Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format text download EPUB
file format pdf download PDF
side by side viewer icon HTML

Abstract

Introduction

It is not rare to experience a biochemical recurrence (BCR) following radical prostatectomy (RP) for prostate cancer (PCa). It has been reported that early detection and management of BCR following surgery could improve survival in PCa.

This study aimed to develop a nomogram integrating deep learning-based radiomic features and clinical parameters to predict 1-year BCR after RP and to examine the associations between radiomic scores and the tumor microenvironment (TME).

Methods

In this retrospective multicenter study, two independent cohorts of patients (n = 349) who underwent RP after multiparametric magnetic resonance imaging (mpMRI) between January 2015 and January 2022 were included in the analysis. Single-cell RNA sequencing data from four prospectively enrolled participants were used to investigate the radiomic score-related TME. The 3D U-Net was trained and optimized for prostate cancer segmentation using diffusion-weighted imaging, and radiomic features of the target lesion were extracted. Predictive nomograms were developed multivariate Cox proportional hazard regression analysis. The nomograms were assessed for discrimination, calibration, and clinical usefulness.

Results

In the development cohort, the clinical-radiomic nomogram had an AUC of 0.892 (95% confidence interval: 0.783--0.939), which was considerably greater than those of the radiomic signature and clinical model. The Hosmer–Lemeshow test demonstrated that the clinical-radiomic model performed well in both the development ( = 0.461) and validation ( = 0.722) cohorts.

Discussion

Decision curve analysis revealed that the clinical-radiomic nomogram displayed better clinical predictive usefulness than the clinical or radiomic signature alone in both cohorts. Radiomic scores were associated with a significant difference in the TME pattern.

Conclusion

Our study demonstrated the feasibility of a DWI-based clinical-radiomic nomogram combined with deep learning for the prediction of 1-year BCR. The findings revealed that the radiomic score was associated with a distinctive tumor microenvironment.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056403104250527045320
2025-06-10
2025-10-29

  • From This Site

    /content/journals/cmir/10.2174/0115734056403104250527045320
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056403104.html?itemId=/content/journals/cmir/10.2174/0115734056403104250527045320&mimeType=html&fmt=ahah

