Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions
The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomog...
Saved in:
Published in | Magnetic resonance imaging Vol. 100; pp. 64 - 72 |
---|---|
Main Authors | , , , , , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Netherlands
Elsevier Inc
01.07.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification.
20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (KTRANS), efflux rate constant (Kep), and extracellular volume ratio (Ve) from mpMR images, and SUVmean and SUVmax from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM).
SUVmax yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input.
ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy.
[Display omitted]
•Among 7 quantitative parameters, SUVmax correlated best with Gleason score (GS).•Machine learning yielded higher accuracies than using cut-points of parameters.•Quantitative parameters (QP) and radiomic features (RF) as inputs for GS prediction.•K-Nearest Neighbour yielded highest accuracy of 0.929 with QP and RF.•Combinations of parameters, risk factors and models affect classification accuracy. |
---|---|
AbstractList | The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification.
20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (K
), efflux rate constant (K
), and extracellular volume ratio (V
) from mpMR images, and SUV
and SUV
from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM).
SUV
yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input.
ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy. INTRODUCTIONThe classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification. METHODS20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (KTRANS), efflux rate constant (Kep), and extracellular volume ratio (Ve) from mpMR images, and SUVmean and SUVmax from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM). RESULTSSUVmax yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input. CONCLUSIONSML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy. The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification. 20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (KTRANS), efflux rate constant (Kep), and extracellular volume ratio (Ve) from mpMR images, and SUVmean and SUVmax from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM). SUVmax yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input. ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy. [Display omitted] •Among 7 quantitative parameters, SUVmax correlated best with Gleason score (GS).•Machine learning yielded higher accuracies than using cut-points of parameters.•Quantitative parameters (QP) and radiomic features (RF) as inputs for GS prediction.•K-Nearest Neighbour yielded highest accuracy of 0.929 with QP and RF.•Combinations of parameters, risk factors and models affect classification accuracy. |
Author | Conti, Maurizio Roy, Sharmili Singha, Arvind Kumar Eriksson, Lars Chiong, Edmund Ang, Bertrand Wei Leng Totman, John J. Reilhac, Anthonin Cheong, Dennis Lai Hong Robins, Edward G. Kok, Trina Schaefferkoetter, Josh Chua, Wynne Yuru Nai, Ying-Hwey Thamboo, Thomas Paulraj Stephenson, Mary C. Wang, Ziting |
Author_xml | – sequence: 1 givenname: Ying-Hwey surname: Nai fullname: Nai, Ying-Hwey email: yinghweynai@yahoo.com organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 2 givenname: Dennis Lai Hong surname: Cheong fullname: Cheong, Dennis Lai Hong organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 3 givenname: Sharmili surname: Roy fullname: Roy, Sharmili organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 4 givenname: Trina surname: Kok fullname: Kok, Trina organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 5 givenname: Mary C. surname: Stephenson fullname: Stephenson, Mary C. organization: Centre for Translational MR, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 6 givenname: Josh surname: Schaefferkoetter fullname: Schaefferkoetter, Josh organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 7 givenname: John J. surname: Totman fullname: Totman, John J. organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 8 givenname: Maurizio surname: Conti fullname: Conti, Maurizio organization: