Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm
Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic he...
Saved in:
| Published in | PloS one Vol. 19; no. 4; p. e0299267 |
|---|---|
| Main Authors | , , , , , , , , , , , , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Public Library of Science
03.04.2024
Public Library of Science (PLoS) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome.
We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity.
WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes.
This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. |
|---|---|
| AbstractList | Background and objective Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome. Methods We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity. Results WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes. Conclusions This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome. We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity. WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes. This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. Background and objectiveGlioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome.MethodsWe proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity.ResultsWSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes.ConclusionsThis study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome. We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity. WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes. This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome.BACKGROUND AND OBJECTIVEGlioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome.We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity.METHODSWe proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity.WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes.RESULTSWSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes.This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology.CONCLUSIONSThis study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology. |
| Audience | Academic |
| Author | Smith, Kris A. Hu, Leland S. Iavarone, Antonio Leon, Gustavo De Jackson, Pamela R. Nakaji, Peter Zimmerman, Richard S. Ceccarelli, Michele Curtin, Lee Krishna, Chandan Urcuyo, Javier Swanson, Kristin R. Donev, Kliment Mrugała, Maciej M. Tran, Nhan L. Hawkins-Daarud, Andrea Wang, Lujia Baxter, Leslie C. D’Angelo, Fulvio Li, Jing Singleton, Kyle W. Patra, Devi P. Wang, Hairong Bendok, Bernard R. Sereduk, Christopher P. |
| AuthorAffiliation | 10 Department of Radiology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America 9 Department of Cancer Biology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America 7 Department of Neuro-Oncology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America 4 Department of Neurosurgery, Barrow Neurological Institute—St. Joseph’s Hospital and Medical Center, Phoenix, Arizona, United States of America University of Maryland College Park, UNITED STATES 1 H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia, United States of America 2 Institute for Cancer Genetics, Columbia University Medical Center, New York City, New York, United States of America 3 Department of Neurosurgery, Mayo Clinic Arizona, Phoenix, Arizona, United States of America 5 Department of Pathology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America 6 Department of Neuropsychology, Mayo Clinic Arizona, Phoenix, Arizona, United Stat |
