Pilot study for generating and assessing nomograms and decision curves analysis to predict clinically significant prostate cancer using only spatially registered multi-parametric MRI.
Gleason score (GS)
decision curve analysis
multi-parametric magnetic resonance imaging (MP-MRI)
multiple variable regression
nomograms
prostate cancer
regularization
signal-to-clutter ratio (SCR)
Journal
Frontiers in oncology
ISSN: 2234-943X
Titre abrégé: Front Oncol
Pays: Switzerland
ID NLM: 101568867
Informations de publication
Date de publication:
2023
2023
Historique:
received:
10
10
2022
accepted:
04
01
2023
entrez:
10
2
2023
pubmed:
11
2
2023
medline:
11
2
2023
Statut:
epublish
Résumé
Current prostate cancer evaluation can be inaccurate and burdensome. To help non-invasive prostate tumor assessment, recent algorithms applied to spatially registered multi-parametric (SRMP) MRI extracted novel clinically relevant metrics, namely the tumor's eccentricity (shape), signal-to-clutter ratio (SCR), and volume. Conduct a pilot study to predict the risk of developing clinically significant prostate cancer using nomograms and employing Decision Curves Analysis (DCA) from the SRMP MRI-based features to help clinicians non-invasively manage prostate cancer. This study retrospectively analyzed 25 prostate cancer patients. MP-MRI (T1, T2, diffusion, dynamic contrast-enhanced) were resized, translated, and stitched to form SRMP MRI. Target detection algorithm [adaptive cosine estimator (ACE)] applied to SRMP MRI determines tumor's eccentricity, noise reduced SCR (by regularizing or eliminating principal components (PC) from the covariance matrix), and volume. Pathology assessed wholemount prostatectomy for Gleason score (GS). Tumors with GS >=4+3 (<=3+4) were judged as "Clinically Significant" ("Insignificant"). Logistic regression combined eccentricity, SCR, volume to generate probability distribution. Nomograms, DCA used all patients plus training (13 patients) and test (12 patients) sets. Area Under the Curves for (AUC) for Receiver Operator Curves (ROC) and p-values evaluated the performance. Combining eccentricity (0.45 ACE threshold), SCR (3, 4 PCs), SCR (regularized, modified regularization) with tumor volume (0.65 ACE threshold) improved AUC (>0.70) for ROC curves and p-values (<0.05) for logistic fit. DCA showed greater net benefit from model fit than univariate analysis, treating "all," or "none." Training/test sets achieved comparable AUC but with higher p-values. Performance of nomograms and DCA based on metrics derived from SRMP-MRI in this pilot study were comparable to those using prostate serum antigen, age, and PI-RADS.
Sections du résumé
Background
UNASSIGNED
Current prostate cancer evaluation can be inaccurate and burdensome. To help non-invasive prostate tumor assessment, recent algorithms applied to spatially registered multi-parametric (SRMP) MRI extracted novel clinically relevant metrics, namely the tumor's eccentricity (shape), signal-to-clutter ratio (SCR), and volume.
Purpose
UNASSIGNED
Conduct a pilot study to predict the risk of developing clinically significant prostate cancer using nomograms and employing Decision Curves Analysis (DCA) from the SRMP MRI-based features to help clinicians non-invasively manage prostate cancer.
Methods
UNASSIGNED
This study retrospectively analyzed 25 prostate cancer patients. MP-MRI (T1, T2, diffusion, dynamic contrast-enhanced) were resized, translated, and stitched to form SRMP MRI. Target detection algorithm [adaptive cosine estimator (ACE)] applied to SRMP MRI determines tumor's eccentricity, noise reduced SCR (by regularizing or eliminating principal components (PC) from the covariance matrix), and volume. Pathology assessed wholemount prostatectomy for Gleason score (GS). Tumors with GS >=4+3 (<=3+4) were judged as "Clinically Significant" ("Insignificant"). Logistic regression combined eccentricity, SCR, volume to generate probability distribution. Nomograms, DCA used all patients plus training (13 patients) and test (12 patients) sets. Area Under the Curves for (AUC) for Receiver Operator Curves (ROC) and p-values evaluated the performance.
