Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Clinical Research Article
  • Published:

CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center

Pediatric Research volume 94, pages 1104–1110 (2023)Cite this article

Abstract

Background

Deep learning (DL) is more and more widely used in children’s medical treatment. In this study, we have developed a computed tomography (CT)-based DL model for identifying undiagnosed non-Wilms tumors (nWTs) from pediatric renal tumors.

Methods

This study collected and analyzed the preoperative clinical data and CT images of pediatric renal tumor patients diagnosed by our center from 2008 to 2020, and established a DL model to identify nWTs noninvasively.

Results

A total of 364 children who had been confirmed by histopathology with renal tumors from our center were enrolled, including 269 Wilms tumors (WTs) and 95 nWTs. For DL model development, all cases were randomly allocated to training set (218 cases), validation set (73 cases), and test set (73 cases). In the test set, the DL model achieved area under the curve of 0.831 (95% CI: 0.712–0.951) in discriminating WTs from nWTs, with the accuracy, sensitivity, and specificity of 0.781, 0.563, and 0.842, respectively. The sensitivity of our model was higher than a radiologist with 15 years of experience.

Conclusions

We presented a DL model for identifying undiagnosed nWTs from pediatric renal tumors, with the potential to improve the image-based diagnosis.

Impact

  • Deep learning model was used for the first time to identify pediatric renal tumors in this study.

  • Deep learning model can identify non-Wilms tumors from pediatric renal tumors.

  • Deep learning model based on computed tomography images can improve tumor diagnosis rate.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: The outline of this study.
Fig. 2: The process of generating axis-aligned bounding boxes and selecting multiple image slices, and the neural network architecture of the DL model.
Fig. 3: The flowchart of the inclusion and exclusion of patients.
Fig. 4: The distribution ratios of different pathological types of kidney tumors in different age groups.
Fig. 5: The ROC curves of the training set, validation set, and test set in the classification of renal tumor types by DL model.

Similar content being viewed by others

Data availability

The datasets generated during and/or analyzed during the current study are not publicly available due to patient privacy concerns but are available from the corresponding authors on reasonable request.

References

  1. Nakata, K. et al. Incidence of childhood renal tumours: an international population-based study. Int J. Cancer 147, 3313–3327 (2020).

    CAS  PubMed  PubMed Central  Google Scholar 

  2. Pastore, G. et al. Malignant renal tumours incidence and survival in European children (1978-1997): report from the Automated Childhood Cancer Information System project. Eur. J. Cancer 42, 2103–2114 (2006).

    PubMed  Google Scholar 

  3. van den Heuvel-Eibrink, M. M. et al. Characteristics and survival of 750 children diagnosed with a renal tumor in the first seven months of life: a collaborative study by the SIOP/GPOH/SFOP, NWTSG, and UKCCSG Wilms tumor study groups. Pediatr. Blood Cancer 50, 1130–1134 (2008).

    PubMed  Google Scholar 

  4. Watson, T., Oostveen, M., Rogers, H., Pritchard-Jones, K. & Olsen, Ø. The role of imaging in the initial investigation of paediatric renal tumours. Lancet Child Adolesc. Health 4, 232–241 (2020).

    PubMed  Google Scholar 

  5. de la Monneraye, Y. et al. Indications and results of diagnostic biopsy in pediatric renal tumors: a retrospective analysis of 317 patients with critical review of SIOP guidelines. Pediatr. Blood Cancer 66, e27641 (2019).

    PubMed  Google Scholar 

  6. Chung, E. M., Graeber, A. R. & Conran, R. M. Renal tumors of childhood: radiologic-pathologic correlation part 1. The 1st decade: from the Radiologic Pathology Archives. Radiographics 36, 499–522 (2016).

    PubMed  Google Scholar 

  7. Chung, E. M. et al. Renal tumors of childhood: radiologic-pathologic correlation part 2. The 2nd decade: from the Radiologic Pathology Archives. Radiographics 37, 1538–1558 (2017).

    PubMed  Google Scholar 

  8. Agrons, G. A., Kingsman, K. D., Wagner, B. J. & Sotelo-Avila, C. Rhabdoid tumor of the kidney in children: a comparative study of 21 cases. AJR Am. J. Roentgenol. 168, 447–451 (1997).

    CAS  PubMed  Google Scholar 

  9. Chung, C. J. et al. Rhabdoid tumors of the kidney in children: CT findings. AJR Am. J. Roentgenol. 164, 697–700 (1995).

    CAS  PubMed  Google Scholar 

  10. Lambin, P. et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur. J. Cancer 48, 441–446 (2012).

    PubMed  PubMed Central  Google Scholar 

  11. He, B. et al. Predicting response to immunotherapy in advanced non-small-cell lung cancer using tumor mutational burden radiomic biomarker. J. Immunother. Cancer 8, e000550 (2020).

