Computer-aided diagnosis of gastrointestinal stromal tumors: a radiomics method on endoscopic ultrasound image

  • Xinyi Li
  • Fei Jiang
  • Yi GuoEmail author
  • Zhendong Jin
  • Yuanyuan WangEmail author
Original Article



The purpose of our study is to propose a preoperative computer-aided diagnosis system based on a radiomics method to differentiate gastrointestinal stromal tumors (GISTs) of the higher-risk group (HRG) from those of the lower-risk group (LRG) on endoscopic ultrasound (EUS) images.

Materials and method

Gastro-EUS (G-EUS) images of four different risk level GISTs were collected from 19 hospitals. The datasheet included 168 case HRG GISTs and 747 case LRG GISTs. A radiomics method with image segmentation, feature extraction, feature selection and classification was developed. Here 439 radiomics features were firstly extracted, and then, the least absolute shrinkage selection operator (lasso) model with a tenfold cross-validation and 31 bootstraps was used to reduce the dimension of feature sets. Finally, random forest was applied to establish the classification model.


The proposed model differentiated 32 case HRG GISTs from 149 case LRG GISTs. Result for the testing set achieved the area under the receiver operating characteristic curve of 0.839, the accuracy of 0.823, the sensitivity of 0.813 and the specificity of 0.826.


The model could increase preoperative diagnostic accuracy and provide a valuable reference for the doctors.


Radiomics Gastrointestinal stromal tumors Endoscopic ultrasound image Computer-aided diagnosis 



This work was supported by the National Natural Science Foundation of China (Grants 61871135 and 81830058) and the Science and Technology Commission of Shanghai Municipality (Grant 18511102904).

Compliance with ethical standards

Conflict of interest

We have no conflict of interest to declare.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the Declaration of Helsinki. For retrospective study, formal consent is not required. Informed consent was obtained from all individual participants included in the study. This study has been approved by the Ethics Committee of the Changhai Hospital.


  1. 1.
    Demetri G, DeVita L, Lawrence TS, Rosenberg SA (2011) DeVita, Hellman, and Rosenberg’s cancer: principles and practice of oncology, 10th edn. Wolters Kluer, Alphen aan den RijnGoogle Scholar
  2. 2.
    Fletcher CD, Berman JJ, Corless C, Gorstein F, Lasota J, Longley BJ, Miettinen M, O’Leary TJ, Remotti H, Rubin BP, Shmookler B, Sobin LH, Weiss SW (2002) Diagnosis of gastrointestinal stromal tumors: a consensus approach. Hum Pathol 33:459–465CrossRefGoogle Scholar
  3. 3.
    Miettinen M, Sobin LH, Lasota J (2005) Gastrointestinal stromal tumors of the stomach: a clinicopathologic, immunohistochemical, and molecular genetic study of 1765 cases with long-term follow-up. Am J Surg Pathol 29:52–68CrossRefGoogle Scholar
  4. 4.
    Xu J, Ling TL, Wang M, Zhao WY, Cao H (2015) Preoperative imatinib treatment in patients with advanced gastrointestinal stromal tumors: patient experiences and systematic review of 563 patients. Int Surg 100(5):860–869CrossRefGoogle Scholar
  5. 5.
    Agaimy A (2010) Review article: gastrointestinal stromal tumors (GIST) from risk stratification systems to the new TNM proposal: more questions than answers? A review emphasizing the need for a standardized GIST reporting. Int J Clin Exp Pathol 3(5):461–471PubMedPubMedCentralGoogle Scholar
  6. 6.
    Blackstein ME, Blay JY, Corless C, Driman DK, Riddell R, Soulières D, Swallow CJ, Verma S (2006) Gastrointestinal stromal tumours: consensus statement on diagnosis and treatment. Can J Gastroenterol 20:157–163CrossRefGoogle Scholar
  7. 7.
    Hwang JH, Rulyak SD, Kimmey MB (2006) American Gastroenterological Association Institute technical review on the management of gastric subepithelial masses. Gastroenterology 130:2217–2228CrossRefGoogle Scholar
  8. 8.
    NCCN guideline for soft tissue sarcoma (2012) Available from:
  9. 9.
    Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, Hoebers F, Rietbergen MM, Leemans R, Dekker A, Quackenbush J, Gillies RJ, Lambin P (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006–4015CrossRefGoogle Scholar
  10. 10.
    Gillies RJ, Kinahan PE, Hricak H (2015) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefGoogle Scholar
  11. 11.
    Guo Y, Hu Y, Qiao M, Wang Y, Yu J, Li J, Chang C (2018) Radiomics analysis on ultrasound for prediction of biologic behavior in breast invasive ductal carcinoma. Clin Breast Cancer 18(3):e335–e344CrossRefGoogle Scholar
  12. 12.
    Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 58(1):267–288Google Scholar
  13. 13.
    Santosa F, Symes WW (1986) Linear inversion of band-limited reflection seismograms. SIAM J Sci Stat Comput 7(4):1307–1330CrossRefGoogle Scholar
  14. 14.
    Blom G, Holst L, Sandell D (1994) Problems and snapshots from the world of probability. Springer, New YorkCrossRefGoogle Scholar
  15. 15.
    Yu J, Shi Z, Lian Y, Li Z, Liu T, Gao Y, Wang Y, Chen L, Mao Y (2016) Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol 27(8):3509–3522CrossRefGoogle Scholar
  16. 16.
    Saito T, Rehmsmeier M (2015) The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10(3):e0118432CrossRefGoogle Scholar

Copyright information

© CARS 2019

Authors and Affiliations

  1. 1.Department of Electronic EngineeringFudan UniversityShanghaiChina
  2. 2.Department of GastroenterologyChanghai HospitalShanghaiChina

Personalised recommendations