Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Clinical Studies

High-throughput precision MRI assessment with integrated stack-ensemble deep learning can enhance the preoperative prediction of prostate cancer Gleason grade

British Journal of Cancer volume 128, pages 1267–1277 (2023)Cite this article

Subjects

Abstract

Background

To develop and test a Prostate Imaging Stratification Risk (PRISK) tool for precisely assessing the International Society of Urological Pathology Gleason grade (ISUP-GG) of prostate cancer (PCa).

Methods

This study included 1442 patients with prostate biopsy from two centres (training, n = 672; internal test, n = 231 and external test, n = 539). PRISK is designed to classify ISUP-GG 0 (benign), ISUP-GG 1, ISUP-GG 2, ISUP-GG 3 and ISUP GG 4/5. Clinical indicators and high-throughput MRI features of PCa were integrated and modelled with hybrid stacked-ensemble learning algorithms.

Results

PRISK achieved a macro area-under-curve of 0.783, 0.798 and 0.762 for the classification of ISUP-GGs in training, internal and external test data. Permitting error ±1 in grading ISUP-GGs, the overall accuracy of PRISK is nearly comparable to invasive biopsy (train: 85.1% vs 88.7%; internal test: 85.1% vs 90.4%; external test: 90.4% vs 94.2%). PSA ≥ 20 ng/ml (odds ratio [OR], 1.58; p = 0.001) and PRISK ≥ GG 3 (OR, 1.45; p = 0.005) were two independent predictors of biochemical recurrence (BCR)-free survival, with a C-index of 0.76 (95% CI, 0.73–0.79) for BCR-free survival prediction.

Conclusions

PRISK might offer a potential alternative to non-invasively assess ISUP-GG of PCa.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: The pipeline of integrative PRISK analysis.
Fig. 2: Construction of six MRI biomarkers with a stepwise stacked-ensemble learning.
Fig. 3: Interpretable PRISK model to derive 5 risk calculators for each ISUP Gleason grade assessment.
Fig. 4: Head-to-head comparison of diagnostic performance of PRISK versus biopsy for ISUP GGs.
Fig. 5: Incremental value of imaging biomarkers to clinical factors for ISUP GG classification.
Fig. 6: Predictive aspect of PRISK for biochemical recurrence (BCR)-free survival.

Similar content being viewed by others

Data availability

The image data from internal and external institutions are not publicly available due to the data privacy and restricted permissions of the current study. The anonymized data are available under restricted access for patient privacy, access can be obtained by sending a request to the corresponding author YDZ for academic purposes. The raw patient data are protected and are not available due to data privacy laws.

Code availability

Source code for analysis of radiomics and deep image embedders is archived on GitHub (https://github.com/salan668/FAE/issues/58; https://github.com/biolab/orange3). Source code of PRISK model is archived on a use of R packages (“glmnet”, “ggplot2” and “caret”).

References

  1. Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022;72:7–33.

    Article  PubMed  Google Scholar 

  2. Verhoef EI, Kweldam CF, Kümmerlin IP, Nieboer D, Bangma CH, Incrocci L, et al. Characteristics and outcome of prostate cancer patients with overall biopsy Gleason score 3 + 4 = 7 and highest Gleason score 3 + 4 = 7 or > 3 + 4 = 7. Histopathology. 2018;72:760–5.

    Article  PubMed  Google Scholar 

  3. Cornford P, Bellmunt J, Bolla M, Briers E, De Santis M, Gross T, et al. EAU-ESTRO-SIOG Guidelines on Prostate Cancer. Part II: Treatment of Relapsing, Metastatic, and Castration-Resistant Prostate Cancer. Eur Urol. 2017;71:630–42.

    Article  PubMed  Google Scholar 

  4. Mottet N, Bellmunt J, Bolla M, Briers E, Cumberbatch MG, De Santis M, et al. EAU-ESTRO-SIOG Guidelines on Prostate Cancer. Part 1: Screening, Diagnosis, and Local Treatment with Curative Intent. Eur Urol. 2017;71:618–29.

    Article  PubMed  Google Scholar 

  5. Porten SP, Whitson JM, Cowan JE, Cooperberg MR, Shinohara K, Perez N, et al. Changes in prostate cancer grade on serial biopsy in men undergoing active surveillance. J Clin Oncol. 2011;29:2795–2800.

