Skip to main content

Advertisement

SpringerLink
Log in

Radiomics-based prognosis classification for high-risk prostate cancer treated with radiotherapy

  • Original Article
  • Published:
Strahlentherapie und Onkologie Aims and scope Submit manuscript

Abstract

Objective

The present study aimed to investigate if CT-based radiomics features could correlate to the risk of metastatic progression in high-risk prostate cancer patients treated with radical RT and long-term androgen deprivation therapy (ADT).

Materials and methods

A total of 157 patients were investigated and radiomics features extracted from the contrast-free treatment planning CT series. Three volumes were segmented: the prostate gland only (CTV_p), the prostate gland with seminal vesicles (CTV_psv), and the seminal vesicles only (CTV_sv). The patients were split into two subgroups of 100 and 57 patients for training and validation. Five clinical and 62 radiomics features were included in the analysis. Considering metastases-free survival (MFS) as an endpoint, the predictive model was used to identify the subgroups with favorable or unfavorable prognoses (separated by a threshold selected according to the Youden method). Pure clinical, pure radiomic, and combined predictive models were investigated.

Results

With a median follow-up of 30.7 months, the MFS at 1 and 3 years was 97.2% ± 1.5 and 92.1% ± 2.0, respectively. Univariate analysis identified seven potential predictors for MFS in the CTV_p group, 11 in the CTV_psv group, and 9 in the CTV_sv group. After elastic net reduction, these were 4 predictors for MFS in the CTV_p group (positive lymph nodes, Gleason score, H_Skewness, and NGLDM_Contrast), 5 in the CTV_psv group (positive lymph nodes, Gleason score, H_Skewnesss, Shape_Surface, and NGLDM_Contrast), and 6 in the CTV_sv group (positive lymph nodes, Gleason score, H_Kurtosis, GLCM_Correlation, GLRLM_LRHGE, and GLZLM_SZLGE). The patients’ group of the training and validation cohorts were stratified into favorable and unfavorable prognosis subgroups. For the combined model, for CTV_p, the mean MFS was 134 ± 14.5 vs. 96.9 ± 22.2 months for the favorable and unfavorable subgroups, respectively, and 136.5 ± 14.6 vs. 70.5 ± 4.3 months for CTV_psv and 150.0 ± 4.2 vs. 91.1 ± 8.6 months for CTV_sv, respectively.

Conclusion

Radiomic features were able to predict the risk of metastatic progression in high-risk prostate cancer. Combining the radiomic features and clinical characteristics can classify high-risk patients into favorable and unfavorable prognostic groups.

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

Similar content being viewed by others

References

  1. Gillies R, Schabath M (2020) Radiomics improves cancer screening and early detection. Cancer Epidemiol Biomarkers Prev 29:2556–2567

    Article  CAS  Google Scholar 

  2. Schick U, Lucia F, Bourbonne V, Dissaux G, Pradier O, Jaouen V et al (2020) Use of radiomics in the radiation oncology setting: Where do we stand and what do we need? Cancer/Radiothérapie 24:755–761

    Article  CAS  Google Scholar 

  3. Cozzi L, Comito T, Fogliata A, Franzese C, Franceschini D, Bonifacio C et al (2019) Computed tomography based radiomic signature as predictive of survival and local control after stereotactic body radiation therapy in pancreatic carcinoma. PLoS One 14:e0210758

    Article  CAS  Google Scholar 

  4. Cozzi L, Franzese C, Fogliata A, Franceschini D, Navarria P, Tomatis S et al (2019) Predicting survival and local control after radiochemotherapy in locally advanced head and neck cancer by means of computed tomography based radiomics. Strahlenther Onkol 195:805–818

    Article  Google Scholar 

  5. Wibmer A, Hricak H, Gondo T, Matsumoto K, Veeraraghavan H, Fehr D 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 

  6. Vignati A, Mazzetti S, Giannini V, Russo F, Bollito E, Porpiglia F et al (2015) Texture features on T2-weighted magnetic resonance imaging: New potential biomarkers for prostate cancer aggressiveness. Phys Med Biol 60:2685–2701