References

  1. LlewellynA. PhungT.H. O SoaresM. ShepherdL. GlynnD. HardenM. WalkerR. DuarteA. DiasS. MRI software and cognitive fusion biopsies in people with suspected prostate cancer: A systematic review, network meta-analysis and cost-effectiveness analysis.Health Technol. Assess.20242861131010.3310/PLFG421039367754
     [Google Scholar]
  2. MorganT.M. BoorjianS.A. BuyyounouskiM.K. ChapinB.F. ChenD.Y.T. ChengH.H. ChouR. JaceneH.A. KamranS.C. KimS.K. KirkbyE. LuckenbaughA.N. NathansonB.J. NyameY.A. PosadasE.M. TranP.T. ChenR.C. Salvage therapy for prostate cancer: AUA/ASTRO/SUO guideline part II: Treatment delivery for non-metastatic biochemical recurrence after primary radical prostatectomy.J. Urol.2024211451852510.1097/JU.000000000000389138421243
     [Google Scholar]
  3. MorizaneS. YumiokaT. MakishimaK. TsounapiP. IwamotoH. HikitaK. HondaM. UmekitaY. TakenakaA. Impact of positive surgical margin status in predicting early biochemical recurrence after robot-assisted radical prostatectomy.Int. J. Clin. Oncol.202126101961196710.1007/s10147‑021‑01977‑x34313905
     [Google Scholar]
  4. FalagarioU.G. AbbadiA. RemmersS. BjörneboL. BogdanovicD. MartiniA. ValdmanA. CarrieriG. MenonM. AkreO. EklundM. NordströmT. GrönbergH. LantzA. WiklundP. Biochemical recurrence and risk of mortality following radiotherapy or radical prostatectomy.JAMA Netw. Open202369e233290010.1001/jamanetworkopen.2023.3290037695584
     [Google Scholar]
  5. GandagliaG. LeniR. BrayF. FleshnerN. FreedlandS.J. KibelA. StattinP. Van PoppelH. La VecchiaC. Epidemiology and prevention of prostate cancer.Eur. Urol. Oncol.20214687789210.1016/j.euo.2021.09.00634716119
     [Google Scholar]
  6. BergengrenO. PekalaK.R. MatsoukasK. FainbergJ. MungovanS.F. BrattO. BrayF. BrawleyO. LuckenbaughA.N. MucciL. MorganT.M. CarlssonS.V. 2022 update on prostate cancer epidemiology and risk factors—a systematic review.Eur. Urol.202384219120610.1016/j.eururo.2023.04.02137202314
     [Google Scholar]
  7. PreisserF. Abrams-PompeR.S. StelwagenP.J. BöhmerD. ZattoniF. MagliA. RivasJ.G. DilmeR.V. SepulcriM. EguibarA. HeideggerI. ArnoldC. FankhauserC.D. ChunF.K.H. van der PoelH. GandagliaG. WiegelT. van den BerghR.C.N. TilkiD. EAU-YAU Prostate Cancer Working Group European association of urology biochemical recurrence risk classification as a decision tool for salvage radiotherapy—a multicenter study.Eur. Urol.202485216417010.1016/j.eururo.2023.05.03837355358
     [Google Scholar]
  8. HuC. QiaoX. HuC. CaoC. WangX. BaoJ. The practical clinical role of machine learning models with different algorithms in predicting prostate cancer local recurrence after radical prostatectomy.Cancer Imaging20242412310.1186/s40644‑024‑00667‑x38326860
     [Google Scholar]
  9. ZhaoL.T. LiuZ.Y. XieW.F. ShaoL.Z. LuJ. TianJ. LiuJ.G. What benefit can be obtained from magnetic resonance imaging diagnosis with artificial intelligence in prostate cancer compared with clinical assessments?Mil. Med. Res.20231012910.1186/s40779‑023‑00464‑w37357263
     [Google Scholar]
  10. TurkbeyB. RosenkrantzA.B. HaiderM.A. PadhaniA.R. VilleirsG. MacuraK.J. TempanyC.M. ChoykeP.L. CornudF. MargolisD.J. ThoenyH.C. VermaS. BarentszJ. WeinrebJ.C. Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2.Eur. Urol.201976334035110.1016/j.eururo.2019.02.03330898406
     [Google Scholar]
  11. ZhangJ. XuL. ZhangG. ZhangD. ZhangX. BaiX. ChenL. PengQ. JinZ. SunH. Multiparametric MRI to predict gleason score upgrading and downgrading at radical prostatectomy compared to presurgical biopsy.Korean J. Radiol.202526542243410.3348/kjr.2024.100840169496
     [Google Scholar]
  12. KrishnaS. LimC.S. McInnesM.D.F. FloodT.A. ShabanaW.M. LimR.S. SchiedaN. Evaluation of MRI for diagnosis of extraprostatic extension in prostate cancer.J. Magn. Reson. Imaging201847117618510.1002/jmri.2572928387981
     [Google Scholar]
