Radiomics nomogram for predicting the malignant potential of gastrointestinal stromal tumours preoperatively
- 413 Downloads
To develop and evaluate a radiomics nomogram for differentiating the malignant risk of gastrointestinal stromal tumours (GISTs).
A total of 222 patients (primary cohort: n = 130, our centre; external validation cohort: n = 92, two other centres) with pathologically diagnosed GISTs were enrolled. A Relief algorithm was used to select the feature subset with the best distinguishing characteristics and to establish a radiomics model with a support vector machine (SVM) classifier for malignant risk differentiation. Determinant clinical characteristics and subjective CT features were assessed to separately construct a corresponding model. The models showing statistical significance in a multivariable logistic regression analysis were used to develop a nomogram. The diagnostic performance of these models was evaluated using ROC curves. Further calibration of the nomogram was evaluated by calibration curves.
The generated radiomics model had an AUC value of 0.867 (95% CI 0.803–0.932) in the primary cohort and 0.847 (95% CI 0.765–0.930) in the external cohort. In the entire cohort, the AUCs for the radiomics model, subjective CT findings model, clinical index model and radiomics nomogram were 0.858 (95% CI 0.807–0.908), 0.774 (95% CI 0.713–0.835), 0.759 (95% CI 0.697–0.821) and 0.867 (95% CI 0.818–0.915), respectively. The nomogram showed good calibration.
This radiomics nomogram predicted the malignant potential of GISTs with excellent accuracy and may be used as an effective tool to guide preoperative clinical decision-making.
• CT-based radiomics model can differentiate low- and high-malignant-potential GISTs with satisfactory accuracy compared with subjective CT findings and clinical indexes.
• Radiomics nomogram integrated with the radiomics signature, subjective CT findings and clinical indexes can achieve individualised risk prediction with improved diagnostic performance.
• This study might provide significant and valuable background information for further studies such as response evaluation of neoadjuvant imatinib and recurrence risk prediction.
KeywordsGastrointestinal stromal tumour Classification Radiomics Nomogram Machine learning
Armed forces institute of pathology
Area under curve
Enlarged vessels feeding or draining the mass
Gastrointestinal stromal tumours
Inter- and intraclass correlation coefficients
National comprehensive cancer network
National institutes of health
Support vector machine
This study has received funding by the State’s Key Project of Research and Development Plan (2017YFC0108300 and 2017YFC0108303) and JSPS KAKENHI Grant (17H00867 and 26108006).
Compliance with ethical standards
The scientific guarantor of this publication is Tao Chen.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise: Hao Liu, Department of General Surgery, Nanfang Hospital, Southern Medical University, Guangdong Provincial Engineering Technology Research Center of Minimally Invasive Surgery, Guangzhou 510515, Guangdong Province, China. Hao Liu has completed postdoctoral research of cancer epidemiological statistics in Heidelberg Cancer Center, Germany. Hao Liu specialises in statistical analysis and provided statistical advice in this study.
Written informed consent or substitute was obtained from all patients in this study.
Institutional review board approval was obtained.
• diagnostic or prognostic study
• multicentre study
- 9.Liu Q, Li Y, Dong M, Kong F, Dong Q (2017) Gastrointestinal bleeding is an independent risk factor for poor prognosis in GIST patients. Biomed Res Int. https://doi.org/10.1155/2017/7152406
- 10.Verma V, Simone CB 2nd, Krishnan S, Lin SH, Yang JZ, Hahn SM (2017) The rise of radiomics and implications for oncologic management. J Natl Cancer Inst. https://doi.org/10.1093/jnci/djx055
- 14.Kononenko I (1994) Estimating attributes: analysis and extensions of RELIEF. In: Bergadano F, De Raedt L (eds) Machine Learning: ECML-94. ECML 1994. Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence), vol 784. Springer, Berlin, pp 171–182Google Scholar
- 18.Han DS, Suh YS, Kong SH et al (2012) Nomogram predicting long-term survival after d2 gastrectomy for gastric cancer. J Clin Oncol 30:3834–3840Google Scholar
- 22.Lv A, Li Z, Tian X et al (2013) SKP2 high expression, KIT exon 11 deletions, and gastrointestinal bleeding as predictors of poor prognosis in primary gastrointestinal stromal tumors. PLoS One. https://doi.org/10.1371/journal.pone.0062951