    Article  PubMed  Google Scholar 

  6. Epstein JI, Feng Z, Trock BJ, Pierorazio PM. Upgrading and downgrading of prostate cancer from biopsy to radical prostatectomy: incidence and predictive factors using the modified Gleason grading system and factoring in tertiary grades. Eur Urol. 2012;61:1019–24.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Schroder FH, Hugosson J, Roobol MJ, Tammela TL, Ciatto S, Nelen V, et al. Screening and prostate-cancer mortality in a randomized European study. N Engl J Med. 2009;360:1320–8.

    Article  PubMed  Google Scholar 

  8. Zhu X, Albertsen PC, Andriole GL, Roobol MJ, Schroder FH, Vickers AJ. Risk-based prostate cancer screening. Eur Urol. 2012;61:652–61.

    Article  PubMed  Google Scholar 

  9. Stabile A, Giganti F, Rosenkrantz AB, Taneja SS, Villeirs G, Gill IS, et al. Multiparametric MRI for prostate cancer diagnosis: current status and future directions. Nat Rev Urol. 2020;17:41–61.

    Article  PubMed  Google Scholar 

  10. Ullrich T, Arsov C, Quentin M, Mones F, Westphalen AC, Mally D, et al. Multiparametric magnetic resonance imaging can exclude prostate cancer progression in patients on active surveillance: a retrospective cohort study. Eur Radiol. 2020. https://doi.org/10.1007/s00330-020-06997-1.

  11. Gandaglia G, Ploussard G, Valerio M, Mattei A, Fiori C, Roumiguié M, et al. The key combined value of multiparametric magnetic resonance imaging, and magnetic resonance imaging-targeted and concomitant systematic biopsies for the prediction of adverse pathological features in prostate cancer patients undergoing radical prostatectomy. Eur Urol. 2020;77:733–41.

    Article  PubMed  Google Scholar 

  12. Zhang Y, Chen W, Yue X, Shen J, Gao C, Pang P, et al. Development of a novel, multi-parametric, MRI-based radiomic nomogram for differentiating between clinically significant and insignificant prostate cancer. Front Oncol. 2020;10:888.

    Article  PubMed  PubMed Central  Google Scholar 

  13. Zhao K, Wang C, Hu J, Yang X, Wang H, Li F, et al. Prostate cancer identification: quantitative analysis of T2-weighted MR images based on a back propagation artificial neural network model. Sci China Life Sci. 2015;58:666–73.

    Article  PubMed  Google Scholar 

  14. Wu D, Jiang K, Li H, Zhang Z, Ba R, Zhang Y, et al. Time-dependent diffusion MRI for quantitative microstructural mapping of prostate cancer. Radiology. 2022;303:578–87.

    Article  PubMed  Google Scholar 

  15. Bulten W, Pinckaers H, van Boven H, Vink R, de Bel T, van Ginneken B, et al. Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol. 2020;21:233–41.

    Article  PubMed  Google Scholar 

  16. Bonekamp D, Kohl S, Wiesenfarth M, Schelb P, Radtke JP, Gotz M, et al. Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values. Radiology. 2018;289:128–37.

    Article  PubMed  Google Scholar 

  17. Fehr D, Veeraraghavan H, Wibmer A, Gondo T, Matsumoto K, Vargas HA, et al. Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci USA 2015;112:E6265–6273.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Saha A, Hosseinzadeh M, Huisman H. End-to-end prostate cancer detection in bpMRI via 3D CNNs: Effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med image Anal. 2021;73:102155.

    Article  PubMed  Google Scholar 

  19. Hosseinzadeh M, Saha A, Brand P, Slootweg I, de Rooij M, Huisman H. Deep learning-assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge. Eur Radiol. 2022;32:2224–34.

    Article  CAS  PubMed  Google Scholar 

  20. Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol. 2017;18:570–84.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Godec P, Pancur M, Ilenic N, Copar A, Strazar M, Erjavec A, et al. Democratized image analytics by visual programming through integration of deep models and small-scale machine learning. Nat Commun. 2019;10:4551.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Deepak S, Ameer PM. Brain tumor classification using deep CNN features via transfer learning. Computers Biol Med. 2019;111:103345.

    Article  CAS  Google Scholar 

  23. Wang K, Lu X, Zhou H, Gao Y, Zheng J, Tong M, et al. Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study. Gut. 2019;68:729–41.

    Article  CAS  PubMed  Google Scholar 

  24. Zhang X, Liang M, Yang Z, Zheng C, Wu J, Ou B, et al. Deep learning-based radiomics of B-mode ultrasonography and shear-wave elastography: improved performance in breast mass classification. Front Oncol. 2020;10:1621.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Zheng X, Yao Z, Huang Y, Yu Y, Wang Y, Liu Y, et al. Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer. Nat Commun. 2020;11:1236.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Zhou L, Zhang Z, Chen YC, Zhao ZY, Yin XD, Jiang HB. A deep learning-based radiomics model for differentiating benign and malignant renal tumors. Transl Oncol. 2019;12:292–300.

