A preoperative computed tomography radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors
Study context
- Population
- French patients with surgically resected pancreatic neuroendocrine tumors (pNETs) and available computed tomography (CT) examinations; median age 61 years, 20 men; grade 1 57%, grade 2 32%, grade 3 11%
- Participants
- 37 patients
- Exposure
- Radiomics index >0.4 vs ≤0.4
- Outcome
- RFS and OS predicted by preoperative CT radiomics index (Kaplan-Meier)
Methodological detailsobservational, radiomics model, Features extracted with 3D-Slicer® (manual segmentation); LASSO selection trained on Ki67 rate (≤2 or >2); ROC used to select cutoff
- Observational
- Radiomics model
- Features extracted with 3D-Slicer® (manual segmentation); LASSO selection trained on Ki67 rate (≤2 or >2); ROC used to select cutoff
Main finding
As reported in the abstract
Median RFS
P = 0.013
Observational data: associations, not effects.
Further findings
- No associations between the radiomics index and OS
- P = 0.86
Original publication
A preoperative computed tomography radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors. Eur J Endocrinol. Published 3 October 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →