Skip to main content
SpringerLink
Log in

Automatic PI-RADS assignment by means of formal methods

  • Magnetic Resonance Imaging
  • Published:
La radiologia medica Aims and scope Submit manuscript

Abstract

Introduction and objectives

The Prostate Imaging Reporting and Data System (PI-RADS) version 2 emerged as standard in prostate magnetic resonance imaging examination. The Pi-RADS scores are assigned by radiologists and indicate the likelihood of a clinically significant cancer. The aim of this paper is to propose a methodology to automatically mark a magnetic resonance imaging with its related PI-RADS.

Materials and methods

We collected a dataset from two different institutions composed by DWI ADC MRI for 91 patients marked by expert radiologists with different PI-RADS score. A formal model is generated starting from a prostate magnetic resonance imaging, and a set of properties related to the different PI-RADS scores are formulated with the help of expert radiologists and pathologists.

Results

Our methodology relies on the adoption of formal methods and radiomic features, and in the experimental analysis, we obtain a specificity and sensitivity equal to 1.Q

Conclusions

The proposed methodology is able to assign the PI-RADS score by analyzing prostate magnetic resonance imaging with a very high accuracy.

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
Fig. 4

Similar content being viewed by others

Notes

  1. https://pyradiomics.readthedocs.io

References

  1. Matthias R, Blondin D, Schlemmer HP, Franiel T (2013) Pi-rads classification: structured reporting for mri of the prostate. Rofo 185(3):253–261

    Google Scholar 

  2. Barentsz JO, Weinreb JC, Verma S, Thoeny HC, Tempany CM, Shtern F, Padhani AR, Margolis D, Macura KJ, Haider MA et al (2016) Synopsis of the pi-rads v2 guidelines for multiparametric prostate magnetic resonance imaging and recommendations for use. Eur Urol 69(1):41

    Article  Google Scholar 

  3. Fusco R, Sansone M, Petrillo A (2017) A comparison of fitting algorithms for diffusion-weighted mri data analysis using an intravoxel incoherent motion model. Magn Reson Mater Phys, Biol Med 30(2):113–120

    Article  CAS  Google Scholar 

  4. Hamoen Esther HJ, de Rooij M, Witjes JA, Barentsz JO, Rovers MM (2015) Use of the prostate imaging reporting and data system (pi-rads) for prostate cancer detection with multiparametric magnetic resonance imaging: a diagnostic meta-analysis. Eur Urol 67(6):1112–1121

    Article  CAS  Google Scholar 

  5. Tristan B, Baris T, Choyke Peter L (2015) Pi-rads version 2: what you need to know. Clin Radiol 70(11):1165–1176

    Article  Google Scholar 

  6. Roberta F, Mario S, Vincenza G, Venanzio SS, Antonella P (2017) A systematic review on multiparametric mr imaging in prostate cancer detection. Infect Agents Cancer 12(1):1–14

    Google Scholar 

  7. Sansone M, Fusco R, Petrillo A (2019) D-optimal design of b-values for precise intra-voxel incoherent motion imaging. Biomed Phys Eng Express 5(3):035025

    Article  Google Scholar 

  8. Roberta F, Vincenza G, Mauro MR, Paolo V, Pasquale DRA, Claudio S, Maurizio DB, Antonella P, Mario S (2021) Blood oxygenation level dependent magnetic resonance imaging (mri), dynamic contrast enhanced mri and diffusion weighted mri for benign and malignant breast cancer discrimination: A preliminary experience. Cancers 13(10):2421

    Article  Google Scholar 

  9. Yoon PS, Chul JD, Taik OY, Hoon CN, Deuk CY, Ho RK, Joon HS, Kyunghwa H (2016) Prostate cancer: Pi-rads version 2 helps preoperatively predict clinically significant cancers. Radiology 280(1):108–116

    Article  Google Scholar 

  10. Schoots Ivo G (2018) Mri in early prostate cancer detection: how to manage indeterminate or equivocal pi-rads 3 lesions? Transl Androl Urol 7(1):70

    Article  CAS  Google Scholar 

  11. Brunese L, Mercaldo F, Reginelli A, Santone A (2019) Neural networks for lung cancer detection through radiomic features. In: 2019 international joint conference on neural networks (IJCNN), pp 1–10. IEEE

  12. Till-Alexander H, Sherko K, Angela K, Hamami Monia E, Steffen H, Anton Q, Andreas B, Michael F, Thomas L, Gerald A et al (2010) Diagnostic value of diffusion-weighted magnetic resonance imaging (dwi) compared to fdg pet/ct for whole-body breast cancer staging. Eur J Nucl Med Mol Imag 37(6):1077–1086