    Article  PubMed  Google Scholar 

  27. Dong D, Fang MJ, Tang L, Shan XH, Gao JB, Giganti F, et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: an international multicenter study. Ann Oncol. 2020;31:912–20.

    Article  CAS  PubMed  Google Scholar 

  28. Cao R, Mohammadian Bajgiran A, Afshari Mirak S, Shakeri S, Zhong X, Enzmann D, et al. Joint prostate cancer detection and Gleason Score prediction in mp-MRI via FocalNet. IEEE Trans Med imaging. 2019;38:2496–506.

    Article  PubMed  Google Scholar 

  29. Brunese L, Mercaldo F, Reginelli A, Santone A. Radiomics for Gleason Score detection through deep learning. Sensors. 2020;20:5411.

  30. Turkbey B, Rosenkrantz AB, Haider MA, Padhani AR, Villeirs G, Macura KJ, et al. Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2. Eur Urol. 2019;76:340–51.

    Article  PubMed  Google Scholar 

  31. Hansen N, Patruno G, Wadhwa K, Gaziev G, Miano R, Barrett T, et al. Magnetic resonance and ultrasound image fusion supported transperineal prostate biopsy using the Ginsburg protocol: technique, learning points, and biopsy results. Eur Urol. 2016;70:332–40.

    Article  PubMed  Google Scholar 

  32. Epstein JI, Egevad L, Amin MB, Delahunt B, Srigley JR, Humphrey, PAJTAJOSP. The 2014 international society of urological pathology (ISUP) consensus conference on gleason grading of prostatic carcinoma definition of grading patterns and proposal for a new grading system. Am J Surg Pathol. 2015;40:244–52.

  33. Cookson MS, Aus G, Burnett AL, Canby-Hagino ED, D’Amico AV, Dmochowski RR, et al. Variation in the definition of biochemical recurrence in patients treated for localized prostate cancer: the American Urological Association Prostate Guidelines for Localized Prostate Cancer Update Panel report and recommendations for a standard in the reporting of surgical outcomes. J Urol. 2007;177:540–5.

    Article  CAS  PubMed  Google Scholar 

  34. Brockman JA, Alanee S, Vickers AJ, Scardino PT, Wood DP, Kibel AS, et al. Nomogram predicting prostate cancer-specific mortality for men with biochemical recurrence after radical prostatectomy. Eur Urol. 2015;67:1160–7.

    Article  PubMed  Google Scholar 

  35. Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW. elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med imaging. 2010;29:196–205.

    Article  PubMed  Google Scholar 

  36. Van Griethuysen JJ, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77:e104–e107.

    Article  PubMed  PubMed Central  Google Scholar 

  37. Xu X, Zhang HL, Liu QP, Sun SW, Zhang J, Zhu FP, et al. Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma. J Hepatol. 2019;70:1133–44.

    Article  PubMed  Google Scholar 

  38. Schaeffer E, Srinivas S, Antonarakis ES, Armstrong AJ, Bekelman JE, Cheng H, et al. NCCN Guidelines Insights: Prostate Cancer, Version 1.2021. J Natl Compr Cancer Netw. 2021;19:134–43.

    Article  CAS  Google Scholar 

  39. Mottet N, van den Bergh RCN, Briers E, Van den Broeck T, Cumberbatch MG, De Santis M, et al. EAU-EANM-ESTRO-ESUR-SIOG Guidelines on Prostate Cancer-2020 Update. Part 1: Screening, Diagnosis, and Local Treatment with Curative Intent. Eur Urol. 2021;79:243–62.

    Article  CAS  PubMed  Google Scholar 

  40. Epstein JI, Zelefsky MJ, Sjoberg DD, Nelson JB, Egevad L, Magi-Galluzzi C, et al. A contemporary prostate cancer grading system: a validated alternative to the Gleason Score. Eur Urol. 2016;69:428–35.

    Article  PubMed  Google Scholar 

  41. Patel HD, Tosoian JJ, Carter HB, Epstein JI. Adverse pathologic findings for men electing immediate radical prostatectomy: defining a favorable intermediate-risk group. JAMA Oncol. 2018;4:89–92.

    Article  PubMed  Google Scholar 

  42. Guazzoni G, Nava L, Lazzeri M, Scattoni V, Lughezzani G, Maccagnano C, et al. Prostate-specific antigen (PSA) isoform p2PSA significantly improves the prediction of prostate cancer at initial extended prostate biopsies in patients with total PSA between 2.0 and 10 ng/ml: results of a prospective study in a clinical setting. Eur Urol. 2011;60:214–22.