| AuthorAffiliation_xml | – name: 3 Department of Neurosurgery, Mayo Clinic Arizona, Phoenix, Arizona, United States of America – name: 10 Department of Radiology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America – name: 5 Department of Pathology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America – name: 8 Department of Electrical Engineering and Information Technology, University of Naples “Federico II”, Naples, Italy – name: 1 H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia, United States of America – name: 7 Department of Neuro-Oncology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America – name: 6 Department of Neuropsychology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America – name: 4 Department of Neurosurgery, Barrow Neurological Institute—St. Joseph’s Hospital and Medical Center, Phoenix, Arizona, United States of America – name: University of Maryland College Park, UNITED STATES – name: 2 Institute for Cancer Genetics, Columbia University Medical Center, New York City, New York, United States of America – name: 9 Department of Cancer Biology, Mayo Clinic Arizona, Phoenix, Arizona, United States of America |
| Author_xml | – sequence: 1 givenname: Lujia surname: Wang fullname: Wang, Lujia – sequence: 2 givenname: Hairong surname: Wang fullname: Wang, Hairong – sequence: 3 givenname: Fulvio orcidid: 0000-0002-4940-4693 surname: D’Angelo fullname: D’Angelo, Fulvio – sequence: 4 givenname: Lee surname: Curtin fullname: Curtin, Lee – sequence: 5 givenname: Christopher P. surname: Sereduk fullname: Sereduk, Christopher P. – sequence: 6 givenname: Gustavo De surname: Leon fullname: Leon, Gustavo De – sequence: 7 givenname: Kyle W. orcidid: 0000-0002-9969-8474 surname: Singleton fullname: Singleton, Kyle W. – sequence: 8 givenname: Javier surname: Urcuyo fullname: Urcuyo, Javier – sequence: 9 givenname: Andrea surname: Hawkins-Daarud fullname: Hawkins-Daarud, Andrea – sequence: 10 givenname: Pamela R. surname: Jackson fullname: Jackson, Pamela R. – sequence: 11 givenname: Chandan surname: Krishna fullname: Krishna, Chandan – sequence: 12 givenname: Richard S. surname: Zimmerman fullname: Zimmerman, Richard S. – sequence: 13 givenname: Devi P. surname: Patra fullname: Patra, Devi P. – sequence: 14 givenname: Bernard R. surname: Bendok fullname: Bendok, Bernard R. – sequence: 15 givenname: Kris A. surname: Smith fullname: Smith, Kris A. – sequence: 16 givenname: Peter orcidid: 0000-0001-6677-2925 surname: Nakaji fullname: Nakaji, Peter – sequence: 17 givenname: Kliment orcidid: 0009-0000-4221-0936 surname: Donev fullname: Donev, Kliment – sequence: 18 givenname: Leslie C. surname: Baxter fullname: Baxter, Leslie C. – sequence: 19 givenname: Maciej M. surname: Mrugała fullname: Mrugała, Maciej M. – sequence: 20 givenname: Michele surname: Ceccarelli fullname: Ceccarelli, Michele – sequence: 21 givenname: Antonio surname: Iavarone fullname: Iavarone, Antonio – sequence: 22 givenname: Kristin R. surname: Swanson fullname: Swanson, Kristin R. – sequence: 23 givenname: Nhan L. surname: Tran fullname: Tran, Nhan L. – sequence: 24 givenname: Leland S. surname: Hu fullname: Hu, Leland S. – sequence: 25 givenname: Jing orcidid: 0000-0001-7028-3681 surname: Li fullname: Li, Jing |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38568950$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNk1uL1DAUx4usuBf9BiIBQfRhxqRp09YXWRYvAyvienkNp7l0sqTJmKSr-zn8wqbOrOyIiPSh7cnv_Gj_nHNcHDjvVFE8JHhJaEOeX_opOLDLTS4vcdl1JWvuFEeko-WClZge3Ho-LI5jvMS4pi1j94pD2tas7Wp8VPz4MIFLRl8bNyDjUoBFmkYfwKJBOZWMQGuVVPDzm0nXyGs0WON7CzH5EVDy3yBItAlKmGi8Q6OSRhin0BRn57uLFQInESAJCRbGCZsPrhQaQaxnzCoIbibBDj6YtB7vF3c12Kge7O4nxefXrz6dvV2cv3-zOjs9X4i6IWkhta57BT2pJWNVVWrSNxWoikHVVlIRgrHUDaUKmgwKLBvaEtl3Upa6Z1TSk2K19UoPl3wTzAjhmnsw_FfBh4FDyAlYxfu6kZUGpWsCFdYCSCW0FpWgmAnoZ9fLrWsz9TkBoeYo7Z50_8SZNR_8FSe463BZsWx4ujME_3VSMfHRRKGsBaf8FDnFlGKCCZvRx1t0gPxtxmmflWLG-WnTtqwkZddkavkXKl9SjUbkqdEm1_canu01ZCap72mAKUa--njx_-z7L_vsk1vsWoFN6-jtlPK4xH3w0e0Qf6d3M64ZeLEFRPAxBqW5MAlmT_41Y3OYfN4NvtsNPu8G3-1Gbq7-aL7x_7PtJ65FGnI |
