Skip to main content
SpringerLink
Log in

MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218)

  • Magnetic Resonance
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

Radiomic involves testing the associations of a large number of quantitative imaging features with clinical characteristics. Our aim was to extract a radiomic signature from axial T2-weighted (T2-W) magnetic resonance imaging (MRI) of the whole prostate able to predict oncological and radiological scores in prostate cancer (PCa).

Methods

This study included 65 patients with localized PCa treated with radiotherapy (RT) between 2014 and 2018. For each patient, the T2-W MRI images were normalized with the histogram intensity scale standardization method. Features were extracted with the IBEX software. The association of each radiomic feature with risk class, T-stage, Gleason score (GS), extracapsular extension (ECE) score, and Prostate Imaging Reporting and Data System (PI-RADS v2) score was assessed by univariate and multivariate analysis.

Results

Forty-nine out of 65 patients were eligible. Among the 1702 features extracted, 3 to 6 features with the highest predictive power were selected for each outcome. This analysis showed that texture features were the most predictive for GS, PI-RADS v2 score, and risk class; intensity features were highly associated with T-stage, ECE score, and risk class, with areas under the receiver operating characteristic curve (ROC AUC) ranging from 0.74 to 0.94.

Conclusions

MRI-based radiomics is a promising tool for prediction of PCa characteristics. Although a significant association was found between the selected features and all the mentioned clinical/radiological scores, further validations on larger cohorts are needed before these findings can be applied in the clinical practice.

Key Points

• A radiomic model was used to classify PCa aggressiveness.

• Radiomic analysis was performed on T2-W magnetic resonance images of the whole prostate gland.

• The most predictive features belong to the texture (57%) and intensity (43%) domains.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Abbreviations

ADC:

Apparent diffusion coefficient

AIRC:

Associazione Italiana per la Ricerca sul Cancro

AS:

Active surveillance

AUC:

Area under the curve

CI:

Confidence intervals

DCE:

Dynamic contrast-enhanced

DIL:

Dominant intraprostatic lesion

DWI:

Diffusion-weighted imaging

EBRT:

External beam radiotherapy

ECE:

Extracapsular extension

FDR:

False discovery rate

Gb-scale:

Generalized ball scale

GLCM:

Gray-level co-occurrence matrix

GLRLM:

Gray-level run length matrix

GOH:

Gradient orient histogram

GS:

Gleason score

G-scale:

Generalized scale

IH:

Intensity histogram

HT:

Hormone therapy

ID:

Intensity direct

IMRT-SIB:

Intensity-modulated radiation therapy simultaneous integrated boost

ISUP:

International Society of Urological Pathology

KW:

Kruskal-Wallis

mpMRI:

Multiparametric magnetic resonance imaging

NCCN:

National Comprehensive Cancer Network

NID:

Neighborhood intensity difference

PC:

Custom normalization based on healthy tissue intensities in the prostate

PCa:

Prostate cancer

PI-RADS:

Prostate imaging reporting and data system

PROMIS:

Prostate mr imaging study

PROTECT:

Prostate testing for cancer and treatment

PSA:

Prostate-specific antigen

PTEN:

Phosphatase and tensin homolog

ROC:

Receiver operating characteristics

ROI:

Regions of interest

RP:

Prostatectomy

RT:

Radiotherapy

T2-W:

T2-weighted

VOI:

Volume of interest

References

  1. Donovan JL, Hamdy FC, Lane JA et al (2016) Patient-reported outcomes after monitoring, surgery, or radiotherapy for prostate cancer. N Engl J Med 375(15):1425–1437

    Article  CAS  Google Scholar 

  2. National Comprehensive Cancer Network (NCCN). Prostate cancer. In: National Comprehensive Cancer Network Clinical Practice Guidelines in Oncology, version 2.2019-April 24, 2019. Available at: https://www.nccn.org/professionals/physician_gls/default.aspx Accessed: May 28, 2019

  3. Morgans (2018) Optimization of risk stratification in localized prostate cancer. J Clin Oncol 36(6):528–533

    Article  Google Scholar 

  4. Ahmed HU, Bosaily AE-S, Brown LC et al (2017) Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study. Lancet 389(10071):815–822

    Article  Google Scholar 

  5. Ma S, Xie H, Wang H et al (2019) MRI-based radiomics signature for the preoperative prediction of extracapsular extension of prostate cancer. J Magn Reson Imaging. 50(6):1914–1925

  6. Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun:1–8

  7. Nketiah G, Elschot M, Kim E et al (2017) T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results. Eur Radiol 27:3050–3059