Siemens Medical Solutions USA, Inc., Molecular Imaging, Knoxville, TN, USA – sequence: 9 givenname: Lars surname: Eriksson fullname: Eriksson, Lars organization: Siemens Medical Solutions USA, Inc., Molecular Imaging, Knoxville, TN, USA – sequence: 10 givenname: Edward G. surname: Robins fullname: Robins, Edward G. organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore – sequence: 11 givenname: Ziting surname: Wang fullname: Wang, Ziting organization: Department of Urology, National University Hospital, Singapore – sequence: 12 givenname: Wynne Yuru surname: Chua fullname: Chua, Wynne Yuru organization: Department of Diagnostic Imaging, National University Hospital, Singapore – sequence: 13 givenname: Bertrand Wei Leng surname: Ang fullname: Ang, Bertrand Wei Leng organization: Department of Diagnostic Imaging, National University Hospital, Singapore – sequence: 14 givenname: Arvind Kumar surname: Singha fullname: Singha, Arvind Kumar organization: Department of Diagnostic Imaging, National University Hospital, Singapore – sequence: 15 givenname: Thomas Paulraj surname: Thamboo fullname: Thamboo, Thomas Paulraj organization: Department of Pathology, National University Health System, Singapore – sequence: 16 givenname: Edmund surname: Chiong fullname: Chiong, Edmund organization: Department of Diagnostic Imaging, National University Hospital, Singapore – sequence: 17 givenname: Anthonin surname: Reilhac fullname: Reilhac, Anthonin organization: Clinical Imaging Research Centre, Yong Loo Lin School of Medicine, National University of Singapore, Singapore |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36933775$$D View this record in MEDLINE/PubMed |
BookMark | eNp9Uc2KFDEQDrLizq4-gBfJ0UuPlaTTPY0nGXQVFrwoeAvZpOJm6CS9SXrBV_FpTTOrR6GgoOr7Keq7IhcxRSTkNYM9Aza8O-1D9nsOXOyhFUzPyI4dRtHJw9RfkB2MArqRyx-X5KqUEwBILuQLcimGSYhxlDvy-5jCorMvKdLk6MOqY_VVV_-ItM11wIq5UB0tzdr6FLyhDnVdM7ZpoT4ua91aTTRoc-8j0hl1jj7-pCFZnAttqyWj9abSeo_0pu03u2JSxs10yak0S6RGR4O58YtPsbwkz52eC7566tfk-6eP346fu9uvN1-OH247I6SonXC9MdY4HNgwjNodAIWZnAHkAxNC9CAPYtLAuRy4RtuzXhoHcKctTFL04pq8Peu2Ox5WLFUFXwzOs46Y1qL4OLERejZAg7Iz1LSTS0anluyDzr8UA7VFok6qRaK2SBS0gqlx3jzJr3cB7T_G3wwa4P0Z0H6Fjx6zKsZj-4T1GU1VNvn_yP8BqjChuw |
CitedBy_id | crossref_primary_10_1007_s13246_024_01402_3 crossref_primary_10_1109_ACCESS_2023_3306515 crossref_primary_10_3390_cancers15184437 crossref_primary_10_3390_jcm13133907 crossref_primary_10_3390_jpm13040643 |
Cites_doi | 10.1016/S0022-5347(17)37394-9 10.1007/s00259-017-3700-x 10.3322/caac.21660 10.1007/s00330-019-06488-y 10.2967/jnumed.120.245605 10.1259/bjr.20170067 10.1186/s41747-019-0109-2 10.1158/0008-5472.CAN-17-0339 10.1016/j.ejrad.2019.05.006 10.3390/cancers10080249 10.1016/j.ejro.2018.03.002 10.1186/s12894-020-00717-z 10.1016/j.radonc.2015.04.012 10.1001/jama.1994.03510290050036 10.1007/s00261-017-1297-y 10.12659/PJR.890805 10.2214/AJR.13.11046 10.1007/s00261-020-02738-6 10.1016/0090-4295(94)90170-8 10.1111/bju.13465 10.1002/jmri.27080 10.1016/j.ejrad.2019.03.010 10.1186/s43055-020-00347-3 10.18632/oncotarget.24652 10.2967/jnumed.115.169243 10.1186/s13550-017-0269-0 10.1186/s40644-020-00311-4 10.1097/PAS.0000000000001497 |
ContentType | Journal Article |
Copyright | 2023 Elsevier Inc. Copyright © 2023 Elsevier Inc. All rights reserved. |
Copyright_xml | – notice: 2023 Elsevier Inc. – notice: Copyright © 2023 Elsevier Inc. All rights reserved. |
DBID | CGR CUY CVF ECM EIF NPM AAYXX CITATION 7X8 |
DOI | 10.1016/j.mri.2023.03.009 |
DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed CrossRef MEDLINE - Academic |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) CrossRef MEDLINE - Academic |
DatabaseTitleList | MEDLINE MEDLINE - Academic |
Database_xml | – sequence: 1 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: 2 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 | Medicine |
EISSN | 1873-5894 |
EndPage | 72 |
ExternalDocumentID | 10_1016_j_mri_2023_03_009 36933775 S0730725X23000504 |
Genre | Research Support, Non-U.S. Gov't Journal Article |