| CitedBy_id | crossref_primary_10_1007_s11910_024_01402_6 crossref_primary_10_1007_s40747_024_01530_z |
| Cites_doi | 10.1016/j.canlet.2020.02.025 10.1148/radiol.2016161382 10.1109/TSMC.1973.4309314 10.1371/journal.pone.0099057 10.1371/journal.pone.0169292 10.1158/1078-0432.CCR-05-0713 10.1016/j.ejmp.2019.03.014 10.1007/978-3-031-01548-9 10.1093/neuonc/now135 10.1162/neco.2007.19.3.792 10.1007/s00062-014-0289-3 10.1016/j.ccr.2011.11.005 10.1371/journal.pone.0071704 10.1158/0008-5472.CAN-08-3658 10.1097/WCO.0b013e328359b0bc 10.1093/neuonc/nos073 10.1056/NEJMoa043330 10.1038/s41598-019-46296-4 10.1371/journal.pone.0141506 10.1038/nrc3261 10.1371/journal.pone.0108335 10.4161/cbt.7.9.6954 10.1093/bioinformatics/bty831 10.1073/pnas.1114033109 10.1162/neco.2007.19.5.1155 10.1016/j.jns.2003.06.001 10.1101/gad.1890510 10.1093/neuonc/noy033 10.1016/j.ejrad.2019.02.014 10.1016/j.crad.2019.12.008 10.1002/nbm.4792 10.1158/0008-5472.CAN-11-0153 |
| ContentType | Journal Article |
| Copyright | Copyright: © 2024 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. COPYRIGHT 2024 Public Library of Science 2024 Wang et al 2024 Wang et al |
| Copyright_xml | – notice: Copyright: © 2024 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. – notice: COPYRIGHT 2024 Public Library of Science – notice: 2024 Wang et al 2024 Wang et al |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM IOV ISR 7X8 5PM DOA |
| DOI | 10.1371/journal.pone.0299267 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Gale In Context: Opposing Viewpoints Gale In Context: Science MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE 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: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Sciences (General) |
| DocumentTitleAlternate | Quantifying intra-tumoral heterogeneity of glioblastoma through MRI and machine learning |
| EISSN | 1932-6203 |
| ExternalDocumentID | oai_doaj_org_article_b57d4faef51a40fca14cffc4c306cabd PMC10990246 A788621297 38568950 10_1371_journal_pone_0299267 |
| Genre | Journal Article |
| GeographicLocations | United States |
| GeographicLocations_xml | – name: United States |
| GrantInformation_xml | – fundername: NCI NIH HHS grantid: U01 CA250481 – fundername: NCI NIH HHS grantid: U54 CA274504 – fundername: NCI NIH HHS grantid: U01 CA220378 – fundername: ; grantid: NIH U01 CA220378-01 and CA250481 – fundername: ; grantid: NSF DMS-2053170 |
| GroupedDBID | --- 123 29O 2WC 53G 5VS 7RV 7X2 7X7 7XC 88E 8AO 8C1 8CJ 8FE 8FG 8FH 8FI 8FJ A8Z AAFWJ AAUCC AAWOE AAYXX ABDBF ABIVO ABJCF ABUWG ACGFO ACIHN ACIWK ACPRK ACUHS ADBBV AEAQA AENEX AEUYN AFKRA AFPKN AFRAH AHMBA ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS APEBS ARAPS ATCPS BAWUL BBNVY BCNDV BENPR BGLVJ BHPHI BKEYQ BPHCQ BVXVI BWKFM CCPQU CITATION CS3 D1I D1J D1K DIK DU5 E3Z EAP EAS EBD EMOBN ESX EX3 F5P FPL FYUFA GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE IAO IEA IGS IHR IHW INH INR IOV IPY ISE ISR ITC K6- KB. KQ8 L6V LK5 LK8 M0K M1P M48 M7P M7R M7S M~E NAPCQ O5R O5S OK1 OVT P2P P62 PATMY PDBOC PHGZM PHGZT PIMPY PQQKQ PROAC PSQYO PTHSS PV9 PYCSY RNS RPM RZL SV3 TR2 UKHRP WOQ WOW ~02 ~KM ADRAZ CGR CUY CVF ECM EIF IPNFZ NPM PJZUB PPXIY PQGLB RIG BBORY PMFND 7X8 5PM PUEGO |
| ID | FETCH-LOGICAL-c571t-dff5beab15d66442f1b74ae46a484de1100df733ea7f5bc0d7381db9dd2fb63d3 |
| IEDL.DBID | M48 |
| ISSN | 1932-6203 |
