Skip to main content

Differentiation of gastric schwannomas from gastrointestinal stromal tumors by CT using machine learning



To identify schwannomas from gastrointestinal stromal tumors (GISTs) by CT features using Logistic Regression (LR), Decision Trees (DT), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT).


This study enrolled 49 patients with schwannomas and 139 with GISTs proven by pathology. CT features with P < 0.1 derived from univariate analysis were inputted to four models. Five machine learning (ML) versions, multivariate analysis, and radiologists’ subjective diagnostic performance were compared to evaluate diagnosis performance of all the traditional and advanced methods.


The CT features with P < 0.1 were as follows: (1) CT attenuation value of unenhancement phase (CTU), (2) portal venous enhancement (CTV), (3) degree of enhancement in the portal venous phase (DEPP), (4) CT attenuation value of portal venous phase minus arterial phase (CTV-CTA), (5) enhanced potentiality (EP), (6) location, (7) contour, (8) growth pattern, (9) necrosis, (10) surface ulceration, (11) enlarged lymph node (LN). LR (M1), RF, DT, and GBDT models contained all of the above 11 variables, while LR (M2) was developed using six most predictive variables derived from (M1). LR (M2) model with AUC of 0.967 in test dataset was thought to be optimal model in differentiating the two tumors. Location in gastric body, exophytic and mixed growth pattern, lack of necrosis and surface ulceration, enlarged lymph nodes, and larger EP were the most important CT features suggestive of schwannomas.


LR (M2) provided the optimal diagnostic potency among other ML versions, multivariate analysis, and radiologists’ performance on differentiation of schwannomas from GISTs.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4


  1. Sarlomo-Rikala M, Miettinen M. Gastric schwannoma: a clinicopathological analysis of six cases. Histopathology. 1995; 27(4):355-360

    CAS  Article  Google Scholar 

  2. Shah AS, Rathi PM, Somani VS, et al. Gastric schwannoma: a benign tumor often misdiagnosed as gastrointestinal stromal tumor. Clin Pract. 2015; 5(3):775

    Google Scholar 

  3. Miettinen M, Majidi M, Lasota J. Pathology and diagnostic criteria of gastrointestinal stromal tumors (GISTs): a review. Eur J Cancer. 2002; 38: Suppl 5:S39-S51

    Article  Google Scholar 

  4. Tzen CY, Mau BL. Analysis of CD117-negative gastrointestinal stromal tumors. World J Gastroenterol. 2005; 11(7):1052-1055

    CAS  Article  Google Scholar 

  5. Miettinen M, Lasota J. Gastrointestinal stromal tumors: pathology and prognosis at different sites. Semin Diagn Pathol. 2006; 23(2):70-83

    Article  Google Scholar 

  6. Nilsson B, Bumming P, Meis-Kindblom, JM, et al. Gastrointestinal stromal tumors: the incidence, prevalence, clinical course, and prognostication in the preimatinib mesylate era–a population-based study in western Sweden. Cancer. 2005; 103(4):821-829

    Article  Google Scholar 

  7. Hong HS, Ha HK, Won HJ, et al. Gastric schwannomas: radiological features with endoscopic and pathological correlation. Clin Radiol. 2008; 63(5):536-542

    CAS  Article  Google Scholar 

  8. Miettinen M, Sarlomo-Rikala M, Lassota J. Gastrointestinal stromal tumors: Recent advances in understanding of their biology. Hum Pathol. 1999; 30(10):1212-1220

    Article  Google Scholar 

  9. Levy AD, Remotti HE, Thompson WM, et al. Gastrointestinal stromal tumors: Radiologic features with pathologic correlation. Radiographics. 2003; 23(2):283–304, 456; quiz 532

  10. Joensuu H. Sunitinib for imatinib-resistant GIST. Lancet. 2006; 368:1303–1304

    Article  Google Scholar 

  11. Linch M, Claus J, Benson C. Update on imatinib for gastrointestinal stromal tumors: duration of treatment. Onco Targets Ther. 2013; 6:1011-1023

    CAS  PubMed  PubMed Central  Google Scholar 

  12. Levy AD, Quiles AM, Miettinen M, et al. Gastrointestinal Schwannomas: CT Features with Clinicopathologic Correlation. AJR Am J Roentgenol. 2005; 184(3):797-802