GroupedDBID | --- --K --M .1- .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29M 3O- 4.4 457 4CK 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABBQC ABFNM ABGSF ABJNI ABLVK ABMAC ABMZM ABNEU ABOCM ABUDA ABXDB ABYKQ ACDAQ ACFVG ACGFS ACIUM ACNNM ACRLP ADBBV ADEZE ADMUD ADUVX AEBSH AEHWI AEKER AENEX AEVXI AFCTW AFFNX AFKWA AFRHN AFTJW AFXIZ AGHFR AGRDE AGUBO AGYEJ AHHHB AIEXJ AIKHN AITUG AIVDX AJBFU AJOXV AJRQY AJUYK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 DOVZS EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA HEI HMK HMO HVGLF HZ~ IHE J1W KOM LCYCR M29 M41 MO0 N9A O-L O9- OAUVE OGIMB OI~ OU0 OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SAE SCC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSQ SSU SSZ T5K WUQ XPP Z5R ZGI ZMT ~G- ~S- AAXKI AFJKZ AKRWK CGR CUY CVF ECM EIF NPM AAYXX ABDPE ACRPL CITATION 7X8 |
ID | FETCH-LOGICAL-c353t-3f4ccdcfe61667af80e3c9fc0e261333405839a022562aed4145cf00bad095343 |
IEDL.DBID | .~1 |
ISSN | 0730-725X |
IngestDate | Wed Dec 04 15:23:35 EST 2024 Fri Dec 06 00:56:55 EST 2024 Sat Sep 28 08:12:47 EDT 2024 Fri Feb 23 02:40:32 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | PRC ADC TZ PZ PSADWP AUC GLDM DT DWI EP2D ML PSA DCE ROC TSE EM Gleason score (GS) ROI GLCM Ktrans SUV GRE GLRLM PSAD SUVmax SVM TOF-PSF GLSZM Radiomics PCa Ve Multiparametric magnetic resonance imaging (mpMRI) Quantitative parameters NPV OP-OSEM PPV kep mRMR T2w TURP WP SUVmean PSADTZ Positron emission tomography (PET) CG NGTDM Machine learning (ML) kNN ADC ratio GS CT PSMA mpMRI csPCa PI-RADS PSADCG PET |
Language | English |
License | Copyright © 2023 Elsevier Inc. All rights reserved. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c353t-3f4ccdcfe61667af80e3c9fc0e261333405839a022562aed4145cf00bad095343 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
PMID | 36933775 |
PQID | 2791704160 |
PQPubID | 23479 |
PageCount | 9 |
ParticipantIDs | proquest_miscellaneous_2791704160 crossref_primary_10_1016_j_mri_2023_03_009 pubmed_primary_36933775 elsevier_sciencedirect_doi_10_1016_j_mri_2023_03_009 |
PublicationCentury | 2000 |
PublicationDate | July 2023 2023-07-00 20230701 |
PublicationDateYYYYMMDD | 2023-07-01 |
PublicationDate_xml | – month: 07 year: 2023 text: July 2023 |
PublicationDecade | 2020 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | Magnetic resonance imaging |
PublicationTitleAlternate | Magn Reson Imaging |
PublicationYear | 2023 |
Publisher | Elsevier Inc |
Publisher_xml | – name: Elsevier Inc |
References | Hauth, Halbritter, Jaeger, Hohmuth, Beer (bb0100) 2017; 90 Sung, Ferlay, Siegel (bb0005) 2021; 71 Cuocolo, Cipullo, Stanzione (bb0050) 2019; 3 Hassanzadeh, Alessandrino, Olubiyi (bb0080) 2018; 43 Min, Li, Dong (bb0110) 2019; 115 Chaddad, Kucharczyk, Niazi (bb0150) 2018; 10 Klingenberg, Jochumsen, Ulhøi (bb0070) 2021; 62 Benson, Whang, Olsson (bb0015) 1992; 147 van Griethuysen, Fedorov, Parmar (bb0135) 2017; 77 de Rooij, Hamoen, Fütterer, Barentsz, Rovers (bb0035) 2014; 202 van Leenders, van der Kwast, Grignon (bb0125) 2020; 44 Giovacchini, Giovannini, Leoncini, Riondato, Ciarmiello (bb0075) 2017; 44 Kalish, Cooner, Graham (bb0020) 1994; 43 Papanikolaou, Matos, Koh (bb0140) 2020; 20 Schaefferkoetter, Wang, Stephenson (bb0060) 2017; 7 Kang, Jeun, Jang (bb0010) 2015; 10 Ma, Lv, Sheng (bb0105) 2019; 17 Steenbergen, Haustermans, Lerut (bb0055) 2015; 115 Washino, Okochi, Saito (bb0030) 2017; 119 Xu, Zhang, Zhang (bb0045) 2020; 45 Chang, Lin, Tsai (bb0025) 2020; 20 Rahbar, Weckesser, Huss (bb0065) 2016; 57 Cuocolo, Stanzione, Ponsiglione (bb0120) 2019; 116 Byun, Park, Kim, Kim (bb0040) 2020; 52 Epstein, Walsh, Carmichael, Brendler (bb0130) 1994; 271 Ragheb, Bassiouny (bb0090) 2020; 51 Wei, Jin, Szewczyk-Bieda (bb0095) 2018; 9 Jyoti, Jain, Haxhimolla, Liddell, Barrett (bb0085) 2018; 5 Bleker, Kwee, Dierckx, de Jong, Huisman, Yakar (bb0115) 2020; 30 Łuczyńska, Heinze-Paluchowska, Domalik (bb0145) 2014; 79 Chang (10.1016/j.mri.2023.03.009_bb0025) 2020; 20 Byun (10.1016/j.mri.2023.03.009_bb0040) 2020; 52 Wei (10.1016/j.mri.2023.03.009_bb0095) 2018; 9 Hauth (10.1016/j.mri.2023.03.009_bb0100) 2017; 90 Ma (10.1016/j.mri.2023.03.009_bb0105) 2019; 17 Klingenberg (10.1016/j.mri.2023.03.009_bb0070) 2021; 62 Epstein (10.1016/j.mri.2023.03.009_bb0130) 1994; 271 van Griethuysen (10.1016/j.mri.2023.03.009_bb0135) 2017; 77 Łuczyńska (10.1016/j.mri.2023.03.009_bb0145) 2014; 79 de Rooij (10.1016/j.mri.2023.03.009_bb0035) 2014; 202 