| IngestDate | Wed Aug 27 01:27:37 EDT 2025 Thu Aug 21 18:34:49 EDT 2025 Fri Jul 11 10:22:48 EDT 2025 Tue Jun 17 22:16:09 EDT 2025 Tue Jun 10 21:13:40 EDT 2025 Fri Jun 27 06:12:14 EDT 2025 Fri Jun 27 05:59:33 EDT 2025 Thu May 22 21:25:18 EDT 2025 Mon Jul 21 06:08:56 EDT 2025 Tue Jul 01 04:06:54 EDT 2025 Thu Apr 24 23:10:38 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | Copyright: © 2024 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c571t-dff5beab15d66442f1b74ae46a484de1100df733ea7f5bc0d7381db9dd2fb63d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 LSH and JL are joint senior authors. Competing Interests: The authors have declared that no competing interests exist. |
| ORCID | 0000-0001-7028-3681 0000-0002-4940-4693 0000-0002-9969-8474 0000-0001-6677-2925 0009-0000-4221-0936 |
| OpenAccessLink | http://journals.scholarsportal.info/openUrl.xqy?doi=10.1371/journal.pone.0299267 |
| PMID | 38568950 |
| PQID | 3033010166 |
| PQPubID | 23479 |
| PageCount | e0299267 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_b57d4faef51a40fca14cffc4c306cabd pubmedcentral_primary_oai_pubmedcentral_nih_gov_10990246 proquest_miscellaneous_3033010166 gale_infotracmisc_A788621297 gale_infotracacademiconefile_A788621297 gale_incontextgauss_ISR_A788621297 gale_incontextgauss_IOV_A788621297 gale_healthsolutions_A788621297 pubmed_primary_38568950 crossref_citationtrail_10_1371_journal_pone_0299267 crossref_primary_10_1371_journal_pone_0299267 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2024-04-03 |
| PublicationDateYYYYMMDD | 2024-04-03 |
| PublicationDate_xml | – month: 04 year: 2024 text: 2024-04-03 day: 03 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: San Francisco, CA USA |
| PublicationTitle | PloS one |
| PublicationTitleAlternate | PLoS One |
| PublicationYear | 2024 |
| Publisher | Public Library of Science Public Library of Science (PLoS) |
| Publisher_xml | – name: Public Library of Science – name: Public Library of Science (PLoS) |
| References | KR Swanson (pone.0299267.ref004) 2003; 216 M-M Inda (pone.0299267.ref045) 2010; 24 A Marusyk (pone.0299267.ref006) 2012; 12 O. Chapelle (pone.0299267.ref029) 2007; 19 H Cao (pone.0299267.ref038) 2019; 35 A Gupta (pone.0299267.ref042) 2015; 25 M Elfil (pone.0299267.ref051) 2017; 5 M Aghi (pone.0299267.ref041) 2005; 11 A Vamvakas (pone.0299267.ref025) 2019; 60 P Kickingereder (pone.0299267.ref012) 2016; 281 R Bonavia (pone.0299267.ref049) 2011; 71 Y Zhou (pone.0299267.ref036) 2004 H. Linusson (pone.0299267.ref040) 2013 M Belkin (pone.0299267.ref035) 2006; 7 H Chen (pone.0299267.ref013) 2021; 11 C Leistner (pone.0299267.ref037) 2009 W Chu (pone.0299267.ref016) 2005 LS Hu (pone.0299267.ref019) 2017; 19 H Akbari (pone.0299267.ref010) 2018; 20 LS Hu (pone.0299267.ref003) 2020; 477 I Etikan (pone.0299267.ref050) 2017; 5 C Williams (pone.0299267.ref039) 2007 YJ Ryu (pone.0299267.ref026) 2014; 9 X Zhu (pone.0299267.ref014) 2009 W Chu (pone.0299267.ref015) 2007; 19 AL Baldock (pone.0299267.ref005) 2014; 9 P Fiorenzo (pone.0299267.ref047) 2010; 36 CM Bishop (pone.0299267.ref031) 2006 SM Lundberg (pone.0299267.ref033) 2017 LS Hu (pone.0299267.ref002) 2015; 10 O Eidel (pone.0299267.ref028) 2017; 12 D. Koul (pone.0299267.ref020) 2008; 7 RM Haralick (pone.0299267.ref022) 1973 LS Hu (pone.0299267.ref007) 2021; 11 R Stupp (pone.0299267.ref001) 2005; 352 A Shashua (pone.0299267.ref017) ES Tykocinski (pone.0299267.ref011) 2012; 14 R Collobert (pone.0299267.ref034) 2006; 7 MA Lewis (pone.0299267.ref024) 2019; 113 SJ Ahn (pone.0299267.ref032) 2020; 10 N Gaw (pone.0299267.ref021) 2019; 9 J. Platt (pone.0299267.ref030) 1998 M Snuderl (pone.0299267.ref043) 2011; 20 I Ryoo (pone.0299267.ref044) 2013; 8 RA Gatenby (pone.0299267.ref018) 2009; 69 NJ Szerlip (pone.0299267.ref046) 2012; 109 Q-H Kha (pone.0299267.ref008) 2021; 13 HG Feichtinger (pone.0299267.ref023) 2012 LHT Lam (pone.0299267.ref009) 2022; 35 ME Hegi (pone.0299267.ref048) 2012; 25 D Alis (pone.0299267.ref027) 2020; 75 |
