRA AFPKN AHBYD AHYZX ALMA_UNASSIGNED_HOLDINGS AMKLP AOIJS ASPBG BAWUL BBNVY BCNDV BENPR BFQNJ BHPHI BMC C6C CCPQU DIK EBLON EBS GROUPED_DOAJ HCIFZ HYE IAO IHR INH INR ISR ITC KQ8 LK8 M48 M7P M~E OK1 PGMZT PHGZM PHGZT PIMPY PQGLB PROAC PUEGO RBZ ROL RPM RSV SOJ AAYXX AFFHD CITATION NPM ABUWG AZQEC DWQXO GNUQQ PKEHL PQEST PQQKQ PQUKI 7X8 5PM
ID	FETCH-LOGICAL-c641t-bcdb692bd1b88990e92c2b47f70ea429c366c8f79c20defcfa476ccfd8b3e2783
IEDL.DBID	BENPR
ISICitedReferencesCount	12
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000920061300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2050-7771
IngestDate	Tue Oct 14 15:12:14 EDT 2025 Tue Nov 04 02:06:35 EST 2025 Thu Oct 02 03:00:59 EDT 2025 Mon Oct 06 16:35:48 EDT 2025 Tue Nov 11 09:53:05 EST 2025 Tue Nov 04 17:24:09 EST 2025 Thu Nov 13 16:15:51 EST 2025 Mon Jul 21 05:56:46 EDT 2025 Tue Nov 18 22:16:05 EST 2025 Sat Nov 29 01:34:22 EST 2025 Sat Sep 06 07:27:45 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	Deep learning Breast cancer Medical imaging Radiogenomics Denoise autoencoder
Language	English
License	2023. The Author(s). Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c641t-bcdb692bd1b88990e92c2b47f70ea429c366c8f79c20defcfa476ccfd8b3e2783
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
OpenAccessLink	https://www.proquest.com/docview/2777780205?pq-origsite=%requestingapplication%
PMID	36694221
PQID	2777780205
PQPubID	2040162
PageCount	11
ParticipantIDs	doaj_primary_oai_doaj_org_article_ecd45ba081664f84a46212d74f74eb61 pubmedcentral_primary_oai_pubmedcentral_nih_gov_9872423 proquest_miscellaneous_2769592702 proquest_journals_2777780205 gale_infotracmisc_A734539044 gale_infotracacademiconefile_A734539044 gale_incontextgauss_ISR_A734539044 pubmed_primary_36694221 crossref_citationtrail_10_1186_s40364_023_00455_y crossref_primary_10_1186_s40364_023_00455_y springer_journals_10_1186_s40364_023_00455_y
PublicationCentury	2000
PublicationDate	2023-01-24
PublicationDateYYYYMMDD	2023-01-24
PublicationDate_xml	– month: 01 year: 2023 text: 2023-01-24 day: 24
PublicationDecade	2020
PublicationPlace	London
PublicationPlace_xml	– name: London – name: England
PublicationTitle	Biomarker research
PublicationTitleAbbrev	Biomark Res
PublicationTitleAlternate	Biomark Res
PublicationYear	2023
Publisher	BioMed Central BioMed Central Ltd Springer Nature B.V BMC
Publisher_xml	– name: BioMed Central – name: BioMed Central Ltd – name: Springer Nature B.V – name: BMC
References	M Fan (455_CR3) 2020; 11 ES Burnside (455_CR4) 2016; 122 M Nair (455_CR33) 2006; 173 B Gyorffy (455_CR37) 2015; 17 M Tan (455_CR39) 2019 455_CR20 455_CR27 E Kolpakova (455_CR31) 2015; 336 AM Hoff (455_CR29) 2015; 6 DA Barbie (455_CR21) 2009 F Chollet (455_CR11) 2016 L Wu (455_CR30) 2018; 50 JS Baxter (455_CR17) 2018 L Cayuela (455_CR23) 2010 RC Seeger (455_CR34) 1985; 313 E Chen (455_CR32) 1996; 5 W Guo (455_CR6) 2015; 2 B Hochberg (455_CR24) 1995 L Wu (455_CR18) 2018 M Davidian (455_CR22) 2017 S Zhao (455_CR14) 2014 B Bm (455_CR13) 2003; 19 455_CR10 M Sugimoto (455_CR38) 2010; 6 455_CR16 B Li (455_CR25) 2016; 17 M Van Goethem (455_CR1) 2006; 32 455_CR35 K Clark (455_CR8) 2013; 26 L Fass (455_CR2) 2008; 2 455_CR28 DMA Gendoo (455_CR19) 2016 L Van Der Maaten (455_CR15) 2008; 9 PS Bernard (455_CR36) 2009; 27 Y Zhu (455_CR5) 2015; 5 DC Koboldt (455_CR9) 2012; 490 YW Jin (455_CR26) 2020; 12 Z Li (455_CR7) 2017; 7 S Ruder (455_CR12) 2016