    PubMed  PubMed Central  Google Scholar 

  12. Dong, D. et al. Development and validation of a novel MR imaging predictor of response to induction chemotherapy in locoregionally advanced nasopharyngeal cancer: a randomized controlled trial substudy (NCT01245959). BMC Med. 17, 190 (2019).

    PubMed  PubMed Central  Google Scholar 

  13. Dong, D. et al. Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer. Ann. Oncol. 30, 431–438 (2019).

    CAS  PubMed  PubMed Central  Google Scholar 

  14. Ohshima, J. et al. Methylation of the RASSF1A promoter is predictive of poor outcome among patients with Wilms tumor. Pediatr. Blood Cancer 59, 499–505 (2012).

    PubMed  Google Scholar 

  15. Karmali, R. J., Suami, H., Wood, C. G. & Karam, J. A. Lymphatic drainage in renal cell carcinoma: back to the basics. BJU Int. 114, 806–817 (2014).

    PubMed  Google Scholar 

  16. Pritchard-Jones, K. & Hargrave, D. Declining childhood and adolescent cancer mortality: great progress but still much to be done. Cancer 120, 2388–239 (2014).

    PubMed  Google Scholar 

  17. Cattell, R. et al. Preoperative prediction of lymph node metastasis using deep learning-based features. Vis. Comput Ind. Biomed. Art. 5, 1–11 (2022).

    Google Scholar 

  18. Zhong, L. Z. et al. A deep learning MR-based radiomic nomogram may predict survival for nasopharyngeal carcinoma patients with stage T3N1M0. Radiother. Oncol. 151, 1–9 (2020).

    PubMed  Google Scholar 

  19. Dong, D. et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: an international multicenter study. Ann. Oncol. 31, 912–920 (2020).

    CAS  PubMed  Google Scholar 

  20. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    CAS  PubMed  Google Scholar 

  21. Zhu, X. et al. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur. Radio. 28, 2772–2778 (2018).

    Google Scholar 

  22. Siegel, M. J. & Chung, E. M. Wilms’ tumor and other pediatric renal masses. Magn. Reson. Imaging Clin. N. Am. 16, 479–497 (2008).

    PubMed  Google Scholar 

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

    PubMed  Google Scholar 

  24. Li, Q. et al. Development and validation of a deep learning algorithm to automatic detection of pituitary microadenoma from MRI. Front. Med. (Lausanne) 8, 758690 (2021).

    PubMed  Google Scholar 

  25. Argani, P. et al. Clear cell sarcoma of the kidney: a review of 351 cases from the National Wilms Tumor Study Group Pathology Center. Am. J. Surg. Pathol. 24, 4–18 (2000).

    CAS  PubMed  Google Scholar 

  26. Gooskens, S. L. et al. Clear cell sarcoma of the kidney: a review. Eur. J. Cancer 48, 2219–2226 (2012).

    CAS  PubMed  Google Scholar 

  27. Gooskens, S. L. et al. Congenital mesoblastic nephroma 50 years after its recognition: a narrative review. Pediatr. Blood Cancer 64, 1–9 (2017).

  28. van den Heuvel-Eibrink, M. M. et al. Malignant rhabdoid tumours of the kidney (MRTKs), registered on recent SIOP protocols from 1993 to 2005: a report of the SIOP renal tumour study group. Pediatr. Blood Cancer 56, 733–737 (2011).

    PubMed  Google Scholar 

  29. Tomlinson, G. E. et al. Rhabdoid tumor of the kidney in the National Wilms’ Tumor Study: age at diagnosis as a prognostic factor. J. Clin. Oncol. 23, 7641–7645 (2005).

    PubMed  Google Scholar 

  30. Aldera, A. P. & Pillay, K. Clear cell sarcoma of the kidney. Arch. Pathol. Lab. Med. 144, 119–123 (2020).

    CAS  PubMed  Google Scholar 

  31. van der Beek, J. N. et al. Characteristics and outcome of pediatric renal cell carcinoma patients registered in the International Society of Pediatric Oncology (SIOP) 93-01, 2001 and UK-IMPORT database: a report of the SIOP-Renal Tumor Study Group. Int J. Cancer 148, 2724–2735 (2021).

    PubMed  PubMed Central  Google Scholar 

  32. Geller, J. I. et al. Characterization of adolescent and pediatric renal cell carcinoma: a report from the Children’s Oncology Group study AREN03B2. Cancer 121, 2457–2464 (2015).

    PubMed  Google Scholar 

  33. Miniati, D. et al. Imaging accuracy and incidence of Wilms’ and non-Wilms’ renal tumors in children. J. Pediatr. Surg. 43, 1301–1307 (2008).