| References_xml | – start-page: 594 volume-title: 16th IEEE International Conference on Tools with Artificial Intelligence. year: 2004 ident: pone.0299267.ref036 – volume: 477 start-page: 97 year: 2020 ident: pone.0299267.ref003 article-title: Imaging of intratumoral heterogeneity in high-grade glioma publication-title: Cancer Lett doi: 10.1016/j.canlet.2020.02.025 – volume: 281 start-page: 907 year: 2016 ident: pone.0299267.ref012 article-title: Radiogenomics of glioblastoma: machine learning–based classification of molecular characteristics by using multiparametric and multiregional MR imaging features. publication-title: Radiology doi: 10.1148/radiol.2016161382 – start-page: 610 year: 1973 ident: pone.0299267.ref022 article-title: Textural features for image classification publication-title: IEEE Trans Syst Man Cybern doi: 10.1109/TSMC.1973.4309314 – volume: 9 start-page: e99057 year: 2014 ident: pone.0299267.ref005 article-title: Patient-specific metrics of invasiveness reveal significant prognostic benefit of resection in a predictable subset of gliomas. publication-title: PLoS One doi: 10.1371/journal.pone.0099057 – year: 2005 ident: pone.0299267.ref016 article-title: Gaussian Processes for Ordinal Regression Zoubin Ghahramani publication-title: Journal of Machine Learning Research – volume: 5 start-page: e52 year: 2017 ident: pone.0299267.ref051 article-title: Sampling methods in Clinical Research; an Educational Review publication-title: Emerg (Tehran). – volume: 12 start-page: e0169292 year: 2017 ident: pone.0299267.ref028 article-title: Tumor Infiltration in Enhancing and Non-Enhancing Parts of Glioblastoma: A Correlation with Histopathology. publication-title: PLoS One. doi: 10.1371/journal.pone.0169292 – volume: 11 year: 2021 ident: pone.0299267.ref013 article-title: Deep Learning Radiomics to Predict PTEN Mutation Status From Magnetic Resonance Imaging in Patients With Glioma. publication-title: Front Oncol. – volume: 11 start-page: 8600 year: 2005 ident: pone.0299267.ref041 article-title: Magnetic resonance imaging characteristics predict epidermal growth factor receptor amplification status in glioblastoma publication-title: Clinical Cancer Research doi: 10.1158/1078-0432.CCR-05-0713 – volume: 60 start-page: 188 year: 2019 ident: pone.0299267.ref025 article-title: Imaging biomarker analysis of advanced multiparametric MRI for glioma grading. publication-title: Phys Med doi: 10.1016/j.ejmp.2019.03.014 – volume: 7 year: 2006 ident: pone.0299267.ref034 article-title: Large scale transductive SVMs publication-title: Journal of Machine Learning Research – volume-title: Introduction to Semi-Supervised Learning year: 2009 ident: pone.0299267.ref014 doi: 10.1007/978-3-031-01548-9 – volume: 19 start-page: 128 year: 2017 ident: pone.0299267.ref019 article-title: Radiogenomics to characterize regional genetic heterogeneity in glioblastoma. publication-title: Neuro Oncol. doi: 10.1093/neuonc/now135 – year: 1998 ident: pone.0299267.ref030 publication-title: Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines – volume: 19 start-page: 792 year: 2007 ident: pone.0299267.ref015 article-title: Support Vector Ordinal Regression. publication-title: Neural Comput. doi: 10.1162/neco.2007.19.3.792 – volume: 25 start-page: 143 year: 2015 ident: pone.0299267.ref042 article-title: Pretreatment dynamic susceptibility contrast