Gastrointestinal stromal tumours: Preoperative imaging features to predict recurrence after curative resection

Haerang Jung, Sang Min Lee, Young Chul Kim, Jieun Byun, Jin Young Park, Bo Young Oh, Mi Jung Kwon, Jeehyoung Kim

Research output: Contribution to journalArticlepeer-review

Abstract

Purpose: To identify whether preoperative factors could predict the recurrence after curative resection of gastrointestinal stromal tumours (GISTs) and evaluate the performance of a prediction model using preoperative factors for GIST recurrence compared to a model using preoperative/postoperative factors. Method: This retrospective study included patients who underwent curative resection and preoperative CT for GIST. CT imaging features as preoperative factors were analysed by two abdominal radiologists. Modified National Institutes of Health scores were accessed as a postoperative factor. Multiple logistic regression analysis was performed to assess the preoperative and postoperative factors in predicting GIST recurrence. Through the logistic regression, two prediction models using preoperative factors only and both preoperative/postoperative factors were constructed, respectively. The internal validation of the prediction models was performed using bootstrapping sampling. Results: Data in 113 patients were evaluated. Among them, 14 patients had recurrence. The multiple logistic regression analysis demonstrated that non-gastric location (odds ratio [OR] = 5.12, p = 0.029), ill-defined margin (OR = 4.93, p = 0.023), and prominent vessels around tumour (OR = 6.78, p = 0.007) were significant factors. The prediction models using these preoperative factors and adding a postoperative factor showed an area under the receiver operating characteristic curve of 0.863 and 0.897, respectively, which were not statistically different. The bootstrapping sampling showed the two models were valid. Conclusion: The prediction model derived from non-gastric location, ill-defined margin, and prominent vessels around tumour can be used preoperatively to estimate the risk of recurrence after resection of GIST.

Original languageEnglish
Article number110193
JournalEuropean Journal of Radiology
Volume149
DOIs
StatePublished - Apr 2022

Keywords

  • Computed tomography
  • Gastrointestinal stromal tumours
  • Logistic models
  • Nomograms
  • Postoperative recurrence

Fingerprint

Dive into the research topics of 'Gastrointestinal stromal tumours: Preoperative imaging features to predict recurrence after curative resection'. Together they form a unique fingerprint.

Cite this