References_xml	– year: 2009 ident: 455_CR21 publication-title: Nature doi: 10.1038/nature08460 – volume: 313 start-page: 1111 year: 1985 ident: 455_CR34 publication-title: N Engl J Med doi: 10.1056/NEJM198510313131802 – ident: 455_CR16 doi: 10.48550/arXiv.1701.05936 – volume: 173 start-page: 253 year: 2006 ident: 455_CR33 publication-title: J Cell Biol doi: 10.1083/jcb.200508196 – volume: 17 start-page: 1 year: 2015 ident: 455_CR37 publication-title: Breast Cancer Res doi: 10.1186/s13058-015-0514-2 – volume: 7 start-page: 1 year: 2017 ident: 455_CR7 publication-title: Sci Rep doi: 10.1038/s41598-017-05848-2 – volume: 17 start-page: 174 year: 2016 ident: 455_CR25 publication-title: Genome Biol doi: 10.1186/S13059-016-1028-7 – volume: 19 start-page: 185 year: 2003 ident: 455_CR13 publication-title: Bioinformatics doi: 10.1093/bioinformatics/19.2.185 – start-page: 1 volume-title: An overview of gradient descent optimization algorithms year: 2016 ident: 455_CR12 – ident: 455_CR20 – year: 1995 ident: 455_CR24 publication-title: J R Stat Soc doi: 10.2307/2346101 – volume: 2 start-page: 115 year: 2008 ident: 455_CR2 publication-title: Mol Oncol doi: 10.1016/j.molonc.2008.04.001 – volume: 26 start-page: 1045 year: 2013 ident: 455_CR8 publication-title: J Digit Imaging doi: 10.1007/s10278-013-9622-7 – year: 2017 ident: 455_CR22 publication-title: Nonlinear models for repeated measurement data. doi: 10.1201/9780203745502 – volume: 27 start-page: 1160 year: 2009 ident: 455_CR36 publication-title: J Clin Oncol doi: 10.1200/JCO.2008.18.1370 – ident: 455_CR35 – ident: 455_CR10 doi: 10.1145/1390156.1390294 – volume-title: Modelos lineales mixtos en R year: 2010 ident: 455_CR23 – ident: 455_CR28 – volume: 5 start-page: 659 year: 1996 ident: 455_CR32 publication-title: Hum Mol Genet doi: 10.1093/hmg/5.5.659 – volume: 6 start-page: 78 year: 2010 ident: 455_CR38 publication-title: Metabolomics doi: 10.1007/s11306-009-0178-y – volume: 5 start-page: 17787 year: 2015 ident: 455_CR5 publication-title: Sci Rep doi: 10.1038/srep17787 – volume: 9 start-page: 2579 year: 2008 ident: 455_CR15 publication-title: J Mach Learn Res doi: 10.1007/s10479-011-0841-3 – volume: 490 start-page: 61 year: 2012 ident: 455_CR9 publication-title: Nature doi: 10.1038/nature11412 – volume: 32 start-page: 901 year: 2006 ident: 455_CR1 publication-title: Eur J Surg Oncol doi: 10.1016/j.ejso.2006.06.009 – volume: 12 start-page: 1076 year: 2020 ident: 455_CR26 publication-title: Cancers (Basel) doi: 10.3390/cancers12051076 – start-page: 1 volume-title: Keras Blog year: 2016 ident: 455_CR11 – year: 2018 ident: 455_CR17 publication-title: Nat Commun doi: 10.1038/s41467-018-03411-9 – year: 2016 ident: 455_CR19 publication-title: Bioinformatics doi: 10.1093/bioinformatics/btv693 – volume: 336 start-page: 213 year: 2015 ident: 455_CR31 publication-title: Biochem J doi: 10.1042/bj3360213 – volume: 122 start-page: 748 year: 2016 ident: 455_CR4 publication-title: Cancer doi: 10.1002/cncr.29791 – volume: 2 start-page: 041007 year: 2015 ident: 455_CR6 publication-title: J Med Imaging doi: 10.1117/1.JMI.2.4.041007 – volume: 6 start-page: 36587 year: 2015 ident: 455_CR29 publication-title: Oncotarget doi: 10.18632/oncotarget.5500 – volume: 11 start-page: 1 year: 2020 ident: 455_CR3 publication-title: Nat Commun doi: 10.1038/s41467-020-18703-2 – year: 2014 ident: 455_CR14 publication-title: Biomed Res Int doi: 10.1155/2014/986048 – ident: 455_CR27 – volume-title: Proceedings of the 36th International Conference on Machine Learning, Long Beach, California, PMLR 97 year: 2019 ident: 455_CR39 – year: 2018 ident: 455_CR18 publication-title: Nat Genet doi: 10.1038/s41588-018-0132-x – volume: 50 start-page: 968 year: 2018 ident: 455_CR30 publication-title: Nat Genet doi: 10.1038/s41588-018-0132-x
SSID	ssj0000884119
Score	2.3073375
Snippet	Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow... It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and... Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow... BackgroundIt has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow... Abstract Background It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally...
SourceID	doaj pubmedcentral proquest gale pubmed crossref springer
SourceType	Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	9
SubjectTerms	Algorithms Biomedical and Life Sciences Biomedicine Breast cancer Cancer Research Classification Deep learning Denoise autoencoder Disease management Epidermal growth factor ErbB-2 protein Estrogen Estrogen receptors Gene expression Genes Genomics Lymph nodes Magnetic resonance imaging Medical imaging Medical imaging equipment Medical research Medicine, Experimental Metastases Metastasis Patients Phenotypes Precision medicine Progesterone Radiogenomic biomarkers Radiogenomics Radiomics RNA Tumors
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQBRIXxJvQggxC4gBRE6-fx4Ko4ECFFpB6s_yESDRbbXYr9t_jcZLtpgi4kON6LMXzjT0zm_E3CL1IEEOgmxBwIZZUcV9axmwpGFHEcMfqUOVmE-LkRJ6eqk87rb6gJqynB-4Vdxicp8wa6A_BaZTUUJ5OWy9oFDTYPvGphNpJpvIZLCWtazXekpH8sKPwxa1MLqqEMIaVm4knyoT9vx_LO37pas3klQ-n2R8d30a3hkASH_ULuIOuhfYuutG3ltzcQz_nxjcLYGA9axw2lyDgRcQ-hHP8cY6bs9yjCMeQ6T07DP_K4nHS0M67w6b1eLxBid2U4Rk3LbZQ2L7CDgxoeR99PX735e37cuiyUDpO61VpnbdcEetrK1PyVQVFHLFURFEFk7yVm3HuZBTKkcqH6KKhgjsXvbSzAH06HqC9dtGGRwiLlPsFTyrjk5Bj0dQWAggu6pQJ8yoWqB41rt1AQQ6dMH7onIpIrnuUdEJJZ5T0pkCvtnPOewKOv0q_ASC3kkCenX9IJqUHk9L_MqkCPQcz0ECP0UL9zTez7jr94fNcH4kZZTNVUVqgl4NQXKQ1ODNcZ0iaAGwmkgcTybR_3XR4tDY9nB-dJiI9MoXyrEDPtsMwE2ri2rBYgwxXTMF9wgI97I1zu-6EWdqEJC1FTMx2opjpSNt8z-ziSgqIsQv0ejTwy9f6s-If_w_F76ObJG_QuiT0AO2tluvwBF13F6umWz7NO_wXyVZTNA priority: 102 providerName: Directory of Open Access Journals – databaseName: Springer Standard Collection dbid: RSV link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaggNQLb2igIIOQOIDVxOvY8bEgKjhQoS2g3iw_SySaVJtdxP57PE6yJeUhQY7xWIrn4RnHM98g9CyKGALdKAHrA2GSO2LK0hBRUkk1t2Xh89RsQhweVsfH8sNQFNaN2e7jlWTaqZNZV3yvY3BlRqKPIRCHlGR9GV0B8BLoWzA_-rz5sxLthhWFHCtkfjt14oUSWP-vW_JPPulivuSFS9Pkiw5u_N8qbqLrQ-yJ93tluYUu-eY2utZ3o1zfQd_n2tUtgLae1hbrc7nhNmDn_Rl-P8f1aWprhINPiKAdhh-5eJw0dADvsG4cHosusZ2CQuO6wQZy4ZfYgs4t7qJPB28-vn5LhsYMxHJWLImxznBJjStMFc9ruZfUUsNEELnX0cHZGee2CkJamjsfbNBMcGuDq8zMQ2uPe2iraRu_g7CIx0XvaK5dJLJl0IWBmIOLIh6eeR4yVIyCUnZALYfmGV9VOr1UXPUcVZGjKnFUrTP0YjPnrMfs-Cv1K5D_hhLwttOLdnGiBvNV3jpWGg1dSjgLFdOMR5_vBAuCecOLDD0F7VGAqNFAys6JXnWdenc0V_tixsqZzBnL0POBKLRxDVYPFRCREyCbCeXuhDKavJ0Oj0qqhi2nU1TEp4rRf5mhJ5thmAlpdI1vV0DDZSmhBDFD93ud3qw7yizaLY1LERNtnzBmOtLUXxIguawEhOUZejnq_Pln_ZnxD_6N_CHapslsCkLZLtpaLlb-Ebpqvy3rbvE4bQE_AL9gWGQ priority: 102 providerName: Springer Nature
Title	Radiogenomic association of deep MR imaging features with genomic profiles and clinical characteristics in breast cancer
URI	https://link.springer.com/article/10.1186/s40364-023-00455-y https://www.ncbi.nlm.nih.gov/pubmed/36694221 https://www.proquest.com/docview/2777780205 https://www.proquest.com/docview/2769592702 https://pubmed.ncbi.nlm.nih.gov/PMC9872423 https://doaj.org/article/ecd45ba081664f84a46212d74f74eb61
Volume	11
WOSCitedRecordID	wos000920061300001&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: PRVADU databaseName: Open Access: BioMedCentral Open Access Titles customDbUrl: eissn: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: RBZ dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.biomedcentral.com/search/ providerName: BioMedCentral – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals - NZ customDbUrl: eissn: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: DOA dateStart: 20130101 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: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: AUTh Library subscriptions: ProQuest Central customDbUrl: eissn: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: BENPR dateStart: 20150101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: M7P dateStart: 20150101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: PIMPY dateStart: 20150101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVAVX databaseName: Springer Standard Collection customDbUrl: eissn: 2050-7771 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000884119 issn: 2050-7771 databaseCode: RSV dateStart: 20131201 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/eLvHCXMwpR1db9Mw0GIdSLzw_REYlUFIPEC0xHXs5AltaBN7WFV1gMaT5c8RiSWlaRH99_jcpCVD7IW8JT5LOd-nz-c7hF57EoOj6ymgrYtpwUysskzFPCMFkUxnqU1Cswk-Hufn58WkDbg1bVplpxODoja1hhj5PuH-yb1zk72f_YihaxScrrYtNHbQLlQqIwO0e3g0nkw3URYvQ9QPdLdlcrbfUDh5i72pisGdyeJVzyKFwv1_q-c_7NPV3MkrB6jBLh3f_V-M7qE7rUeKD9YsdB_dsNUDdGvdo3L1EP2aSlPWUMr1stRYbqmJa4eNtTN8OsXlZWh2hJ0NdUIbDOFd3E1q-4I3WFYGd1cxse6XisZlhRVkyC-wBk6cP0Kfj48-ffgYt-0aYs1ouoiVNooVRJlU5X4Xl9iCaKIodzyx0ps9PWJM544XmiTGOu0k5UxrZ3I1stDw4zEaVHVlnyLM_SbSGpJI44F05mSqwBNhPPVbapa4CKUdyYRua5lDS43vIuxpcibWZBaezCKQWawi9HYzZ7au5HEt9CFwwgYSqnCHD_X8QrRCLaw2NFMSepcw6nIqKfOegOHUcWoVSyP0CvhIQJ2NChJ5LuSyacTJ2VQc8BHNRkVCaYTetECu9jho2d6L8CsBtOlB7vUgvSLQ_eGOz0SriBqxZbIIvdwMw0xIrqtsvQQYVmQFXEyM0JM1d2_w9jTz0kw8KrzH972F6Y9U5bdQprzIOTjrEXrXScj2t_698M-ux-I5uk2C7KYxoXtosJgv7Qt0U_9clM18iHb4eT5slcAwxFeGkM078d8mJ6eTr_5tevblN5nkaIU