    Article  Google Scholar 

  8. Wibmer A, Hricak H, Gondo T et al (2015) Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol 25:2840–2850

    Article  Google Scholar 

  9. Barentsz JO, Richenberg J, Clements R et al (2012) ESUR prostate MR guidelines 2012. Eur Radiol 22(4):746–757

    Article  Google Scholar 

  10. Timon G, Ciardo D, Bazani A et al (2018) Short-term high precision radiotherapy for early prostate cancer with concomitant boost to the dominant lesion: ad interim analysis and preliminary results of Phase II trial AIRC-IG-13218. Br J Radiol. 91(1089):20160725

  11. Zhang L, Fried DV, Fave XJ, Hunter LA, Yang J, Court LE (2015) IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics. Med Phys 42(3):1341–1353

    Article  Google Scholar 

  12. Nyul LG, Udupa JK (1999) On standardizing the MR image intensity scale. Magn Reson Med 42:072–1081

    Article  Google Scholar 

  13. Madabhushi A, Udupa JK, Souza A (2006) Generalized scale: theory, algorithms, and application to image inhomogeneity correction. Comput Vis Image Underst 101(2):100–121

    Article  Google Scholar 

  14. Madabhushi A, Udupa JK (2006) New methods of mr image intensity standardization via generalized scale. Med Phys 33(9):3426–3434

    Article  Google Scholar 

  15. Isaksson LJ, Raimondi S, Botta F et al (2020) Effects of MRI image normalization techniques in prostate cancer radiomics. Phys Med 71:7–13

    Article  Google Scholar 

  16. Perneger TV (1999) Adjusting for multiple testing in studies is less important than other concerns. BMJ 318(7193):1288

    Article  CAS  Google Scholar 

  17. Luzzago S, Petralia G, Musi G et al (2019) Multiparametric magnetic resonance imaging second opinion may reduce the number of unnecessary prostate biopsies: time to improve radiologists’ training program? Clin Genitourin Cancer 17(2):88–96

    Article  Google Scholar 

  18. Sonn GA, Fan RE, Ghanouni P et al (2017) Prostate magnetic resonance imaging interpretation varies substantially across radiologists. Eur Urol Focus. 5(4):592–599

  19. Hectors SJ, Cherny M, Yadav KK et al (2019) Radiomics features measured with multiparametric magnetic resonance imaging predict prostate cancer aggressiveness. J Urol. 02(3):498–505

  20. Cuocolo R, Stanzione A, Ponsiglione A et al (2019) Clinically significant prostate cancer detection on MRI: a radiomic shape features study. Eur J Radiol 116:144–149

    Article  Google Scholar 

  21. Schwier M, van Griethuysen J, Vangel MG et al (2019) Repeatability of multiparametric prostate MRI radiomics features. Sci Rep 9(1):9441

    Article  Google Scholar 

  22. Bianchini L, Botta F, Origgi D et al (2020) PETER PHAN: an MRI phantom for the optimisation of radiomic studies of the female pelvis. Phys Med 71:71–81

    Article  Google Scholar 

  23. Fehr D, Veeraraghavan H, Wibmer A et al (2015) Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci U S A 112(46):E6265–E6273

    Article  CAS  Google Scholar 

  24. Chaddad A, Niazi T, Probst S, Bladou F, Anidjar M, Bahoric B (2018) Predicting Gleason score of prostate cancer patients using radiomic analysis. Front Oncol 8

  25. Abdollahi H, Mofid B, Shiri I et al (2019) Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer. Radiol Med. 124(6):555–567

  26. Wang J, Wu CJ, Bao ML, Zhang J, Wang XN, Zhang YD (2017) Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer. Eur Radiol 27(10):4082–4090

    Article  Google Scholar 

  27. Algohary A, Viswanath S, Shiradkar R et al (2018) Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: preliminary findings. J Magn Reson Imaging 48(3):818–828

    Article  Google Scholar 

  28. Tanadini-Lang S, Bogowicz M, Veit-Haibach P et al (2018) Exploratory radiomics in computed tomography perfusion of prostate cancer. Anticancer Res 38(2):685–690

    PubMed  Google Scholar 

  29. Brooks FJ, Grigsby PW (2014) The effect of small tumor volumes on studies of intratumoral heterogeneity of tracer uptake. J Nucl Med 55(1):37–42

    Article  CAS  Google Scholar 

  30. Oommen T, Baise LG, Vogel RM (2011) Sampling bias and class imbalance in maximum-likelihood logistic regression. Math Geosci 43(1):99–120

    Article  Google Scholar 

  31. Kasivisvanathan V, Rannikko AS, Borghi M et al (2018) MRI-targeted or standard biopsy for prostate-cancer diagnosis. N Engl J Med 378(19):1767–1777

    Article  Google Scholar 

  32. Gao J, Jiang Q, Zhou B, Chen D (2019) Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: an overview. Math Biosci Eng 16(6):6536