  13. Dinis FernandesC. SimõesR. GhobadiG. HeijminkS.W.T.P.J. SchootsI.G. de JongJ. WalravenI. van der PoelH.G. van HoudtP.J. SmolicM. PosF.J. van der HeideU.A. Multiparametric MRI tumor probability model for the detection of locally recurrent prostate cancer after radiation therapy: Pathologic validation and comparison with manual tumor delineations.Int. J. Radiat. Oncol. Biol. Phys.2019105114014810.1016/j.ijrobp.2019.05.00331085288
     [Google Scholar]
  14. RodriguesA. RodriguesN. SantinhaJ. LisitskayaM.V. UysalA. MatosC. DominguesI. PapanikolaouN. Value of handcrafted and deep radiomic features towards training robust machine learning classifiers for prediction of prostate cancer disease aggressiveness.Sci. Rep.2023131620610.1038/s41598‑023‑33339‑037069257
     [Google Scholar]
  15. El NaqaI. HaiderM.A. GigerM.L. Ten HakenR.K. Artificial intelligence: Reshaping the practice of radiological sciences in the 21st century.Br. J. Radiol.20209311062019085510.1259/bjr.2019085531965813
     [Google Scholar]
  16. StrohmL. HehakayaC. RanschaertE.R. BoonW.P.C. MoorsE.H.M. Implementation of artificial intelligence (AI) applications in radiology: Hindering and facilitating factors.Eur. Radiol.202030105525553210.1007/s00330‑020‑06946‑y32458173
     [Google Scholar]
  17. AldojN. BiavatiF. MichallekF. StoberS. DeweyM. Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net.Sci. Rep.20201011431510.1038/s41598‑020‑71080‑032868836
     [Google Scholar]
  18. BhandaryS. KuhnD. BabaieeZ. FechterT. BenndorfM. ZamboglouC. GrosuA.L. GrosuR. Investigation and benchmarking of U-Nets on prostate segmentation tasks.Comput. Med. Imaging Graph.202310710224110.1016/j.compmedimag.2023.10224137201475
     [Google Scholar]
  19. HaroonU.M. O’Grady-CoyneS. DavisN.F. GullmannC. FordeJ.C. SmythG.P. PowerR.E. CheemaI.A. McLornanL. Intraductal carcinoma of the prostate in an Irish prostate cancer patient cohort—an aggressive pathology and a strong familial link.Prostate Int.20208310711110.1016/j.prnil.2020.02.00133102390
     [Google Scholar]
  20. SauerbreiW. RoystonP. BinderH. Selection of important variables and determination of functional form for continuous predictors in multivariable model building.Stat. Med.200726305512552810.1002/sim.314818058845
     [Google Scholar]
  21. DecaesteckerK. De MeerleerG. AmeyeF. FonteyneV. LambertB. JoniauS. DelrueL. BillietI. DuthoyW. JuniusS. HuysseW. LumenN. OstP. Surveillance or metastasis-directed therapy for oligo metastatic prostate cancer recurrence (STOMP): Study protocol for a randomized phase II trial.BMC Cancer201414167110.1186/1471‑2407‑14‑67125223986
     [Google Scholar]
  22. PunnenS. FreedlandS.J. PrestiJ.C.Jr AronsonW.J. TerrisM.K. KaneC.J. AmlingC.L. CarrollP.R. CooperbergM.R. Multi-institutional validation of the CAPRA-S score to predict disease recurrence and mortality after radical prostatectomy.Eur. Urol.20146561171117710.1016/j.eururo.2013.03.05823587869
     [Google Scholar]
  23. CooperbergM.R. DavicioniE. CrisanA. JenkinsR.B. GhadessiM. KarnesR.J. Combined value of validated clinical and genomic risk stratification tools for predicting prostate cancer mortality in a high-risk prostatectomy cohort.Eur. Urol.201567232633310.1016/j.eururo.2014.05.03924998118
     [Google Scholar]
  24. SandemanK. EineluotoJ.T. PohjonenJ. EricksonA. KilpeläinenT.P. JärvinenP. SanttiH. PetasA. MatikainenM. MarjasuoS. KenttämiesA. MirttiT. RannikkoA. Prostate MRI added to CAPRA, MSKCC and Partin cancer nomograms significantly enhances the prediction of adverse findings and biochemical recurrence after radical prostatectomy.PLoS One2020157e023577910.1371/journal.pone.023577932645056
     [Google Scholar]
  25. MerrimanK.M. HarmonS.A. BelueM.J. YilmazE.C. BlakeZ. LayN.S. PhelpsT.E. MerinoM.J. ParnesH.L. LawY.M. GurramS. WoodB.J. ChoykeP.L. PintoP.A. TurkbeyB. Comparison of MRI-based staging and pathologic staging for predicting biochemical recurrence of prostate cancer after radical prostatectomy.AJR Am. J. Roentgenol.2023221677378710.2214/AJR.23.2960937404084