Ragheb (10.1016/j.mri.2023.03.009_bb0090) 2020; 51 Cuocolo (10.1016/j.mri.2023.03.009_bb0050) 2019; 3 Rahbar (10.1016/j.mri.2023.03.009_bb0065) 2016; 57 Min (10.1016/j.mri.2023.03.009_bb0110) 2019; 115 Xu (10.1016/j.mri.2023.03.009_bb0045) 2020; 45 Washino (10.1016/j.mri.2023.03.009_bb0030) 2017; 119 Kalish (10.1016/j.mri.2023.03.009_bb0020) 1994; 43 Kang (10.1016/j.mri.2023.03.009_bb0010) 2015; 10 Chaddad (10.1016/j.mri.2023.03.009_bb0150) 2018; 10 Benson (10.1016/j.mri.2023.03.009_bb0015) 1992; 147 Sung (10.1016/j.mri.2023.03.009_bb0005) 2021; 71 Giovacchini (10.1016/j.mri.2023.03.009_bb0075) 2017; 44 Bleker (10.1016/j.mri.2023.03.009_bb0115) 2020; 30 Schaefferkoetter (10.1016/j.mri.2023.03.009_bb0060) 2017; 7 van Leenders (10.1016/j.mri.2023.03.009_bb0125) 2020; 44 Steenbergen (10.1016/j.mri.2023.03.009_bb0055) 2015; 115 Papanikolaou (10.1016/j.mri.2023.03.009_bb0140) 2020; 20 Jyoti (10.1016/j.mri.2023.03.009_bb0085) 2018; 5 Hassanzadeh (10.1016/j.mri.2023.03.009_bb0080) 2018; 43 Cuocolo (10.1016/j.mri.2023.03.009_bb0120) 2019; 116 |
References_xml | – volume: 5 start-page: 58 year: 2018 end-page: 63 ident: bb0085 article-title: Correlation of apparent diffusion coefficient ratio on 3.0 T MRI with prostate cancer Gleason score publication-title: Eur J Radiol Open contributor: fullname: Barrett – volume: 57 start-page: 563 year: 2016 end-page: 567 ident: bb0065 article-title: Correlation of intraprostatic tumor extent with publication-title: J Nucl Med contributor: fullname: Huss – volume: 51 start-page: 242 year: 2020 ident: bb0090 article-title: Can mean ADC value and ADC ratio of benign prostate tissue to prostate cancer assist in the prediction of clinically significant prostate cancer within the PI-RADSv2 scoring system? publication-title: Egypt J Radiol Nucl Med contributor: fullname: Bassiouny – volume: 45 start-page: 4133 year: 2020 end-page: 4141 ident: bb0045 article-title: Comparison of PI-RADS version 2.1 and PI-RADS version 2 regarding interreader variability and diagnostic accuracy for transition zone prostate cancer publication-title: Abdom Radiol contributor: fullname: Zhang – volume: 20 start-page: 151 year: 2020 ident: bb0025 article-title: Zonal adjusted PSA density improves prostate cancer detection rates compared with PSA in Taiwanese males with PSA < publication-title: BMC Urol contributor: fullname: Tsai – volume: 44 start-page: 1751 year: 2017 end-page: 1776 ident: bb0075 article-title: PET and PET/CT with radiolabeled choline in prostate cancer: a critical reappraisal of 20 years of clinical studies publication-title: Eur J Nucl Med Mol Imaging contributor: fullname: Ciarmiello – volume: 90 start-page: 20170067 year: 2017 ident: bb0100 article-title: Diagnostic value of semi-quantitative and quantitative analysis of functional parameters in multiparametric MRI of the prostate publication-title: Br J Radiol contributor: fullname: Beer – volume: 3 start-page: 35 year: 2019 ident: bb0050 article-title: Machine learning applications in prostate cancer magnetic resonance imaging publication-title: Eur Radiol Exp contributor: fullname: Stanzione – volume: 116 start-page: 144 year: 2019 end-page: 149 ident: bb0120 article-title: Clinically significant prostate cancer detection on MRI: a radiomic shape features study publication-title: Eur J Radiol contributor: fullname: Ponsiglione – volume: 43 start-page: 1237 year: 2018 end-page: 1244 ident: bb0080 article-title: Comparison of quantitative apparent diffusion coefficient parameters with prostate imaging reporting and data system V2 assessment for detection of clinically significant peripheral zone prostate cancer publication-title: Abdom Radiol (NY) contributor: fullname: Olubiyi – volume: 71 start-page: 209 year: 2021 end-page: 249 ident: bb0005 article-title: Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries publication-title: CA Cancer J Clin contributor: fullname: Siegel – volume: 44 start-page: e87 year: 2020 end-page: e99 ident: bb0125 article-title: The 2019 International Society of Urological Pathology (ISUP) consensus conference on grading of prostatic carcinoma publication-title: Am J Surg Pathol contributor: fullname: Grignon – volume: 10 start-page: E249 year: 2018 ident: bb0150 