Skip to main content
SpringerLink
Log in

Deep learning imaging features derived from kidney ultrasounds predict chronic kidney disease progression in children with posterior urethral valves

  • Original Article
  • Published:
Pediatric Nephrology Aims and scope Submit manuscript

Abstract

Background

We sought to use deep learning to extract anatomic features from postnatal kidney ultrasounds and evaluate their performance in predicting the risk and timing of chronic kidney disease (CKD) progression for boys with posterior urethral valves (PUV). We hypothesized that these features would predict CKD progression better than clinical characteristics such as nadir creatinine alone.

Methods

We performed a retrospective cohort study of boys with PUV treated at two pediatric health systems from 1990 to 2021. Features of kidneys were extracted from initial postnatal kidney ultrasound images using a deep learning model. Three time-to-event prediction models were built using random survival forests. The Imaging Model included deep learning imaging features, the Clinical Model included clinical data, and the Ensemble Model combined imaging features and clinical data. Separate models were built to include time-dependent clinical data that were available at 6 months, 1 year, 3 years, and 5 years.

Results

Two-hundred and twenty-five patients were included in the analysis. All models performed well with C-indices of 0.7 or greater. The Clinical Model outperformed the Imaging Model at all time points with nadir creatinine driving the performance of the Clinical Model. Combining the 6-month Imaging Model (C-index 0.7; 95% confidence interval [CI] 0.6, 0.79) with the 6-month Clinical Model (C-index 0.79; 95% CI 0.71, 0.86) resulted in a 6-month Ensemble Model that performed better (C-index 0.82; 95% CI 0.77, 0.88) than either model alone.

Conclusions

Deep learning imaging features extracted from initial postnatal kidney ultrasounds may improve early prediction of CKD progression among children with PUV.

Graphical abstract

A higher resolution version of the Graphical abstract is available as Supplementary information

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. Krishnan A, de Souza A, Konijeti R, Baski LS (2006) The anatomy and embryology of posterior urethral valves. J Urol 175:1214–1220

    Article  Google Scholar 

  2. Gunn TR, Mora JD, Pease P (1995) Antenatal diagnosis of urinary tract abnormalities by ultrasonography after 28 weeks’ gestation: incidence and outcome. Am J Obstet Gynecol 172:479–486

    Article  CAS  Google Scholar 

  3. Heikkila J, Holmberg C, Kyllonen L, Rintala R et al (2011) Long-term risk of end stage renal disease in patients with posterior urethral valves. J Urol 186:2392–2396

    Article  Google Scholar 

  4. Neild GH (2009) What do we know about chronic renal failure in young adults? II. Adult outcome of pediatric renal disease. Pediatr Nephrol 24:1921–1928

    Article  Google Scholar 

  5. Groothoff J, Gruppen M, de Groot E, Offringa M (2005) Cardiovascular disease as a late complication of end-stage renal disease in children. Perit Dial Int 25:S123–S126

    Article  Google Scholar 

  6. Groothoff JW (2005) Long-term outcomes of children with end-stage renal disease. Pediatr Nephrol 20:849–853

    Article  CAS  Google Scholar 

  7. Groothoff JW, Offringa M, Van Eck-Smit BL, Gruppen MP et al (2003) Severe bone disease and low bone mineral density after juvenile renal failure. Kidney Int 63:266–275

    Article  Google Scholar 

  8. Dodson JL, Jerry-Fluker JV, Ng DK, Moxey-Mims M et al (2011) Urological disorders in chronic kidney disease in children cohort: clinical characteristics and estimation of glomerular filtration rate. J Urol 186:1460–1466

    Article  Google Scholar 

  9. Neild GH (2009) What do we know about chronic renal failure in young adults? I Primary renal disease Pediatr Nephrol 24:1913–1919

    Google Scholar 

  10. Heikkilä J, Holmberg C, Kyllonen L, Rintala R et al (2011) Long-term risk of end stage renal disease in patients with posterior urethral valves. J Urol 186:2392–2396

    Article  Google Scholar 

  11. Drozdz D, Drozdz M, Gretz N, Mohring K et al (1998) Progression to end-stage renal disease in children with posterior urethral valves. Pediatr Nephrol 12:630–636

    Article  CAS  Google Scholar 

  12. Lal R, Bhatnagar V, Mitra DK (1999) Long-term prognosis of renal function in boys treated for posterior urethral valves. Eur J Pediatr Surg 9:307–311

    Article  CAS  Google Scholar 

  13. DeFoor W, Clark C, Jackson E, Reddy P et al (2008) Risk factors for end stage renal disease in children with posterior urethral valves. J Urol 180:1705–1708

    Article  Google Scholar 

  14. Yin S, Peng Q, Li H, Zhang Z et al (2020) Multi-instance deep learning of ultrasound imaging data for pattern classification of congenital abnormalities of the kidney and urinary tract in children. Urology 142:183–189

    Article  Google Scholar 

  15. Yin S, Peng Q, Li H, Zhang Z et al (2020) Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks. Med Image Anal 60:101602

    Article  Google Scholar 

  16. Zheng Q, Furth SL, Tasian GE, Fan Y (2019) Computer-aided diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data by integrating texture image features and deep transfer learning image features. J Pediatr Urol 15:75.e1-75.e7

    Article  CAS  Google Scholar 

  17. Zheng Q, Tasian G, Fan Y (2018) Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data. Proc IEEE Int Symp Biomed Imaging 1487–1490