Results
UNASSIGNED
Combining eccentricity (0.45 ACE threshold), SCR (3, 4 PCs), SCR (regularized, modified regularization) with tumor volume (0.65 ACE threshold) improved AUC (>0.70) for ROC curves and p-values (<0.05) for logistic fit. DCA showed greater net benefit from model fit than univariate analysis, treating "all," or "none." Training/test sets achieved comparable AUC but with higher p-values.
Conclusions
UNASSIGNED
Performance of nomograms and DCA based on metrics derived from SRMP-MRI in this pilot study were comparable to those using prostate serum antigen, age, and PI-RADS.
Identifiants
pubmed: 36761948
doi: 10.3389/fonc.2023.1066498
pmc: PMC9902912
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1066498Informations de copyright
Copyright © 2023 Mayer, Turkbey, Choyke and Simone.
Déclaration de conflit d'intérêts
RM works for Oncoscore. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Lancet Oncol. 2015 Apr;16(4):e173-80
pubmed: 25846097
Minerva Urol Nefrol. 2020 Oct;72(5):637-639
pubmed: 32495611
Front Oncol. 2020 Jun 30;10:888
pubmed: 32695660
Radiology. 2020 Jul;296(1):76-84
pubmed: 32315265
Minerva Urol Nephrol. 2022 Feb;74(1):29-37
pubmed: 33016030
Med Decis Making. 2006 Nov-Dec;26(6):565-74
pubmed: 17099194
Radiology. 2010 Apr;255(1):89-99
pubmed: 20308447
J Magn Reson Imaging. 1997 Jan-Feb;7(1):91-101
pubmed: 9039598
Minerva Urol Nephrol. 2021 Feb;73(1):128-129
pubmed: 33764029
Eur Urol. 2013 Dec;64(6):876-92
pubmed: 23787356
Prostate. 2022 Apr;82(5):556-565
pubmed: 35098557
Minerva Urol Nephrol. 2021 Aug;73(4):442-451
pubmed: 33769016
Rev Sci Instrum. 2009 Oct;80(10):104301
pubmed: 19895076
Prostate Int. 2020 Mar;8(1):10-15
pubmed: 32257972
Urology. 2004 Dec;64(6):1165-70
pubmed: 15596191
Quant Imaging Med Surg. 2022 Feb;12(2):1096-1108
pubmed: 35111607
J Digit Imaging. 2013 Dec;26(6):1045-57
pubmed: 23884657
J Urol. 2011 Nov;186(5):1818-24
pubmed: 21944089
Mod Pathol. 2005 Jul;18(7):886-90
pubmed: 15803186
Radiology. 2007 Jan;242(1):182-8
pubmed: 17090712
Urol Int. 2017;99(2):156-161
pubmed: 28391284
Urol Oncol. 2017 Nov;35(11):664.e11-664.e18
pubmed: 28801025
Quant Imaging Med Surg. 2021 Oct;11(10):4235-4244
pubmed: 34603979
Prostate. 2008 Nov 1;68(15):1674-80
pubmed: 18712715
J Med Imaging Radiat Oncol. 2018 Apr;62(2):183-187
pubmed: 28990727
Eur Urol. 2012 Dec;62(6):976-83
pubmed: 22698574
BMC Med Imaging. 2017 Feb 1;17(1):11
pubmed: 28143433
Ther Adv Urol. 2019 Aug 28;11:1756287219870074
pubmed: 31489033
Quant Imaging Med Surg. 2022 Jul;12(7):3844-3859
pubmed: 35782272
Biomed Res Int. 2018 Sep 12;2018:6368309
pubmed: 30276213
Curr Opin Urol. 2003 Mar;13(2):111-6
pubmed: 12584470
Quant Imaging Med Surg. 2022 Mar;12(3):1859-1870
pubmed: 35284265
Quant Imaging Med Surg. 2021 Jan;11(1):119-132
pubmed: 33392016
J Magn Reson Imaging. 1999 Sep;10(3):223-32
pubmed: 10508281
Eur Urol. 2016 Jan;69(1):16-40
pubmed: 26427566
Comput Biol Med. 2018 Mar 1;94:65-73
pubmed: 29407999