    Article  Google Scholar 

Download references

Acknowledgments

LJI was partially supported by Associazione Italiana per la Ricerca sul Cancro (AIRC), by project IG-13218 “Short-term High Precision Radiotherapy for Early Prostate Cancer With Concomitant Boost on the Dominant Lesion,” registered at ClinicalTrials.gov (NCT01913717), and SGG by project IG-14300 “Carbon ions boost followed by pelvic photon intensity modulated radiotherapy for high-risk prostate cancer,” registered at ClinicalTrials.gov (NCT02672449). MP was supported by a research grant from Accuray Inc. entitled “Data collection and analysis of Tomotherapy and CyberKnife breast clinical studies, breast physics studies and prostate study.” The work was also partially supported by the Italian Ministry of Health with Ricerca Corrente and 5x1000 funds. The sponsors did not play any role in the study design, collection, analysis and interpretation of data, nor in the writing of the manuscript, nor in the decision to submit the manuscript for publication. All authors have participated in (a) conception and design, or analysis and interpretation of the data; (b) drafting the article or revising it critically for important intellectual content; and (c) approval of the final version.

This manuscript has not been submitted to, nor is under review at, another journal or other publishing venue.

Funding

The study was partially funded by Associazione Italiana per la Ricerca sul Cancro (AIRC) and by Accuray Inc.

Author information

Author notes

  1. Simone Giovanni Gugliandolo and Matteo Pepa contributed equally to this work.

Authors and Affiliations

  1. Division of Radiotherapy, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Simone Giovanni Gugliandolo, Matteo Pepa, Lars Johannes Isaksson, Giulia Marvaso, Delia Ciardo, Stefania Volpe, Giulia Riva, Damari Patricia Rojas, Dario Zerini & Barbara Alicja Jereczek-Fossa

  2. European School of Molecular Medicine, IFOM-IEO Campus, Via Adamello, 16, 20139, Milan, Italy

    Lars Johannes Isaksson

  3. Department of Oncology and Hemato-Oncology, University of Milan, Via Festa del Perdono 7, 20122, Milan, Italy

    Giulia Marvaso, Stefania Volpe, Giuseppe Petralia, Ottavio De Cobelli, Massimo Bellomi & Barbara Alicja Jereczek-Fossa

  4. Molecular and Pharmaco-Epidemiology Unit, Department of Experimental Oncology, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Sara Raimondi & Sara Gandini

  5. Medical Physics Unit, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Francesca Botta & Federica Cattani

  6. Clinical Department, National Center for Oncological Hadrontherapy (CNAO), Pavia, Italy

    Giulia Riva

  7. Division of Radiology, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Paola Pricolo, Sarah Alessi, Giuseppe Petralia, Paul Eugene Summers & Massimo Bellomi

  8. Division of Urology, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Frnacesco Alessandro Mistretta, Stefano Luzzago & Ottavio De Cobelli

  9. University of Milan, Via Festa del Perdono 7, 20122, Milan, Italy

    Frnacesco Alessandro Mistretta

  10. Breast Imaging Division, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Enrico Cassano

  11. Radiation Research Unit, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Marta Cremonesi

  12. Scientific Directorate, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, 20141, Milan, Italy

    Roberto Orecchia

Authors
  1. Simone Giovanni Gugliandolo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Matteo Pepa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lars Johannes Isaksson
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Giulia Marvaso
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sara Raimondi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Francesca Botta
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Sara Gandini
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Delia Ciardo
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Stefania Volpe
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Giulia Riva
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Damari Patricia Rojas
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Dario Zerini
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Paola Pricolo
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Sarah Alessi
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Giuseppe Petralia
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Paul Eugene Summers
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Frnacesco Alessandro Mistretta
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Stefano Luzzago
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Federica Cattani
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Ottavio De Cobelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Enrico Cassano
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Marta Cremonesi
    View author publications

    You can also search for this author in PubMed Google Scholar

  23. Massimo Bellomi
    View author publications

    You can also search for this author in PubMed Google Scholar

  24. Roberto Orecchia
    View author publications

    You can also search for this author in PubMed Google Scholar

  25. Barbara Alicja Jereczek-Fossa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Giulia Marvaso.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Prof. Barbara Alicja Jereczek-Fossa.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

Two of the authors are biostatisticians.

Informed consent

Written informed consent was obtained from all patients in this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Experimental

• Study performed at one institution

Additional information

Publisher’s note

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

The first affiliation was the affiliation at the time of data collection for authors Simone Giovanni Gugliandolo, Delia Ciardo and Giulia Riva.

Electronic supplementary material

ESM 1

(DOCX 41 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gugliandolo, S.G., Pepa, M., Isaksson, L.J. et al. MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218). Eur Radiol 31, 716–728 (2021). https://doi.org/10.1007/s00330-020-07105-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-07105-z

Keywords

Search

Navigation