Skip to main content
SpringerLink
Log in

Predicting muscle invasion in bladder cancer by deep learning analysis of MRI: comparison with vesical imaging–reporting and data system

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To compare the diagnostic performance of a novel deep learning (DL) method based on T2-weighted imaging with the vesical imaging–reporting and data system (VI-RADS) in predicting muscle invasion in bladder cancer (MIBC).

Methods

A total of 215 tumours (129 for training and 31 for internal validation, centre 1; 55 for external validation, centre 2) were included. MIBC was confirmed by pathological examination. VI-RADS scores were provided by two groups of radiologists (readers 1 and readers 2) independently. A deep convolutional neural network was constructed in the training set, and validation was conducted on the internal and external validation sets. ROC analysis was performed to evaluate the performance for MIBC diagnosis.

Results

The AUCs of the DL model, readers 1, and readers 2 were as follows: in the internal validation set, 0.963, 0.843, and 0.852, respectively; in the external validation set, 0.861, 0.808, and 0.876, respectively. The accuracy of the DL model in the tumours scored VI-RADS 2 or 3 was higher than that of radiologists in the external validation set: for readers 1, 0.886 vs. 0.600, p = 0.006; for readers 2, 0.879 vs. 0.636, p = 0.021. The average processing time (38 s and 43 s in two validation sets) of the DL method was much shorter than the readers, with a reduction of over 100 s in both validation sets.

Conclusions

Compared to radiologists using VI-RADS, the DL method had a better diagnostic performance, shorter processing time, and robust generalisability, indicating good potential for diagnosing MIBC.

Key Points

• The DL model shows robust performance for MIBC diagnosis in both internal and external validation.

• The diagnostic performance of the DL model in the tumours scored VI-RADS 2 or 3 is better than that obtained by radiologists using VI-RADS.

• The DL method shows potential in the preoperative assessment of MIBC.

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
Fig. 5

Similar content being viewed by others

Abbreviations

AUC:

Area under the receiver operating characteristic curve

BCa:

Bladder cancer

CI:

Confidence interval

DCE-MRI:

Dynamic contrast-enhanced MRI

DL:

Deep learning

DWI:

Diffusion-weighted imaging

Grad-CAM:

Gradient-weighted class activation mapping

MIBC:

Muscle-invasive bladder cancer

MRI:

Magnetic resonance imaging

NMIBC:

Non-muscle-invasive bladder cancer

NPV:

Negative predictive value

PPV:

Positive predictive value

ROC:

Receiver operating characteristic

T2WI:

T2-weighted imaging

T-SNE:

T-distributed stochastic neighbour embedding

TURBT:

Transurethral resection of the bladder tumour

VI-RADS:

Vesical imaging–reporting and data system

VOIs:

Volumes of interest

References

  1. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A (2018) Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 68:394–424

    Article  PubMed  Google Scholar 

  2. Wu XR (2005) Urothelial tumorigenesis: a tale of divergent pathways. Nat Rev Cancer 5:713–725

    Article  CAS  PubMed  Google Scholar 

  3. Witjes JA, Bruins HM, Cathomas R et al (2021) European Association of Urology Guidelines on Muscle-invasive and Metastatic Bladder Cancer: Summary of the 2020 Guidelines. Eur Urol 79:82–104

    Article  CAS  PubMed  Google Scholar 

  4. Cookson MS, Herr HW, Zhang ZF, Soloway S, Sogani PC, Fair WR (1997) The treated natural history of high risk superficial bladder cancer: 15-year outcome. J Urol 158:62–67

    Article  CAS  PubMed  Google Scholar 

  5. Chang SS, Boorjian SA, Chou R et al (2016) Diagnosis and treatment of non-muscle invasive bladder cancer: AUA/SUO guideline. J Urol 196:1021–1029

    Article  PubMed  Google Scholar 

  6. Babjuk M, Bohle A, Burger M et al (2017) EAU guidelines on non-muscle-invasive urothelial carcinoma of the bladder: update 2016. Eur Urol 71:447–461

    Article  PubMed  Google Scholar 

  7. Josephson D, Pasin E, Stein JP (2014) Superficial bladder cancer: part 2. Management. Expert Rev Antican Ther 7:567–581

  8. Sherif A, Jonsson MN, Wiklund NP (2007) Treatment of muscle-invasive bladder cancer. Expert Rev Anticancer Ther 7:1279–1283

    Article  PubMed  Google Scholar 

  9. Panebianco V, De Berardinis E, Barchetti G et al (2017) An evaluation of morphological and functional multi-parametric MRI sequences in classifying non-muscle and muscle invasive bladder cancer. Eur Radiol 27:3759–3766

    Article  PubMed  Google Scholar 

  10. Panebianco V, Narumi Y, Altun E et al (2018) Multiparametric magnetic resonance imaging for bladder cancer: development of VI-RADS (vesical imaging-reporting and data system). Eur Urol 74:294–306

    Article  PubMed  PubMed Central  Google Scholar 

  11. Barchetti G, Simone G, Ceravolo I et al (2019) Multiparametric MRI of the bladder: inter-observer agreement and accuracy with the Vesical imaging-reporting and data system (VI-RADS) at a single reference center. Eur Radiol 29:5498–5506

    Article  PubMed  Google Scholar 

  12. Feng C, Wang Y, Dan G et al (2021) Evaluation of a fractional-order calculus diffusion model and bi-parametric VI-RADS for staging and grading bladder urothelial carcinoma. Eur Radiol 32:890–900