MRI perfusion in glioblastoma: prediction of EGFR gene amplification publication-title: Clin Neuroradiol doi: 10.1007/s00062-014-0289-3 – volume: 11 start-page: 1 year: 2021 ident: pone.0299267.ref007 article-title: Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma. publication-title: Sci Rep – year: 2013 ident: pone.0299267.ref040 publication-title: Multi-output Random Forests – volume: 7 year: 2006 ident: pone.0299267.ref035 article-title: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples publication-title: Journal of machine learning research – volume: 10 year: 2020 ident: pone.0299267.ref032 article-title: Contrast-enhanced T1-weighted image radiomics of brain metastases may predict EGFR mutation status in primary lung cancer publication-title: Sci Rep – volume: 20 start-page: 810 year: 2011 ident: pone.0299267.ref043 article-title: Mosaic amplification of multiple receptor tyrosine kinase genes in glioblastoma publication-title: Cancer Cell doi: 10.1016/j.ccr.2011.11.005 – start-page: 4768 year: 2017 ident: pone.0299267.ref033 article-title: A unified approach to interpreting model predictions publication-title: Proceedings of the 31st international conference on neural information processing systems. – volume: 8 start-page: e71704 year: 2013 ident: pone.0299267.ref044 article-title: Cerebral blood volume calculated by dynamic susceptibility contrast-enhanced perfusion MR imaging: preliminary correlation study with glioblastoma genetic profiles publication-title: PLoS One doi: 10.1371/journal.pone.0071704 – volume: 69 start-page: 4894 year: 2009 ident: pone.0299267.ref018 article-title: Adaptive therapy. publication-title: Cancer Res doi: 10.1158/0008-5472.CAN-08-3658 – volume: 25 start-page: 774 year: 2012 ident: pone.0299267.ref048 article-title: Epidermal growth factor receptor: a re-emerging target in glioblastoma publication-title: Curr Opin Neurol doi: 10.1097/WCO.0b013e328359b0bc – volume: 14 start-page: 613 year: 2012 ident: pone.0299267.ref011 article-title: Use of magnetic perfusion-weighted imaging to determine epidermal growth factor receptor variant III expression in glioblastoma publication-title: Neuro Oncol doi: 10.1093/neuonc/nos073 – ident: pone.0299267.ref017 publication-title: Ranking with Large Margin Principle: Two Approaches*. – volume: 352 start-page: 987 year: 2005 ident: pone.0299267.ref001 article-title: Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma publication-title: New England journal of medicine doi: 10.1056/NEJMoa043330 – volume: 9 start-page: 10063 year: 2019 ident: pone.0299267.ref021 article-title: Integration of machine learning and mechanistic models accurately predicts variation in cell density of glioblastoma using multiparametric MRI publication-title: Sci Rep doi: 10.1038/s41598-019-46296-4 – volume: 10 start-page: e0141506 year: 2015 ident: pone.0299267.ref002 article-title: Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma. publication-title: PLoS One. doi: 10.1371/journal.pone.0141506 – volume: 12 start-page: 323 year: 2012 ident: pone.0299267.ref006 article-title: Intra-tumour heterogeneity: a looking glass for cancer? publication-title: Nat Rev Cancer. doi: 10.1038/nrc3261 – volume: 9 start-page: e108335 year: 2014 ident: pone.0299267.ref026 article-title: Glioma: application of whole-tumor texture analysis of diffusion-weighted imaging for the evaluation of tumor heterogeneity. publication-title: PLoS One doi: 10.1371/journal.pone.0108335 – start-page: 153 year: 2007 ident: pone.0299267.ref039 article-title: Multi-task Gaussian process prediction publication-title: Adv Neural Inf Process Syst – volume: 7 start-page: 