article-title: Multimodal radiomic features for the predicting gleason score of prostate cancer publication-title: Cancers (Basel) contributor: fullname: Niazi – volume: 115 start-page: 186 year: 2015 end-page: 190 ident: bb0055 article-title: Prostate tumor delineation using multiparametric magnetic resonance imaging: inter-observer variability and pathology validation publication-title: Radiother Oncol contributor: fullname: Lerut – volume: 9 start-page: 15997 year: 2018 end-page: 16007 ident: bb0095 article-title: Quantitative parameters in dynamic contrast-enhanced magnetic resonance imaging for the detection and characterization of prostate cancer publication-title: Oncotarget. contributor: fullname: Szewczyk-Bieda – volume: 52 start-page: 577 year: 2020 end-page: 586 ident: bb0040 article-title: Direct comparison of PI-RADS version 2 and 2.1 in transition zone lesions for detection of prostate cancer: preliminary experience publication-title: J Magn Reson Imaging contributor: fullname: Kim – volume: 62 start-page: 214 year: 2021 end-page: 220 ident: bb0070 article-title: 68Ga-PSMA PET/CT for primary lymph node and distant metastasis NM staging of high-risk prostate cancer publication-title: J Nucl Med contributor: fullname: Ulhøi – volume: 271 start-page: 368 year: 1994 end-page: 374 ident: bb0130 article-title: Pathologic and clinical findings to predict tumor extent of nonpalpable (stage T1c) prostate cancer publication-title: JAMA. contributor: fullname: Brendler – volume: 10 start-page: 6555 year: 2015 end-page: 6569 ident: bb0010 article-title: Diagnosis of prostate cancer via nanotechnological approach publication-title: Int J Nanomedicine contributor: fullname: Jang – volume: 7 start-page: 25 year: 2017 ident: bb0060 article-title: Quantitative 18F-fluorocholine positron emission tomography for prostate cancer: correlation between kinetic parameters and Gleason scoring publication-title: EJNMMI Res contributor: fullname: Stephenson – volume: 147 start-page: 817 year: 1992 end-page: 821 ident: bb0015 article-title: The use of prostate specific antigen density to enhance the predictive value of intermediate levels of serum prostate specific antigen publication-title: J Urol contributor: fullname: Olsson – volume: 79 start-page: 450 year: 2014 end-page: 455 ident: bb0145 article-title: The utility of diffusion weighted imaging (DWI) using apparent diffusion coefficient (ADC) values in discriminating between prostate cancer and normal tissue publication-title: Pol J Radiol contributor: fullname: Domalik – volume: 43 start-page: 601 year: 1994 end-page: 606 ident: bb0020 article-title: Serum PSA adjusted for volume of transition zone (PSAT) is more accurate than PSA adjusted for total gland volume (PSAD) in detecting adenocarcinoma of the prostate publication-title: Urology. contributor: fullname: Graham – volume: 202 start-page: 343 year: 2014 end-page: 351 ident: bb0035 article-title: Accuracy of multiparametric MRI for prostate cancer detection: a meta-analysis publication-title: Am J Roentgenol contributor: fullname: Rovers – volume: 115 start-page: 16 year: 2019 end-page: 21 ident: bb0110 article-title: Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: cross-validation of a machine learning method publication-title: Eur J Radiol contributor: fullname: Dong – volume: 77 start-page: e104 year: 2017 end-page: e107 ident: bb0135 article-title: Computational Radiomics system to decode the radiographic phenotype publication-title: Cancer Res contributor: fullname: Parmar – volume: 20 start-page: 33 year: 2020 ident: bb0140 article-title: How to develop a meaningful radiomic signature for clinical use in oncologic patients publication-title: Cancer Imaging contributor: fullname: Koh – volume: 30 start-page: 1313 year: 2020 end-page: 1324 ident: bb0115 article-title: Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer publication-title: Eur Radiol contributor: fullname: Yakar – volume: 119 start-page: 225 year: 2017 end-page: 233 ident: bb0030 article-title: Combination of prostate imaging reporting and data system (PI-RADS) score and prostate-specific antigen (PSA) density predicts biopsy outcome in prostate biopsy naïve patients publication-title: BJU Int