    PubMed  Google Scholar 

  34. Shin, H. J. et al. Texture analysis to differentiate malignant renal tumors in children using gray-scale ultrasonography images. Ultrasound Med. Biol. 45, 2205–2212 (2019).

    PubMed  Google Scholar 

  35. Gillies, R. J., Kinahan, P. E. & Hricak, H. Radiomics: images are more than pictures, they are data. Radiology 278, 563–577 (2016).

    PubMed  Google Scholar 

  36. Napel, S., Mu, W., Jardim-Perassi, B. V., Aerts, H. & Gillies, R. J. Quantitative imaging of cancer in the postgenomic era: radio(geno)mics, deep learning, and habitats. Cancer 124, 4633–4649 (2018).

    PubMed  Google Scholar 

  37. Wagner, M. W., Bilbily, A., Beheshti, M., Shammas, A. & Vali, R. Artificial intelligence and radiomics in pediatric molecular imaging. Methods 188, 37–43 (2021).

    CAS  PubMed  Google Scholar 

  38. Yamashita, R., Nishio, M., Do, R. K. G. & Togashi, K. Convolutional neural networks: an overview and application in radiology. Insights Imaging 9, 611–629 (2018).

    PubMed  PubMed Central  Google Scholar 

  39. Shen, D., Wu, G. & Suk, H. I. Deep learning in medical image analysis. Annu Rev. Biomed. Eng. 19, 221–248 (2017).

    CAS  PubMed  PubMed Central  Google Scholar 

  40. Zabihollahy, F., Schieda, N., Krishna, S. & Ukwatta, E. Automated classification of solid renal masses on contrast-enhanced computed tomography images using convolutional neural network with decision fusion. Eur. Radio. 30, 5183–5190 (2020).

    Google Scholar 

  41. Han, S., Hwang, S. I. & Lee, H. J. The classification of renal cancer in 3-phase CT images using a deep learning method. J. Digit Imaging 32, 638–643 (2019).

    PubMed  PubMed Central  Google Scholar 

  42. Nguyen, K. et al. Effect of phase of enhancement on texture analysis in renal masses evaluated with non-contrast-enhanced, corticomedullary, and nephrographic phase-enhanced CT images. Eur. Radio. 31, 1676–1686 (2021).

    Google Scholar 

Download references

Funding

National Natural Science Foundation of China (82022036, 91959130, 81971776, 81771924, 62027901, 81930053), the Beijing Natural Science Foundation (L182061), Strategic Priority Research Program of Chinese Academy of Sciences (XDB 38040200), the Project of High-Level Talents Team Introduction in Zhuhai City (Zhuhai HLHPTP201703), and the Youth Innovation Promotion Association CAS (2017175).

Author information

Author notes

  1. These authors contributed equally: Yupeng Zhu, Hailin Li.

  2. These authors jointly supervised this work: Ning Sun, Di Dong, Jie Tian, Yun Peng.

Authors and Affiliations

  1. Department of Radiology, MOE Key Laboratory of Major Diseases in Children, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing, 100045, China

    Yupeng Zhu, Wangxing Fu & Yun Peng

  2. Department of Radiology, Peking University Third Hospital, Beijing, 100191, China

    Yupeng Zhu

  3. Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing, 100191, China

    Hailin Li & Jie Tian

  4. CAS Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China

    Hailin Li, Siwen Wang, Di Dong & Jie Tian

  5. Department of Pediatric Urology, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing, 100045, China

    Yangyue Huang & Ning Sun

  6. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China

    Siwen Wang & Di Dong

  7. Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi, 710126, China

    Jie Tian

  8. Zhuhai Precision Medical Center, Zhuhai People’s Hospital (affiliated with Jinan University), Zhuhai, 519000, China

    Jie Tian

Authors
  1. Yupeng Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hailin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yangyue Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wangxing Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Siwen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ning Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Di Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jie Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Yun Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Substantial contributions to conception and design: Y.Z., H.L., N.S., D.D., J.T., Y.P. Acquisition of data: Y.Z., H.L., Y.H. Analysis and interpretation of data: Y.Z., H.L., S.W. Drafting the article or revising it critically for important intellectual content: Y.Z., H.L., N.S., D.D., J.T., Y.P. Final approval of the version to be published: N.S., D.D., J.T., Y.P.

Corresponding authors

Correspondence to Ning Sun, Di Dong, Jie Tian or Yun Peng.

Ethics declarations

Competing interests

The authors declare no competing interests.

Consent for publication

Informed consent was obtained from all participants for the imaging examinations. Specific patient consent was not required for the publication of this paper.

Additional information

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

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

Zhu, Y., Li, H., Huang, Y. et al. CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center. Pediatr Res 94, 1104–1110 (2023). https://doi.org/10.1038/s41390-023-02553-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41390-023-02553-x

Search

Advanced search

Quick links