Skip to main content
SpringerLink
Log in

MRI-based deep learning model for differentiation of hepatic hemangioma and hepatoblastoma in early infancy

  • RESEARCH
  • Published:
European Journal of Pediatrics Aims and scope Submit manuscript

Abstract

Hepatic hemangioma (HH) and hepatoblastoma (HBL) are common pediatric liver tumors and present with similar clinical manifestations with limited distinguishing value of serum AFP in early infancy. An accurate differentiation diagnostic tool is warranted for optimizing treatments and improving prognosis. The present study aimed to develop an innovative and cost-effective diagnostic tool to differentiate HH and HBL in early infancy using advanced deep learning (DL) techniques. One hundred forty patients ≤4 months old diagnosed as HH or HBL with histological specimens were recruited from two institutions assigned into a training set with cross-validation and a testing set for external validation, respectively. Based on MRI images, imaging diagnoses were interpreted by two radiologists, and imaging-derived radiomic features were extracted by pretrained convolutional neural networks (CNNs)-Xception extractor via DL analysis. A nomogram model was constructed integrating predictive clinical variables, radiologist-based interpretation, and DL features, evaluated comprehensively on diagnostic and calibration accuracy. The DL-based model performed an area under the receiver operating characteristic curve (AUC) of 0.966 for the training cohort and 0.864 for the testing cohort. The radiologist-interpreted differentiation model showed an AUC of 0.837 in the testing cohort. The integrated nomogram model represented an increasing performance with an AUC of 0.887, accuracy of 78.57%, sensitivity of 76.19%, and specificity of 80.95% in the testing cohort.

Conclusion: The MRI-based integrated model, a noninvasive preoperative diagnostic tool, yielded favorable efficacy for differentiating HH and HBL in early infancy, which might reduce the patients’ costs of repetitive and unnecessary examinations or over-treatment.

Trial registration: ClinicalTrials.gov Identifier: NCT05170282.

What is Known:

• Hepatic hemangioma (HH) and hepatoblastoma (HBL) are common pediatric liver tumors and present with similar clinical manifestations with limited distinguishing value of serum AFP in early infancy.

• Considering the rare incidence of infantile hepatic tumors, the distinguishing accuracy between HBL and HH for cases in early infancy is unsatisfactory for radiologists’ recognition solely.

What is New:

• The MRI-based integrated model, a noninvasive preoperative diagnostic tool yielded favorable efficacy for differentiating HH and HBL in early infancy, which might reduce the patients’ costs of repetitive and unnecessary examinations or over-treatment.

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

Similar content being viewed by others

Data availability

The data used and/or analysed during the current study is available from the corresponding author on reasonable request.

Abbreviations

DL:

Deep learning

HH:

Hepatic hemangioma

HBL:

Hepatoblastoma

CNN:

Convolutional neural network

AUC:

Area under the receiver operating characteristic curve

MRI:

Magnetic resonance imaging

AFP:

Serum alpha fetoprotein

ALBI:

Albumin-bilirubin

ROI:

Region of interest

SVM:

Support vector machine

References

  1. Jha P, Chawla SC, Tavri S et al (2009) Pediatric liver tumors–a pictorial review. Eur Radiol 19:209–219

    Article  PubMed  Google Scholar 

  2. Iacobas I, Phung TL, Adams DM et al (2018) Guidance document for hepatic hemangioma (infantile and congenital) evaluation and monitoring. J Pediatr 203:294-300

    Article  PubMed  Google Scholar 

  3. Herzog CE, Andrassy RJ, Eftekhari F (2000) Childhood cancers: hepatoblastoma. Oncologist 5:445–453

    Article  CAS  PubMed  Google Scholar 

  4. Ferraro S, Panzeri A, Braga F et al (2019) Serum α-fetoprotein in pediatric oncology: not a children’s tale. Clin Chem Lab Med 57:783–797

    Article  CAS  PubMed  Google Scholar 

  5. Navarro OM (2016) Magnetic resonance imaging of pediatric soft-tissue vascular anomalies. Pediatr Radiol 46:891–901

    Article  PubMed  Google Scholar 

  6. Gnarra M, Behr G, Kitajewski A et al (2016) History of the infantile hepatic hemangioma: from imaging to generating a differential diagnosis. World J Clin Pediatr 5:273–280

    Article  PubMed  PubMed Central  Google Scholar 

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

    Article  CAS  PubMed  Google Scholar 

  8. Yamashita R, Nishio M, Do RKG et al (2018) Convolutional neural networks: an overview and application in radiology. Insights Imaging 9:611–629

    Article  PubMed  PubMed Central  Google Scholar 

  9. Kermany DS, Goldbaum M, Cai W et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172:1122-1131

    Article  CAS  PubMed  Google Scholar 

  10. Johnson PJ, Berhane S, Kagebayashi C et al (2015) Assessment of liver function in patients with hepatocellular carcinoma: a new evidence-based approach-the ALBI grade. J Clin Oncol 33:550–558

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Pediatric Surgery, West China Hospital, Sichuan University, No. 37, Guo Xue Xiang, Chengdu, 610041, China

    Yuhan Yang & Yuan Li

  2. Laboratory of Digestive Surgery, State Key Laboratory of Biotherapy and Cancer Center, West China Hospital, Sichuan University, No. 37, Guo Xue Xiang, Chengdu, 610041, China

    Zongguang Zhou & Yuan Li

  3. Department of General Surgery, West China Hospital, Sichuan University, No. 37, Guo Xue Xiang, Chengdu, 610041, China

    Zongguang Zhou

Authors
  1. Yuhan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zongguang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Yuhan Yang: investigation, data curation, methodology, visualization, writing-original draft preparation. Zongguang Zhou: validation, writing-review and editing. Yuan Li: conceptualization, supervision, writing-review and editing.

Corresponding author

Correspondence to Yuan Li.

Ethics declarations

Ethics approval

This study obtained the ethics approval from West China Hospital, Sichuan University.

Consent to participate

The consent to participate was waived considering the ethics standards of study design of retrospective cohort in this study.

Conflict of interest

The authors declare no competing interests.

Additional information

Communicated by Peter de Winter

Publisher's Note

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

Supplementary Information

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

Yang, Y., Zhou, Z. & Li, Y. MRI-based deep learning model for differentiation of hepatic hemangioma and hepatoblastoma in early infancy. Eur J Pediatr 182, 4365–4368 (2023). https://doi.org/10.1007/s00431-023-05113-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00431-023-05113-x

Keywords

Search

Navigation