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwELbKFgQX3o9AAYNAHCBq4jh2ckCohVat2q6qpUi9GcePEokmy2YX2D_Fb8STxy4porce2ON6vNrxPDxje-ZD6IUTMQS6TgLKWJ-mTPtZHGc-j0lKJFNxaIIabIIPh8nxcXq4gn51tTDwrLLzibWj1qWCM_J1wt0nccFN_G78zQfUKLhd7SA0GrXYM_MfLmWr3u5-cPJ9Scj21tH7Hb9FFfAVo-HUz5TOWEoyHWaJSzYCkxJFMsotD4x03llFjKnE8lSRQBurrKScKWV1kkUGcCnc715CqzSiMR2g1c2t4eFocarjbJaGYdpV5yRsvaJw0-e7rdGH8Cn2570dsAYK-Hs7-GM_PPtW88yFbb0Pbt_431bwJrreRtx4ozGRW2jFFLfRlQaDc34H_RxJnZfQqvY0V1gutRWXFmtjxvhghPPTGswJW1P3Qa0wHF_jblKLe15hWWjclZpi1W-FjfMCZ1ABMMUKLG1yF326ELbvoUFRFuYBwtwlyUaTQGpHpGIrwwwiLcbDMIpYYD0UdioiVNurHSBDvoo6Z0uYaNRKOLUStVqJuYdeL-aMm04l51JvguYtKKHLeP1FOTkRrdMSRmkaZxKwWRi1CZWUuUhHc2o5NRkLPfQc9FZAH5ECHiqdyFlVid2PI7HBnX1EaUCph161RLZ0PCjZ1n24lQDZ9CjXepTO0an-cKfXonW0lVgqtYeeLYZhJjweLEw5AxqWxikUXnrofmNNC76dzJy3Io4V3rOz3sL0R4r8S92GPU04JCMeetNZ5PJv_XvhH57PxVN0defoYF_s7w73HqFrpPYboU_oGhpMJzPzGF1W36d5NXnSuh6MPl-0rf4GelfCoQ
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Zb9QwELagHOKF-wgUMAiJB4iaZB07fizHigpYVVtAfbN8lkg0WW2yiP33eJxk25RDQuQxHkvxHPZMPPMNQs-8iMHR9RLQ1sWEUxOrPFcxyzOeSarz1Cah2QSbzYrDQ75_qoo_ZLsPV5JdTQOgNFXtzsK4zsQLutMQuD6L_XkTg0-Sx-vz6AIBNDSI1w--bP6yeBsiacqHapnfTh2dSAG4_9ft-dT5dDZ38swFajiXptf-f0XX0dXeJ8W7nRLdQOdsdRNd6rpUrm-hH3NpyhrAXI9LjeWJPHHtsLF2gT_OcXkc2h1hZwNSaIPhBy8eJvWdwRssK4OHYkysx2DRuKywghz5FmvQxeVt9Hn69tPrd3HfsCHWlKRtrLRRlGfKpKrwcVxieaYzRZhjiZX-4NMTSnXhGNdZYqzTThJGtXamUBMLLT_uoK2qruw9hJkPI63JEmk8kc6dTBX4IpSlPqimiYtQOghN6B7NHJpqfBMhqimo6DgqPEdF4KhYR-jFZs6iw_L4K_Ur0IUNJeBwhxf18kj0Zi2sNiRXErqXUOIKIgn1voBhxDFiFU0j9BQ0SQDSRgWpPEdy1TRi72AudtmE5BOeEBKh5z2Rq_0atOwrIzwnQDYjyu0Rpd8K9Hh4UFjRb0WNyJh_Ch8V5BF6shmGmZBeV9l6BTSU5xxKEyN0t9Pvzbq9zLw9Z34pbKT5I8aMR6ryawAq5wUDdz1CLwf9P_msPzP-_r-RP0aX999MxYe92fsH6EoWLCiNM7KNttrlyj5EF_X3tmyWj8LO8BO_RGQs
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=Radiogenomic+association+of+deep+MR+imaging+features+with+genomic+profiles+and+clinical+characteristics+in+breast+cancer&rft.jtitle=Biomarker+research&rft.au=Liu%2C+Qian&rft.au=Hu%2C+Pingzhao&rft.date=2023-01-24&rft.pub=BioMed+Central+Ltd&rft.issn=2050-7771&rft.eissn=2050-7771&rft.volume=11&rft.issue=1&rft_id=info:doi/10.1186%2Fs40364-023-00455-y&rft.externalDBID=ISR&rft.externalDocID=A734539044
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2050-7771&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2050-7771&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2050-7771&client=summon