    Article  CAS  PubMed  Google Scholar 

  43. Alberts AR, Roobol MJ, Verbeek JFM, Schoots IG, Chiu PK, Osses DF, et al. Prediction of high-grade prostate cancer following multiparametric magnetic resonance imaging: improving the Rotterdam European Randomized Study of Screening for Prostate Cancer Risk Calculators. Eur Urol. 2019;75:310–8.

    Article  PubMed  Google Scholar 

  44. Ahdoot M, Wilbur AR, Reese SE, Lebastchi AH, Mehralivand S, Gomella PT, et al. MRI-targeted, systematic, and combined biopsy for prostate cancer diagnosis. N Engl J Med. 2020;382:917–28.

    Article  PubMed  PubMed Central  Google Scholar 

  45. Hamada R, Nakashima J, Ohori M, Ohno Y, Komori O, Yoshioka K, et al. Preoperative predictive factors and further risk stratification of biochemical recurrence in clinically localized high-risk prostate cancer. Int J Clin Oncol. 2016;21:595–600.

    Article  CAS  PubMed  Google Scholar 

  46. Van den Broeck T, van den Bergh RCN, Arfi N, Gross T, Moris L, Briers E, et al. Prognostic value of biochemical recurrence following treatment with curative intent for prostate cancer: a systematic review. Eur Urol. 2019;75:967–87.

    Article  PubMed  Google Scholar 

  47. Ahdoot M, Lebastchi AH, Long L, Wilbur AR, Gomella PT, Mehralivand S, et al. Using Prostate Imaging-Reporting and Data System (PI-RADS) Scores to Select an Optimal Prostate Biopsy Method: A Secondary Analysis of the Trio Study. Eur Urol Oncol. 2021. https://doi.org/10.1016/j.euo.2021.03.004.

  48. Siddiqui MM, Rais-Bahrami S, Truong H, Stamatakis L, Vourganti S, Nix J, et al. Magnetic resonance imaging/ultrasound-fusion biopsy significantly upgrades prostate cancer versus systematic 12-core transrectal ultrasound biopsy. Eur Urol. 2013;64:713–9.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

We thank all those who helped us during the writing of this research. We also thank the department of Ultrasound, Urology and Pathology of the two hospitals for their valuable help and feedback.

Funding

Contract grant sponsor: Key research and development program of Jiangsu Province; contract grant number: BE2017756 (to YDZ); Special Program for Diagnosis and Treatment Technology of Clinical Key Diseases in Suzhou; contract grant number: LCZX202001 (to XMW); Contract grant sponsor: Gusu health talent project of Suzhou;contract grant number: GSWS2020003 (to HCH).

Author information

Author notes

  1. These authors contributed equally: Jie Bao, Ying Hou.

Authors and Affiliations

  1. Department of Radiology, The First Affiliated Hospital of Soochow University, 188N, Shizi Road, 215006, Suzhou, Jiangsu, China

    Jie Bao, Xi-Ming Wang & Chun-Hong Hu

  2. Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300N, Guangzhou Road, 210029, Nanjing, Jiangsu, China

    Ying Hou, Lang Qin, Rui Zhi, Hai-Bin Shi & Yu-Dong Zhang

  3. Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China

    Hong-Zan Sun

Authors
  1. Jie Bao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ying Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lang Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rui Zhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xi-Ming Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hai-Bin Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Hong-Zan Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Chun-Hong Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Yu-Dong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

YDZ and CHH conceived, designed and supervised the project; JB, YH, LQ, RZ, XMW, HBS, HZS, CHH and YDZ collected and processed data and performed the research; JB, YH, RZ, XMW and YDZ performed imaging data annotation and clinical data review; YDZ proposed the model; YDZ and JB drafted the paper; all authors reviewed, edited and approved the final version of article.

Corresponding authors

Correspondence to Hong-Zan Sun, Chun-Hong Hu or Yu-Dong Zhang.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

This retrospective study was approved by local Institutional Review Board of the participating institutes (grant no. 2019-SR-396), and the informed consent was waived.

Consent to publish

Not applicable.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bao, J., Hou, Y., Qin, L. et al. High-throughput precision MRI assessment with integrated stack-ensemble deep learning can enhance the preoperative prediction of prostate cancer Gleason grade. Br J Cancer 128, 1267–1277 (2023). https://doi.org/10.1038/s41416-022-02134-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41416-022-02134-5

This article is cited by

Search

Advanced search

Quick links