contributor: fullname: Saito – volume: 17 start-page: 3077 year: 2019 end-page: 3084 ident: bb0105 article-title: Application evaluation of DCE-MRI combined with quantitative analysis of DWI for the diagnosis of prostate cancer publication-title: Oncol Lett contributor: fullname: Sheng – volume: 147 start-page: 817 issue: 3 II year: 1992 ident: 10.1016/j.mri.2023.03.009_bb0015 article-title: The use of prostate specific antigen density to enhance the predictive value of intermediate levels of serum prostate specific antigen publication-title: J Urol doi: 10.1016/S0022-5347(17)37394-9 contributor: fullname: Benson – volume: 44 start-page: 1751 issue: 10 year: 2017 ident: 10.1016/j.mri.2023.03.009_bb0075 article-title: PET and PET/CT with radiolabeled choline in prostate cancer: a critical reappraisal of 20 years of clinical studies publication-title: Eur J Nucl Med Mol Imaging doi: 10.1007/s00259-017-3700-x contributor: fullname: Giovacchini – volume: 71 start-page: 209 issue: 3 year: 2021 ident: 10.1016/j.mri.2023.03.009_bb0005 article-title: Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries publication-title: CA Cancer J Clin doi: 10.3322/caac.21660 contributor: fullname: Sung – volume: 30 start-page: 1313 issue: 3 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0115 article-title: Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer publication-title: Eur Radiol doi: 10.1007/s00330-019-06488-y contributor: fullname: Bleker – volume: 62 start-page: 214 issue: 2 year: 2021 ident: 10.1016/j.mri.2023.03.009_bb0070 article-title: 68Ga-PSMA PET/CT for primary lymph node and distant metastasis NM staging of high-risk prostate cancer publication-title: J Nucl Med doi: 10.2967/jnumed.120.245605 contributor: fullname: Klingenberg – volume: 90 start-page: 20170067 issue: 1078 year: 2017 ident: 10.1016/j.mri.2023.03.009_bb0100 article-title: Diagnostic value of semi-quantitative and quantitative analysis of functional parameters in multiparametric MRI of the prostate publication-title: Br J Radiol doi: 10.1259/bjr.20170067 contributor: fullname: Hauth – volume: 3 start-page: 35 issue: 1 year: 2019 ident: 10.1016/j.mri.2023.03.009_bb0050 article-title: Machine learning applications in prostate cancer magnetic resonance imaging publication-title: Eur Radiol Exp doi: 10.1186/s41747-019-0109-2 contributor: fullname: Cuocolo – volume: 77 start-page: e104 issue: 21 year: 2017 ident: 10.1016/j.mri.2023.03.009_bb0135 article-title: Computational Radiomics system to decode the radiographic phenotype publication-title: Cancer Res doi: 10.1158/0008-5472.CAN-17-0339 contributor: fullname: van Griethuysen – volume: 116 start-page: 144 year: 2019 ident: 10.1016/j.mri.2023.03.009_bb0120 article-title: Clinically significant prostate cancer detection on MRI: a radiomic shape features study publication-title: Eur J Radiol doi: 10.1016/j.ejrad.2019.05.006 contributor: fullname: Cuocolo – volume: 10 start-page: E249 issue: 8 year: 2018 ident: 10.1016/j.mri.2023.03.009_bb0150 article-title: Multimodal radiomic features for the predicting gleason score of prostate cancer publication-title: Cancers (Basel) doi: 10.3390/cancers10080249 contributor: fullname: Chaddad – volume: 5 start-page: 58 year: 2018 ident: 10.1016/j.mri.2023.03.009_bb0085 article-title: Correlation of apparent diffusion coefficient ratio on 3.0 T MRI with prostate cancer Gleason score publication-title: Eur J Radiol Open doi: 10.1016/j.ejro.2018.03.002 contributor: fullname: Jyoti – volume: 20 start-page: 151 issue: 1 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0025 article-title: Zonal adjusted PSA density improves prostate cancer detection rates compared with PSA in Taiwanese males with PSA <20 ng/mL publication-title: BMC Urol doi: 10.1186/s12894-020-00717-z contributor: fullname: Chang – volume: 115 start-page: 186 issue: 2 year: 2015 ident: 10.1016/j.mri.2023.03.009_bb0055 article-title: Prostate tumor delineation using multiparametric magnetic resonance imaging: inter-observer variability and pathology validation publication-title: Radiother Oncol doi: 10.1016/j.radonc.2015.04.012 contributor: fullname: Steenbergen – volume: 271 start-page: 368 issue: 5 year: 1994 ident: 10.1016/j.mri.2023.03.009_bb0130 