1321 year: 2008 ident: pone.0299267.ref020 article-title: PTEN signaling pathways in glioblastoma publication-title: Cancer Biol Ther doi: 10.4161/cbt.7.9.6954 – volume: 35 start-page: 1797 year: 2019 ident: pone.0299267.ref038 article-title: RMTL: an R library for multi-task learning publication-title: Bioinformatics doi: 10.1093/bioinformatics/bty831 – volume: 109 start-page: 3041 year: 2012 ident: pone.0299267.ref046 article-title: Intratumoral heterogeneity of receptor tyrosine kinases EGFR and PDGFRA amplification in glioblastoma defines subpopulations with distinct growth factor response publication-title: Proc Natl Acad Sci U S A doi: 10.1073/pnas.1114033109 – volume-title: Gabor analysis and algorithms: Theory and applications year: 2012 ident: pone.0299267.ref023 – volume: 19 start-page: 1155 year: 2007 ident: pone.0299267.ref029 article-title: Training a support vector machine in the primal. publication-title: Neural Comput. doi: 10.1162/neco.2007.19.5.1155 – volume: 216 start-page: 1 year: 2003 ident: pone.0299267.ref004 article-title: Virtual and real brain tumors: using mathematical modeling to quantify glioma growth and invasion publication-title: J Neurol Sci doi: 10.1016/j.jns.2003.06.001 – volume: 24 start-page: 1731 year: 2010 ident: pone.0299267.ref045 article-title: Tumor heterogeneity is an active process maintained by a mutant EGFR-induced cytokine circuit in glioblastoma publication-title: Genes Dev doi: 10.1101/gad.1890510 – volume: 20 start-page: 1068 year: 2018 ident: pone.0299267.ref010 article-title: In vivo evaluation of EGFRvIII mutation in primary glioblastoma patients via complex multiparametric MRI signature publication-title: Neuro Oncol doi: 10.1093/neuonc/noy033 – volume: 13 year: 2021 ident: pone.0299267.ref008 article-title: Development and Validation of an Efficient MRI Radiomics Signature for Improving the Predictive Performance of 1p/19q Co-Deletion in Lower-Grade Gliomas. publication-title: Cancers (Basel). – volume: 113 start-page: 116 year: 2019 ident: pone.0299267.ref024 article-title: Filtration-histogram based magnetic resonance texture analysis (MRTA) for glioma IDH and 1p19q genotyping. publication-title: Eur J Radiol doi: 10.1016/j.ejrad.2019.02.014 – volume: 36 start-page: 785 year: 2010 ident: pone.0299267.ref047 article-title: HIF1-positive and HIF1-negative glioblastoma cells compete in vitro but cooperate in tumor growth in vivo publication-title: Int J Oncol – start-page: 506 year: 2009 ident: pone.0299267.ref037 article-title: Semi-Supervised Random Forests publication-title: IEEE 12th international conference on computer vision. – volume-title: Pattern recognition and machine learning year: 2006 ident: pone.0299267.ref031 – volume: 75 start-page: 351 year: 2020 ident: pone.0299267.ref027 article-title: The diagnostic value of quantitative texture analysis of conventional MRI sequences using artificial neural networks in grading gliomas. publication-title: Clin Radiol. doi: 10.1016/j.crad.2019.12.008 – volume: 5 year: 2017 ident: pone.0299267.ref050 article-title: Sampling and Sampling Methods. publication-title: Biom Biostat Int J – volume: 35 start-page: e4792 year: 2022 ident: pone.0299267.ref009 article-title: Molecular subtype classification of low-grade gliomas using magnetic resonance imaging-based radiomics and machine learning publication-title: NMR Biomed doi: 10.1002/nbm.4792 – volume: 71 start-page: 4055 year: 2011 ident: pone.0299267.ref049 article-title: Heterogeneity Maintenance in Glioblastoma: A Social Network publication-title: Cancer Res doi: 10.1158/0008-5472.CAN-11-0153 |
| SSID | ssj0053866 |
| Score | 2.4658494 |