    Article  PubMed  Google Scholar 

  13. Akcay A, Yagci AB, Celen S, Ozlulerden Y, Turk NS, UFUK F (2021) VI-RADS score and tumor contact length in MRI: a potential method for the detection of muscle invasion in bladder cancer. Clin Imaging 77:25–36

    Article  PubMed  Google Scholar 

  14. Zheng Z, Xu F, Gu Z et al (2021) Combining multiparametric MRI radiomics signature with the vesical imaging-reporting and data system (VI-RADS) score to preoperatively differentiate muscle invasion of bladder cancer. Front Oncol. https://doi.org/10.3389/fonc.2021.619893

  15. Zheng Z, Xu F, Gu Z et al (2021) Integrating multiparametric MRI radiomics features and the vesical imaging-reporting and data system (VI-RADS) for bladder cancer grading. Abdom Radiol 46:4311–4323

    Article  Google Scholar 

  16. Wang X, Tu N, Sun F et al (2021) Detecting muscle invasion of bladder cancer using a proposed magnetic resonance imaging strategy. J Magn Reson Imaging 54:1212–1221

    Article  PubMed  Google Scholar 

  17. Kufukihara R, Kikuchi E, Shigeta K et al (2021) Diagnostic performance of the vesical imaging-reporting and data system for detecting muscle-invasive bladder cancer in real clinical settings: comparison with diagnostic cystoscopy. Urol Oncol 40:611–618

    Article  Google Scholar 

  18. Wang H, Luo C, Zhang F et al (2019) Multiparametric MRI for bladder cancer: validation of VI-RADS for the detection of detrusor muscle invasion. Radiology 291:668–674

    Article  PubMed  Google Scholar 

  19. Metwally MI, Zeed NA, Hamed EM et al (2021) The validity, reliability, and reviewer acceptance of VI-RADS in assessing muscle invasion by bladder cancer: a multicenter prospective study. Eur Radiol 31:6949–6961

    Article  PubMed  Google Scholar 

  20. Wang H, Xu X, Zhang X et al (2020) Elaboration of a multisequence MRI-based radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer: a double-center study. Eur Radiol 30:4816–4827

    Article  PubMed  Google Scholar 

  21. Zhang G, Wu Z, Zhang X et al (2022) CT-based radiomics to predict muscle invasion in bladder cancer. Eur Radiol 32:3260–3268

    Article  CAS  PubMed  Google Scholar 

  22. Zhang G, Wu Z, Xu L et al (2021) Deep learning on enhanced CT images can predict the muscular invasiveness of bladder cancer. Front Oncol 11:654–685

    Google Scholar 

  23. Yushkevich PA, Piven J, Hazlett HC et al (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31:1116–1128

    Article  PubMed  Google Scholar 

  24. He K, Zhang X, Ren S, Sun J. (2016). Deep residual learning for image recognitionIEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.770-778

  25. Lin TY, Goyal P, Girshick R, He K, Dollar P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42:318–327

    Article  PubMed  Google Scholar 

  26. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. 10.48550/arXiv.1412.6980

  27. Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983. 10.48550/arXiv.1608.03983

  28. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) (Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision,, pp 618-626

  29. Van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605

    Google Scholar 

  30. Ueno Y, Tamada T, Takeuchi M et al (2021) VI-RADS: multiinstitutional multireader diagnostic accuracy and interobserver agreement study. AJR Am J Roentgenol 216:1257–1266

    Article  PubMed  Google Scholar 

Download references

Funding

This study has received funding by Dongguan Science and Technology of Social Development Program (20211800905212), Guangdong Basic and Applied Basic Research Foundation (2020A1515010571), and Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions (2021SHIBS0003).

Author information

Authors and Affiliations

  1. Department of Radiology, Affiliated Dongguan Hospital, Southern Medical University, Dongguan, Guangdong, China

    Jianpeng Li, Lei Deng, Shuiqing Yang, Yun Gao, Manqiu Liang, Kunlin Zhang & Yujian Zou

  2. Medical AI Lab, School of Biomedical Engineering, Health Science Centre, Shenzhen University, Shenzhen, China

    Kangyang Cao, Hongxin Lin, Chuxuan Lin, Zhaohong Pan, Peiyan Yue & Bingsheng Huang

  3. Imaging Department, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China

    Weijing Zhang & Chuanmiao Xie

  4. Department of Urology, Affiliated Dongguan Hospital, Southern Medical University, Dongguan, Guangdong, China

    Jiexin Luo

Authors
  1. Jianpeng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kangyang Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hongxin Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lei Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shuiqing Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yun Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Manqiu Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Chuxuan Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Weijing Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Chuanmiao Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Kunlin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Jiexin Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Zhaohong Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Peiyan Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Yujian Zou
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Bingsheng Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yujian Zou or Bingsheng Huang.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Prof. Bingsheng Huang.

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

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• multi-centre study

Additional information

Publisher’s note

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

Jianpeng Li and Kangyang Cao contributed to the work equally and should be regarded as co-first authors.

Supplementary Information

ESM 1

(DOCX 468 kb)

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

Li, J., Cao, K., Lin, H. et al. Predicting muscle invasion in bladder cancer by deep learning analysis of MRI: comparison with vesical imaging–reporting and data system. Eur Radiol 33, 2699–2709 (2023). https://doi.org/10.1007/s00330-022-09272-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-09272-7

Keywords

Search

Navigation