article-title: Pathologic and clinical findings to predict tumor extent of nonpalpable (stage T1c) prostate cancer publication-title: JAMA. doi: 10.1001/jama.1994.03510290050036 contributor: fullname: Epstein – volume: 43 start-page: 1237 issue: 5 year: 2018 ident: 10.1016/j.mri.2023.03.009_bb0080 article-title: Comparison of quantitative apparent diffusion coefficient parameters with prostate imaging reporting and data system V2 assessment for detection of clinically significant peripheral zone prostate cancer publication-title: Abdom Radiol (NY) doi: 10.1007/s00261-017-1297-y contributor: fullname: Hassanzadeh – volume: 17 start-page: 3077 issue: 3 year: 2019 ident: 10.1016/j.mri.2023.03.009_bb0105 article-title: Application evaluation of DCE-MRI combined with quantitative analysis of DWI for the diagnosis of prostate cancer publication-title: Oncol Lett contributor: fullname: Ma – volume: 79 start-page: 450 year: 2014 ident: 10.1016/j.mri.2023.03.009_bb0145 article-title: The utility of diffusion weighted imaging (DWI) using apparent diffusion coefficient (ADC) values in discriminating between prostate cancer and normal tissue publication-title: Pol J Radiol doi: 10.12659/PJR.890805 contributor: fullname: Łuczyńska – volume: 202 start-page: 343 issue: 2 year: 2014 ident: 10.1016/j.mri.2023.03.009_bb0035 article-title: Accuracy of multiparametric MRI for prostate cancer detection: a meta-analysis publication-title: Am J Roentgenol doi: 10.2214/AJR.13.11046 contributor: fullname: de Rooij – volume: 45 start-page: 4133 issue: 12 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0045 article-title: Comparison of PI-RADS version 2.1 and PI-RADS version 2 regarding interreader variability and diagnostic accuracy for transition zone prostate cancer publication-title: Abdom Radiol doi: 10.1007/s00261-020-02738-6 contributor: fullname: Xu – volume: 43 start-page: 601 issue: 5 year: 1994 ident: 10.1016/j.mri.2023.03.009_bb0020 article-title: Serum PSA adjusted for volume of transition zone (PSAT) is more accurate than PSA adjusted for total gland volume (PSAD) in detecting adenocarcinoma of the prostate publication-title: Urology. doi: 10.1016/0090-4295(94)90170-8 contributor: fullname: Kalish – volume: 119 start-page: 225 issue: 2 year: 2017 ident: 10.1016/j.mri.2023.03.009_bb0030 article-title: Combination of prostate imaging reporting and data system (PI-RADS) score and prostate-specific antigen (PSA) density predicts biopsy outcome in prostate biopsy naïve patients publication-title: BJU Int doi: 10.1111/bju.13465 contributor: fullname: Washino – volume: 52 start-page: 577 issue: 2 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0040 article-title: Direct comparison of PI-RADS version 2 and 2.1 in transition zone lesions for detection of prostate cancer: preliminary experience publication-title: J Magn Reson Imaging doi: 10.1002/jmri.27080 contributor: fullname: Byun – volume: 115 start-page: 16 year: 2019 ident: 10.1016/j.mri.2023.03.009_bb0110 article-title: Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: cross-validation of a machine learning method publication-title: Eur J Radiol doi: 10.1016/j.ejrad.2019.03.010 contributor: fullname: Min – volume: 51 start-page: 242 issue: 1 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0090 article-title: Can mean ADC value and ADC ratio of benign prostate tissue to prostate cancer assist in the prediction of clinically significant prostate cancer within the PI-RADSv2 scoring system? publication-title: Egypt J Radiol Nucl Med doi: 10.1186/s43055-020-00347-3 contributor: fullname: Ragheb – volume: 9 start-page: 15997 issue: 22 year: 2018 ident: 10.1016/j.mri.2023.03.009_bb0095 article-title: Quantitative parameters in dynamic contrast-enhanced magnetic resonance imaging for the detection and characterization of prostate cancer publication-title: Oncotarget. doi: 10.18632/oncotarget.24652 contributor: fullname: Wei – volume: 57 start-page: 563 issue: 4 year: 2016 ident: 10.1016/j.mri.2023.03.009_bb0065 article-title: Correlation of intraprostatic tumor extent with 68Ga-PSMA distribution in patients with prostate cancer publication-title: J Nucl Med doi: 10.2967/jnumed.115.169243 contributor: fullname: Rahbar – volume: 7 