| Snippet | Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment.... Background and objective Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant... Background and objectiveGlioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant... |
| SourceID | doaj pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | e0299267 |
| SubjectTerms | Algorithms Analysis Biology and Life Sciences Care and treatment Data mining Diagnosis ErbB Receptors - genetics Genetic aspects Genetic Heterogeneity Genetic research Glioblastoma - diagnostic imaging Glioblastoma - genetics Glioblastoma - pathology Glioblastoma multiforme Health aspects Humans Machine Learning Magnetic resonance imaging Magnetic Resonance Imaging - methods Medicine and Health Sciences Physical Sciences Platelet-derived growth factor Precision Medicine Research and Analysis Methods Support Vector Machine |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwELbQnrgglmdhAYOQgEN2k9hxkuOCWO0iAWJh0d4sP9tKbVK1yS_hDzPjuKURh-XAsfU0bWfGM2P5m28IeZ37Gu9zi8RUPk24T02ioKpOtK1r70WgREO0xRdxfsU_XRfXe6O-EBM20AMPijvRRWm5V84XmeKpNyrjxnvDDdS6RmmL0Rdy3vYwNcRg2MVCxEY5VmYn0S7Hq7ZxxylE4DzMlf-TiAJf_99ReS8tjSGTezno7C65E4tHejr86ENyyzX3yGHcnhv6NnJIv7tPfn3rFcKAsImJzvFhSdcvsRufgsdg4yKdIRCmxVdQiNPW0-li3mooprt2qWgX4LR0tY4zeOj2Ep4iUn5KP19eUNVYqihiTJN5YxY9IuHpMqAzHY3jKKZULabtet7Nlg_I1dnHHx_Okzh_ITFFmXWJ9b7QTumssALKptxnuuTKcaF4xa1DsjnrS8acKkHQpLaE9G91bW3utWCWPSQHDWj8MaEQjmutuDZ1wbjiVnmdFs7zkom0zq2eELY1hjSRnBxnZCxkuHEr4ZAyqFiiCWU04YQku0-tBnKOG-Tfo513skitHd4Ah5PR4eRNDjchL9BL5NCnugsQ8rSs4HQI5RN8zasggfQaDeJ3pqrfbOTF15__IPT9ciT0Jgr5FtRhVOyZgP-EtF0jyaORJAQJM1p-ufVpiUuIrGtc228klDAs8AyKCXk0-PhOP6wqRFUX6YRUI-8fKXC80sxngaM8XLjmXDz5Hyp_Sm7n8LAAmGJH5KBb9-4Z1IKdfh62_W9h4mcV priority: 102 providerName: Directory of Open Access Journals |
| Title | Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/38568950 https://www.proquest.com/docview/3033010166 https://pubmed.ncbi.nlm.nih.gov/PMC10990246 https://doaj.org/article/b57d4faef51a40fca14cffc4c306cabd |
| Volume | 19 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lj9MwELb2ceGCWJ5dlmIQEnBIlYcTJweEdlctu0i7QKFob5EfcVqpTUqbSnDhT_CHmXHdaiNAIC6uWo9TdTwej-tvviHkWWgyvM-NPZUa32PGV56AqNqTOsuMSSwlGqItLpOzEXt7FV_tkE3NVqfA5W-PdlhParSY9r5--fYaFvwrW7WBB5tBvXldFT0f_GuY8F2yD3sTx6V6wbb3CrC6k8Ql0P1pZGuDsjz-v3rra9tVG0p5bW8a3CI3XVBJj9dWcEB2iuo2OXDLdklfOG7pl3fIjw8rgfAgTG6iE3yY16xmmKVPwZIwoZGOESBT4zsI0GltaDmd1BKC7KaeCdpYmC2dL1xtHrq5nKeIoC_pxfCcikpTQRF76k0qNV0hQp7OLGqzoK5MRUnFtKwXk2Y8u0tGg_6n0zPP1WXwVMyDxtPGxLIQMoh1AuFUaALJmShYIljKdIEkdNrwKCoEB0Hlaw5hgZaZ1qGRSaSje2SvAo0_IBTcdCYFkyqLIyaYFkb6cWEYjxI_C7XskGgzGblypOVYO2Oa25s4DoeXtYpznMLcTWGHeNtR8zVpx1_kT3Cet7JIuW0_qBdl7lZwLmOumRGFiQPBfKNEwJQxiik4dCkhdYc8RivJ1_mrW8eRH_MUTo0QVsHXPLUSSLtRIa6nFKvlMj9_9_kfhD4OW0LPnZCpQR1KuFwK-E1I59WSPGpJgvNQre4nG5vOsQsRd1VRr5Y5hDaR5R9MOuT-2sa3-onSOEmz2O-QtGX9LQW2e6rJ2HKX24vYkCWH_z_0IbkRwquFT0VHZK9ZrIpHEBk2skt2-RWHNj0NsB286ZL9k_7l-2HX_tfStc4A2-_9n4z8dAw |
| linkProvider | Scholars Portal |
| 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=Quantifying+intra-tumoral+genetic+heterogeneity+of+glioblastoma+toward+precision+medicine+using+MRI+and+a+data-inclusive+machine+learning+algorithm&rft.jtitle=PloS+one&rft.au=Wang%2C+Lujia&rft.au=Wang%2C+Hairong&rft.au=D%E2%80%99Angelo%2C+Fulvio&rft.au=Curtin%2C+Lee&rft.date=2024-04-03&rft.pub=Public+Library+of+Science&rft.eissn=1932-6203&rft.volume=19&rft.issue=4&rft_id=info:doi/10.1371%2Fjournal.pone.0299267&rft.externalDocID=PMC10990246 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-6203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-6203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-6203&client=summon |