    Article  Google Scholar 

  13. Iima M, Partridge SC, Le Bihan D (2020) Six dwi questions you always wanted to know but were afraid to ask: clinical relevance for breast diffusion mri. European Radiology, Springer, pp 1–10

  14. Kumar Virendra G, Yuhua BS, Anders B, Eschrich Steven A, Schabath Matthew B, Kenneth F, Aerts Hugo JWL, Andre D, David F et al (2012) Radiomics: the process and the challenges. Magn Reson Imag 30(9):1234–1248

    Article  CAS  Google Scholar 

  15. Stirling C (1989) An introduction to modal and temporal logics for CCS. UK/Japan Workshop on Concurrency, Springer, pp 1–20

  16. Brunese L, Mercaldo F, Reginelli A, Santone A (2020) Formal methods for prostate cancer gleason score and treatment prediction using radiomic biomarkers. Magn Reson Imaging 66:165–175

    Article  Google Scholar 

  17. Brunese L, Mercaldo F, Reginelli A, Santone A (2019) Prostate gleason score detection and cancer treatment through real-time formal verification. IEEE Access 7:186236–186246

    Article  Google Scholar 

  18. Milner R (1989) Communication and concurrency. PHI Series in computer science. Prentice Hall

  19. Cleaveland R, Li T, Sims S (2000) The concurrency workbench of the new century, version 1.2-user’s manual

  20. Leonardo R, Changhee H, Yudai N, Jin Z, Ryuichiro H, Carmelo M, Andrea T, Nobile Marco S, Claudio F, Daniela B et al (2019) Use-net: incorporating squeeze-and-excitation blocks into u-net for prostate zonal segmentation of multi-institutional mri datasets. Neurocomputing 365:31–43

    Article  Google Scholar 

  21. Tyler C, Junjie Z, Sameer B, Alexander W, Haider MA, Khalvati F (2017) Fully automated segmentation of prostate whole gland and transition zone in diffusion-weighted mri using convolutional neural networks. J Med Imag 4(4):041307

    Google Scholar 

  22. Lapa P, Castelli M, Gonçalves I, Sala E, Rundo L (2020) A hybrid end-to-end approach integrating conditional random fields into cnns for prostate cancer detection on mri. Appl Sci 10(1):338

    Article  Google Scholar 

  23. Wang Z, Liu C, Cheng D, Wang L, Yang X, Cheng K-T (2018) Automated detection of clinically significant prostate cancer in mp-mri images based on an end-to-end deep neural network. IEEE Trans Med Imag 37(5):1127–1139

    Article  Google Scholar 

  24. Patrick S, Simon K, Philipp RJ, Manuel W, Philipp K, Sebastian B, Anselm KT, Albrecht S, Markus H, Heinz-Peter S et al (2019) Classification of cancer at prostate mri: deep learning versus clinical pi-rads assessment. Radiology 293(3):607–617

    Article  Google Scholar 

  25. Wang J, Chen-Jiang W, Bao M-L, Zhang J, Wang X-N, Zhang Y-D (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 

  26. David B, Simon K, Manuel W, Patrick S, Philipp RJ, Michael G, Philipp K, Kaneschka Y, Bertram H, Nils G et al (2018) Radiomic machine learning for characterization of prostate lesions with mri: comparison to adc values. Radiology 289(1):128–137

    Article  Google Scholar 

  27. Chen T, Li M, Gu Y, Zhang Y, Yang S, Wei C, Wu J, Li X, Zhao W, Shen J (2019) Prostate cancer differentiation and aggressiveness: assessment with a radiomic-based model vs. pi-rads v2. J Magn Reson Imag 49(3):875–884

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, Campobasso, Italy

    Luca Brunese, Maria Chiara Brunese, Francesco Mercaldo & Antonella Santone

  2. Dipartimento Diagnostico per Immagini U.O.C. di Radiologia, Ospedale San Giovanni di Dio e Ruggi d’Aragona, Salerno, Italy

    Mattia Carbone & Vincenzo Ciccone

Authors
  1. Luca Brunese
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Maria Chiara Brunese
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mattia Carbone
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Vincenzo Ciccone
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Francesco Mercaldo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Antonella Santone
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Francesco Mercaldo.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest. This research involves human participants. The informed consent was obtained from all participants to the study.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Brunese, L., Brunese, M.C., Carbone, M. et al. Automatic PI-RADS assignment by means of formal methods. Radiol med 127, 83–89 (2022). https://doi.org/10.1007/s11547-021-01431-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11547-021-01431-y

Keywords

Search

Navigation