     [Google Scholar]
  26. FengZ. LiH. LiuQ. DuanJ. ZhouW. YuX. ChenQ. LiuZ. WangW. RongP. CT radiomics to predict macrotrabecular-massive subtype and immune status in hepatocellular carcinoma.Radiology20233071e22129110.1148/radiol.22129136511807
     [Google Scholar]
  27. ShiradkarR. GhoseS. JamborI. TaimenP. EttalaO. PuryskoA.S. MadabhushiA. Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings.J. Magn. Reson. Imaging20184861626163610.1002/jmri.2617829734484
     [Google Scholar]
  28. AnP. LinY. HuY. QinP. YeY. GuW. LiX. SongP. FengG. Predicting model of biochemical recurrence of prostate carcinoma (PCa-BCR) using MR perfusion-weighted imaging-based radiomics.Technol. Cancer Res. Treat.2023221533033823116676610.1177/1533033823116676637016971
     [Google Scholar]
  29. VenteC. VosP. HosseinzadehM. PluimJ. VetaM. Deep learning regression for prostate cancer detection and grading in bi-parametric MRI.IEEE Trans. Biomed. Eng.202168237438310.1109/TBME.2020.299352832396068
     [Google Scholar]
  30. UshinskyA. BardisM. Glavis-BloomJ. UchioE. ChantadulyC. NguyentatM. ChowD. ChangP.D. HoushyarR. A 3D-2D hybrid U-net convolutional neural network approach to prostate organ segmentation of multiparametric MRI.AJR Am. J. Roentgenol.2021216111111610.2214/AJR.19.2216832812797
     [Google Scholar]
  31. ZhuJ. ZhangJ. QiuB. LiuY. LiuX. ChenL. Comparison of the automatic segmentation of multiple organs at risk in CT images of lung cancer between deep convolutional neural network-based and atlas-based techniques.Acta Oncol.201958225726410.1080/0284186X.2018.152942130398090
     [Google Scholar]
  32. KneeboneA. Fraser-BrowneC. DuchesneG.M. FisherR. FrydenbergM. HerschtalA. WilliamsS.G. BrownC. DelpradoW. HaworthA. JosephD.J. MartinJ.M. MatthewsJ.H.L. MillarJ.L. SidhomM. SpryN. TangC.I. TurnerS. WiltshireK.L. WooH.H. DavisI.D. LimT.S. PearseM. Adjuvant radiotherapy versus early salvage radiotherapy following radical prostatectomy (TROG 08.03/ANZUP RAVES): A randomised, controlled, phase 3, non-inferiority trial.Lancet Oncol.202021101331134010.1016/S1470‑2045(20)30456‑333002437
     [Google Scholar]
  33. SooriakumaranP. HaendlerL. NybergT. GronbergH. NilssonA. CarlssonS. HosseiniA. AddingC. JonssonM. PloumidisA. EgevadL. SteineckG. WiklundP. Biochemical recurrence after robot-assisted radical prostatectomy in a European single-centre cohort with a minimum follow-up time of 5 years.Eur. Urol.201262576877410.1016/j.eururo.2012.05.02422633365
     [Google Scholar]
  34. WangY. ZhuG.Q. YangR. WangC. QuW.F. ChuT.H. TangZ. YangC. YangL. ZhouC.W. MiaoG.Y. LiuW.R. ShiY.H. ZengM.S. Deciphering intratumoral heterogeneity of hepatocellular carcinoma with microvascular invasion with radiogenomic analysis.J. Transl. Med.202321173410.1186/s12967‑023‑04586‑637853415
     [Google Scholar]
  35. RussoL. BottazziS. KocakB. Zormpas-PetridisK. GuiB. StanzioneA. ImbriacoM. SalaE. CuocoloR. PonsiglioneA. Evaluating the quality of radiomics-based studies for endometrial cancer using RQS and METRICS tools.Eur. Radiol.202435120221410.1007/s00330‑024‑10947‑639014086
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056403104250527045320
Loading
DWI-based Biologically Interpretable Radiomic Nomogram for Predicting 1-year Biochemical Recurrence after Radical Prostatectomy: A Deep Learning, Multicenter Study
Curr. Med. Imaging 21, E15734056403104 (2025); https://doi.org/10.2174/0115734056403104250527045320
/content/journals/cmir/10.2174/0115734056403104250527045320
/content/journals/cmir/10.2174/0115734056403104250527045320
Loading

Data & Media loading...

Supplements

Supplementary material is available on the publisher’s website along with the published article.

file format download Download

  • Article Type:     Research Article
Keyword(s): Biochemical recurrence; Deep learning; Diffusion-weighted imaging; Prostate cancer; Radiomic; Tumor microenvironment

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test