    Article  Google Scholar 

  13. Kalkmann J, Zeile M, Antoch G, et al. Consensus report on the radiological management of patients with gastrointestinal stromal tumours (GIST): recommendations of the German GIST Imaging Working Group. Cancer Imaging. 2012; 12(1):126-135

    Article  Google Scholar 

  14. Cruz JA, Wishart DS. Applications of Machine Learning in Cancer Prediction and Prognosis. Cancer Inform. 2007; 2:59-77

    PubMed  PubMed Central  Google Scholar 

  15. Choi YR, Kim SH, Kim SA, et al. Differentiation of large (≥5 cm) gastrointestinal stromal tumors from benign subepithelial tumors in the stomach: Radiologists’ performance using CT. Eur J Radiol. 2014; 83(2):250-260

    Article  Google Scholar 

  16. Choi JW, Choi D, Kim KM, et al. Small Submucosal Tumors of the Stomach: Differentiation of Gastric Schwannoma from Gastrointestinal Stromal Tumor with CT. Korean J Radiol. 2012; 13(4):425-433

    Article  Google Scholar 

  17. He MY, Zhang R, Peng ZP, et al. Differentiation Between Gastrointestinal Schwannomas and Gastrointestinal Stromal Tumors by Computed Tomography. Oncol Lett. 2017; 13(5):3746-3752

    Article  Google Scholar 

  18. Varoquaux FG, Gramfort A, Pedregosa J, et al. Scikit-learn: Machine Learning in Python. JMLR. 2011; 12:2825-2830

    Google Scholar 

  19. Atmatzidis S, ChatzimavroudisG, Dragoumis D, et al. Gastric schwannoma: A case report and literature review. Hippokratia. 2012; 16(3):280-282

    CAS  PubMed  PubMed Central  Google Scholar 

  20. Prévot S, Bienven L, Vaillant JC, et al. Benign schwannoma of the digestive tract: a clinicopathologic and immunohistochemical study of five cases, including a case of esophageal tumor. Am J Surg Pathol. 1999; 23(4):431-436

    Article  Google Scholar 

  21. Zhou CP, Duan XH, Zhang X, et al. Predictive features of CT for risk stratifications in patients with primary gastrointestinal stromal tumour. Eur Radiol. 2016; 26(9):3086-3093

    Article  Google Scholar 

  22. Burkill GJ, Badran M. Malignant gastrointestinal stromal tumor: distribution, imaging features, and pattern of metastatic spread. Radiology. 2013; 226(2):527-532

    Article  Google Scholar 

  23. Cai, MY, Xu JX, Zhou PH, et al. Endoscopic resection for gastric schwannoma with long-term outcomes. Surg Endosc. 2016; 30(9):3994-4000

    Article  Google Scholar 

  24. Ji JS, Lu CY, Mao WB, et al. Gastric schwannoma: CT findings and clinicopathologic correlation. Abdom Imaging. 2015; 40(5):1164-1169

    Article  Google Scholar 

  25. Liu JL, Chai JJ, Zhou JL, et al. Spectral Computed Tomography Imaging of Gastric Schwannoma and Gastric Stromal Tumor. J Comput Assist Tomogr. 2017; 41(3):417-421

    Article  Google Scholar 

  26. Zhang Xl, Bai LC, Wang D. et al. Gastrointestinal stromal tumor risk classification: spectral CT quantitative parameters. Abdom Radiol (NY). 2019; 44(7): 2329-2336

    Google Scholar 

Download references



Author information

Authors and Affiliations


Corresponding author

Correspondence to Cui Zhang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicts of interest.

Ethical approval

The study was approved by the institutional review board of TongDe Hospital of Zhejiang Province.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Additional information

Publisher's Note

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

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 13 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Wang, J., Xie, Z., Zhu, X. et al. Differentiation of gastric schwannomas from gastrointestinal stromal tumors by CT using machine learning. Abdom Radiol 46, 1773–1782 (2021).

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Schwannoma
  • Gastrointestinal stromal tumor
  • Tomography, X-ray computed
  • Machine learning