start-page: 25 issue: 1 year: 2017 ident: 10.1016/j.mri.2023.03.009_bb0060 article-title: Quantitative 18F-fluorocholine positron emission tomography for prostate cancer: correlation between kinetic parameters and Gleason scoring publication-title: EJNMMI Res doi: 10.1186/s13550-017-0269-0 contributor: fullname: Schaefferkoetter – volume: 20 start-page: 33 issue: 1 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0140 article-title: How to develop a meaningful radiomic signature for clinical use in oncologic patients publication-title: Cancer Imaging doi: 10.1186/s40644-020-00311-4 contributor: fullname: Papanikolaou – volume: 10 start-page: 6555 year: 2015 ident: 10.1016/j.mri.2023.03.009_bb0010 article-title: Diagnosis of prostate cancer via nanotechnological approach publication-title: Int J Nanomedicine contributor: fullname: Kang – volume: 44 start-page: e87 issue: 8 year: 2020 ident: 10.1016/j.mri.2023.03.009_bb0125 article-title: The 2019 International Society of Urological Pathology (ISUP) consensus conference on grading of prostatic carcinoma publication-title: Am J Surg Pathol doi: 10.1097/PAS.0000000000001497 contributor: fullname: van Leenders |
SSID | ssj0005235 |
Score | 2.4669576 |
Snippet | The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This... INTRODUCTIONThe classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader... |
SourceID | proquest crossref pubmed elsevier |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 64 |
SubjectTerms | Gleason score (GS) Humans Machine Learning Machine learning (ML) Magnetic Resonance Imaging - methods Male Multiparametric magnetic resonance imaging (mpMRI) Neoplasm Grading Positron emission tomography (PET) Prostate-Specific Antigen Prostatic Neoplasms - pathology Quantitative parameters Radiomics Retrospective Studies |
Title | Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions |
URI | https://dx.doi.org/10.1016/j.mri.2023.03.009 https://www.ncbi.nlm.nih.gov/pubmed/36933775 https://search.proquest.com/docview/2791704160 |
Volume | 100 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1La9wwEBYhgdBLaZq03T6CCjkVnNWuZMk-hqXptmX3kgZyE7IexYX1urb32h-SX5sZ2Q7JIT0EDMaSzAjNWPpkzcxHyJnKCu6YE4ktbJEIafPEWBWSuVOzwPOQ-cixtFrL5bX4cZPe7JHFGAuDbpXD3N_P6XG2Hkqmw2hO67KcXqFxqjlstnjMYoI5QUXKkMXg_N9DN4-eZBMaJ9h6PNmMPl6bpjxH_vA-z2n-1Nr0FPaMa9DlK_JyAI_0ou_fEdnz1WtyuBqOx4_J7eKeVZBuA_27M1WMIYMZjWKO7w36vrTUVI42xpUYkEyDj6k9obSlZVXvOrx1W7qJXpaeDrQSv2nkzGkpVNUNSuwoYEf6DepRXIvpMFFojWEkAGCpRXtq4H38H9eekOvLr78Wy2QgX0gsT3mX8CCsdTZ4OZNSmZAxz20eLPOw5-KcA9ADbGUAAgCCMt6JmUhtYKwwDlPYCf6G7Ffbyr8jNATAHYWZyVwokRqVSZnNTaGUdYXLUzshX8Zh13WfY0OPzmd_NOhIo440g4vlEyJGxehHhqJhDfjfa59HJWr4gPBUxFR-u2v1XMGOlQEuZRPyttfufS-4zDlXKn3_PKEfyAt86r17P5L9rtn5T4BhuuI0GukpObj4_nO5vgPDXvOM |
link.rule.ids | 314,780,784,4502,24116,27924,27925,45585,45679 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELZKkYALKpTHQgFX6gkpXe_asZMjWrUs0O2lrdSb5fiBgrTZkGSv_SH9tcw4SQWHcqgUKZIfGsszGX8Tz4OQI5UV3DEnElvYIhHS5omxKiRzp2aB5yHzscbS6lwur8T36_R6hyzGWBh0qxx0f6_To7YeWqbDbk7rspxeoHCqORhbPGYxEY_IY5EC-gWhPr7528-jr7IJoxMcPl5tRievdVMeYwHxPtFpft_hdB_4jIfQ6R55PqBH-qVf4Auy46uX5MlquB_fJ7eLu7KCdBPo762pYhAZqDSKSb7X6PzSUlM52hhXYkQyDT7m9oTWlpZVve3w1W3oOrpZejrUlfhJY9GclkJX3SDFjgJ4pF-hH8m1mA8TidYYRwIIlloUqAbm4w-59hW5Oj25XCyTofpCYnnKu4QHYa2zwcuZlMqEjHlu82CZB6OLcw5ID8CVAQwAEMp4J2YitYGxwjjMYSf4a7JbbSr_ltAQAHgUZiZzoURqVCZlNjeFUtYVLk_thHwet13XfZINPXqf_dLAI4080gwelk-IGBmj_5EUDYfA_6YdjkzU8AXhtYip_Gbb6rkCk5UBMGUT8qbn7t0quMw5Vyp99zCin8jT5eXqTJ99O__xnjzDnt7V94Dsds3WfwBA0xUfo8D-AXyx9Sk |
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=Comparison+of+quantitative+parameters+and+radiomic+features+as+inputs+into+machine+learning+models+to+predict+the+Gleason+score+of+prostate+cancer+lesions&rft.jtitle=Magnetic+resonance+imaging&rft.au=Nai%2C+Ying-Hwey&rft.au=Cheong%2C+Dennis+Lai+Hong&rft.au=Roy%2C+Sharmili&rft.au=Kok%2C+Trina&rft.date=2023-07-01&rft.eissn=1873-5894&rft.volume=100&rft.spage=64&rft_id=info:doi/10.1016%2Fj.mri.2023.03.009&rft_id=info%3Apmid%2F36933775&rft.externalDocID=36933775 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0730-725X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0730-725X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0730-725X&client=summon |