    Article  CAS  Google Scholar 

  7. Fehr D, Veeraraghavan H, Wibmer A, Gondo T, Matsumoto K, Vargas HA et al (2015) Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci U S A 112:E6265–73

    Article  CAS  Google Scholar 

  8. Mostafaei S, Abdollahi H, Kazempour Dehkordi S, Shiri I, Razzaghdoust A, Zoljalali Moghaddam SH et al (2020) CT imaging markers to improve radiation toxicity prediction in prostate cancer radiotherapy by stacking regression algorithm. Radiol Med 125:87–97

    Article  Google Scholar 

  9. National Comprehensive Cancer Network (2019) NCCN clinical practice guidelines in oncology: prostate cancer 2019. Version4. http://www.nccn.org

  10. Franzese C, Fogliata A, D’Agostino GR, Di Brina L, Comito T, Navarria P et al (2017) Moderate hypofractionated radiotherapy with volumetric modulated arc therapy and simultaneous integrated boost for pelvic irradiation in prostate cancer. J Cancer Res Clin Oncol 143:1301–1309

    Article  CAS  Google Scholar 

  11. Yao L, Shou J, Wang S, Song Y, Fang H, Lu N et al (2020) Long-term outcomes of moderately hypofractionated radiotherapy (67.5 Gy in 25 fractions) for prostate cancer confined to the pelvis: a single center retrospective analysis. Radiat Oncol 15:231

    Article  CAS  Google Scholar 

  12. Nioche C, Orlhac F, Boughdad S, Reuze S, Goya-Outi J, Robert C et al (2018) Lifex: A freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterisation of tumor heterogeneity. Cancer Res 78:4786–4789

    Article  CAS  Google Scholar 

  13. Collins GS, Reitsma JB, Altman DG, Moons KGM (2015) Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD Statement. Eur Urol 67:1142–1151

    Article  Google Scholar 

  14. Youden WJ (1950) Index for rating diagnostic tests. Cancer 3:32–35

    Article  CAS  Google Scholar 

  15. RDCT (2018) A Language and Environment for Statistical Computing. R Found. Stat. Comput., vol. 2. https://www.R-project.org

  16. Moris L, Cumberbatch MG, Van den Broeck T, Gandaglia G, Fossati N, Kelly B et al (2020) Benefits and risks of primary treatments for high-risk localized and locally advanced prostate cancer: an international multidisciplinary systematic review. Eur Urol 77:614–627

    Article  CAS  Google Scholar 

  17. Bolla M, Collette L, Blank L, Warde P, Dubois JB, Mirimanoff RO et al (2002) Long-term results with immediate androgen suppression and external irradiation in patients with locally advanced prostate cancer (an EORTC study): A phase III randomised trial. Lancet 360:103–108

    Article  CAS  Google Scholar 

  18. Ramón y Cajal S, Sesé M, Capdevila C, Aasen T, De Mattos-Arruda L, Diaz-Cano SJ et al (2020) Clinical implications of intratumor heterogeneity: challenges and opportunities. Mol Med 98:161–177

    Article  Google Scholar 

  19. Caswell DR, Swanton C (2017) The role of tumour heterogeneity and clonal cooperativity in metastasis, immune evasion and clinical outcome. BMC Med 15:133

    Article  Google Scholar 

  20. Schweizer MT, Zhou XC, Wang H, Yang T, Shaukat F, Partin AW et al (2013) Metastasis-free survival is associated with overall survival in men with PSA-recurrent prostate cancer treated with deferred androgen deprivation therapy. Ann Oncol 24:2881–2886

    Article  CAS  Google Scholar 

  21. Bosetti DG, Ruinelli L, Piliero MA, van der Gaag LC, Pesce GA, Valli M et al (2020) Cone-beam computed tomography-based radiomics in prostate cancer: a mono-institutional study. Strahlenther Onkol 196:943–951