  18. Zhao X, Wu Y, Song G, Li Z et al (2018) A deep learning model integrating FCNNs and CRFs for brain tumor segmentation. Med Image Anal 43:98–111

    Article  Google Scholar 

  19. Harris PA, Taylor R, Thielke R, Payne J et al (2009) Research electronic data capture (REDCap)–a metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inform 42:377–381

    Article  Google Scholar 

  20. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. https://ieeexplore.ieee.org/document/7780459

  21. Coresh J, Turin TC, Matsushita K, Sang Y et al (2014) Decline in estimated glomerular filtration rate and subsequent risk of end-stage renal disease and mortality. JAMA 311:2518–2531

    Article  Google Scholar 

  22. Levey AS, Inker LA, Matsushita K, Greene T et al (2014) GFR decline as an end point for clinical trials in CKD: a scientific workshop sponsored by the National Kidney Foundation and the US Food and Drug Administration. Am J Kidney Dis 64:821–835

    Article  Google Scholar 

  23. Warady BA, Abraham AG, Schwartz GJ, Wong CS et al (2015) Predictors of rapid progression of glomerular and nonglomerular kidney disease in children and adolescents: the chronic kidney disease in children (CKiD) cohort. Am J Kidney Dis 65:878–888

    Article  Google Scholar 

  24. Pierce CB, Munoz A, Ng DK, Warady BA et al (2021) Age- and sex-dependent clinical equations to estimate glomerular filtration rates in children and young adults with chronic kidney disease. Kidney Int 99:948–956

    Article  CAS  Google Scholar 

  25. Viteri B, Elsingergy M, Roem J, Ng D et al (2021) Ultrasound-based renal parenchymal area and kidney function decline in infants with congenital anomalies of the kidney and urinary tract. Semin Nephrol 41:427–433

    Article  Google Scholar 

  26. Coleman R, King T, Nicoara C, Bader M et al (2015) Combined creatinine velocity and nadir creatinine: a reliable predictor of renal outcome in neonatally diagnosed posterior urethral valves. J Pediatr Urol 11:214.e1-e3

    Article  Google Scholar 

  27. Coleman R, King T, Nicoara CD, Bader M et al (2015) Nadir creatinine in posterior urethral valves: how high is low enough? J Pediatr Urol 11:356.e1-e5

    Article  CAS  Google Scholar 

  28. Kwong JC, Khondker A, Kim JK, Chua M et al (2022) Posterior urethral valves outcomes prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves. Pediatr Nephrol 37:1067–1074

    Article  Google Scholar 

  29. Vasconcelos MA, Silva AC, Gomes IR, Carvalho RA et al (2019) A clinical predictive model of chronic kidney disease in children with posterior urethral valves. Pediatr Nephrol 34:283–294

    Article  Google Scholar 

Download references

Funding

R21DK117297 NIH/NIDDK Anatomic Biomarkers of Chronic Kidney Disease, National Center for Advancing Translational Sciences of the National Institutes of Health under award number TL1TR001880 and 2UL1TR001878-06.

Author information

Authors and Affiliations

  1. Division of Pediatric Urology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    John K. Weaver, Joey Logan, Neeta D’Souza, Salima Shah, Antoine Selman, Katherine Fischer, Dana A. Weiss, Christopher J. Long & Greg E. Tasian

  2. Department of Urology, Rainbow Babies and Children’s Hospital, Case Western Reserve University School of Medicine, Cleveland, OH, USA

    John K. Weaver

  3. Division of Urology, Hospital for Sick Children, Toronto, ON, Canada

    Karen Milford, Mandy Rickard, Daniel Keefe & Armando Lorenzo

  4. Center for Pediatric Clinical Effectiveness, The Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    Joey Logan, Andy Cucchiara, Salima Shah, Antoine Selman & Greg E. Tasian

  5. Translational Research Informatics Group, The Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    Joey Logan

  6. Center for Computational Medicine, Hospital for Sick Children Research Institute, Toronto, ON, Canada

    Lauren Erdman & Marta Skreta

  7. Department of Computer Science, University of Toronto, Toronto, ON, Canada

    Lauren Erdman & Marta Skreta

  8. Division of Nephrology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    Bernarda Viteri

  9. Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

    Yong Fan

  10. Departments of Surgery and Biostatistics, Epidemiology, Perelman School of Medicine, University of Pennsylvania, & Informatics, Philadelphia, PA, USA

    Greg E. Tasian

  11. Surgery and Epidemiology, , The Children’s Hospital of Philadelphia, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, 19104, USA

    Greg E. Tasian

Authors
  1. John K. Weaver
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Karen Milford
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mandy Rickard
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joey Logan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lauren Erdman
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Bernarda Viteri
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Neeta D’Souza
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Andy Cucchiara
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Marta Skreta
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Daniel Keefe
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Salima Shah
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Antoine Selman
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Katherine Fischer
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Dana A. Weiss
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Christopher J. Long
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Armando Lorenzo
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Yong Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Greg E. Tasian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Greg E. Tasian.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Disclosures

None.

Additional information

Publisher's note

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

Supplementary information

Below is the link to the electronic supplementary material.

Graphical Abstract (PPTX 164 KB)

Rights and permissions

Springer Nature or its licensor 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

Weaver, J.K., Milford, K., Rickard, M. et al. Deep learning imaging features derived from kidney ultrasounds predict chronic kidney disease progression in children with posterior urethral valves. Pediatr Nephrol 38, 839–846 (2023). https://doi.org/10.1007/s00467-022-05677-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00467-022-05677-0

Keywords

Search

Navigation