Back to all papers

Machine learning based on preoperative CT for noninvasive prediction of recurrence-free survival in gastrointestinal stromal tumors.

August 3, 2026pubmed logopapers

Authors

Zhao L,Zhao L,Yin X,Yuan E,Gu Y,Zheng X,Wu B,Yin Y,Liu X

Affiliations (6)

  • Department of Radiology, West China Hospital of Sichuan University, No. 37 Guoxue Lane, Wuhou District, Chengdu, Sichuan Province, 610041, China.
  • Department of Radiology, Chengdu Sixth People's Hospital, Chengdu, China.
  • Department of Radiology, Sichuan Academy of Medical Sciences, Sichuan Provincial People's Hospital, Chengdu, China.
  • Division of Gastrointestinal Surgery, Department of General Surgery, West China Hospital of Sichuan University, Chengdu, China.
  • Division of Gastrointestinal Surgery, Department of General Surgery, West China Hospital of Sichuan University, Chengdu, China. [email protected].
  • Department of Radiology, West China Hospital of Sichuan University, No. 37 Guoxue Lane, Wuhou District, Chengdu, Sichuan Province, 610041, China. [email protected].

Abstract

Clinicians need a reliable, noninvasive tool that can predict the risk of gastrointestinal stromal tumor (GIST) recurrence preoperatively. We aimed to develop a machine learning model based on preoperative contrast-enhanced CT (CECT) to predict recurrence-free survival (RFS) in GIST patients who underwent radical resection. A total of 192 patients with intermediate- and high-risk GISTs who underwent radical resection and subsequently received adjuvant imatinib were included, with a minimum follow-up duration of 24 months. A machine learning model (Model<sub>radiomic</sub>) based on preoperative CECT was built to predict RFS, which was compared with the Armed Forces Institute of Pathology (AFIP) index (Model<sub>AFIP</sub>). The C-index and time-dependent receiver operating characteristic curves were estimated via the Kaplan-Meier method and compared via the log-rank test. The C-index values of the Model<sub>radiomic</sub> in the training, testing and validation cohorts ranged from 0.678 to 0.763, whereas the areas under the curves (AUCs) at 3 and 5 years were 0.744-0.790 and 0.703-0.833, respectively. The C-index values of Model<sub>AFIP</sub> in the above datasets were 0.539-0.660, and the AUCs at 3 and 5 years were 0.497-0.649 and 0.503-0.630. Model<sub>radiomic</sub> demonstrated a higher C-index than Model<sub>AFIP</sub> did in the training and external validation cohorts (p = 0.010 and 0.042, respectively). Model<sub>radiomic</sub> presented a greater AUC value than Model<sub>AFIP</sub> did at the 5th year in the training cohort (p = 0.009). We found the machine learning-based preoperative CECT performed better than the AFIP index in prediction of RFS of GIST patients, especially at the 5th year, predicting recurrence risk in patients who underwent radical resection and receiving adjuvant therapy. This model may serve as a non-invasive tool to identify high-risk individuals who require more intensive surveillance and personalized management following radical resection.

Topics

Gastrointestinal Stromal TumorsMachine LearningTomography, X-Ray ComputedNeoplasm Recurrence, LocalGastrointestinal NeoplasmsJournal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.