    Article  Google Scholar 

  22. Osman S, Leijenaar R, Cole A, Lyons C, Hounsell A, Prise K et al (2019) Computed tomography-based radiomics for risk stratification in prostate cancer. Int J Radiat Oncol Biol Phys 105:448–456

    Article  Google Scholar 

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

    PubMed  Google Scholar 

  24. Bautista J, Houshyar R, Verma S, Uchio E, Lall C (2016) Prostate cancer on computed tomography: a direct comparison with multi-parametric magnetic resonance imaging and tissue pathology. Eur J Radiol 85:261–267

    Article  Google Scholar 

  25. Kim B, Kawashima A, Ryu J, Takahashi N, Hartman R, King B (2009) Imaging of the seminal vescicle and vas deferens. Radiographics 29(4):1105–1121

    Article  Google Scholar 

  26. Glazer D, Davenport M, Khalatbari S, Cohan R, Ellis J, Caoili E et al (2015) Mass-like peripheral zone enhancement on CT is predictive of higher grade (Gleason 4+3) and higher prostate cancer. Abdom Imaging 40(3):560–570

    Article  CAS  Google Scholar 

  27. Delgadillo R, Ford JC, Abramowitz MC, Dal Pra A, Pollack A, Stoyanova R (2020) The role of radiomics in prostate cancer radiotherapy. Strahlenther Onkol 196:900–912

    Article  Google Scholar 

  28. Gugliandolo SG, Pepa M, Isaksson LJ, Marvaso G, Raimondi S, Botta F et al (2020) 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

  29. Gnep K, Fargeas A, Gutiérrez-Carvajal RE, Commandeur F, Mathieu R, Ospina JD et al (2017) Haralick textural features on T 2 -weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer. J Magn Reson Imaging 45:103–117

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Radiotherapy and Radiosurgery Department, Humanitas Clinical and Research Center—IRCCS, via Manzoni 56, 20089, Rozzano (Mi), Italy

    Ciro Franzese MD, Luca Cozzi PhD, Marco Badalamenti MD, Davide Baldaccini MD, Giuseppe D’Agostino MD, Antonella Fogliata MSc, Pierina Navarria MD, Davide Franceschini MD, Tiziana Comito MD, Elena Clerici MD, Giacomo Reggiori MSc, Stefano Tomatis MSc & Marta Scorsetti MD

  2. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20090, Pieve Emanuele (Mi), Italy

    Ciro Franzese MD, Luca Cozzi PhD & Marta Scorsetti MD

Authors
  1. Ciro Franzese MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luca Cozzi PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marco Badalamenti MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Davide Baldaccini MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Giuseppe D’Agostino MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Antonella Fogliata MSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Pierina Navarria MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Davide Franceschini MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Tiziana Comito MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Elena Clerici MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Giacomo Reggiori MSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Stefano Tomatis MSc
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Marta Scorsetti MD
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Luca Cozzi PhD.

Ethics declarations

Conflict of interest

L. Cozzi acts as scientific advisor to Varian Medical Systems and is a clinical research scientist at Humanitas Cancer Center. C. Franzese, M. Badalamenti, D. Baldaccini, G. D’agostino, A. Fogliata, P. Navarria, D. Franceschini, T. Comito, E. Clerici, G. Reggiori, S. Tomatis, and M. Scorsetti declare that they have no competing interests.

Ethical standards

Ethics approval: the Ethics Committee of the Humanitas Cancer Center approved by notification this retrospective study. Consent to participate: all patients provided consent for retrospective studies at hospital admission.

Additional information

Availability of data and material

Data and material are available upon request to the corresponding author.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Franzese, C., Cozzi, L., Badalamenti, M. et al. Radiomics-based prognosis classification for high-risk prostate cancer treated with radiotherapy. Strahlenther Onkol 198, 710–718 (2022). https://doi.org/10.1007/s00066-021-01886-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00066-021-01886-y

Keywords

Search

Navigation