Radiomic survival analysis protocol aids prognosis in small tumor studies
A four-step validation protocol for radiomic survival analysis in small cohorts: a body composition case study
Computer Vision and Pattern RecognitionMachine Learning
Summary
Predicting patient outcomes with radiomic features from CT scans can be tricky, especially when the number of patients is small. The authors created a four-step process to better test these predictions and reduce mistakes caused by random chance or overfitting. Using scans from patients with a specific type of tumor, they found some body features linked to better survival but also showed uncertainty remains. Their process can help others check radiomic models more reliably in small patient groups.
What this means in practice
- •For medical imaging teams: Validate predictive radiomic models for survival outcomes in small patient groups more reliably.
- •For clinical data analysts: Use the four-step validation protocol to reduce overfitting risks when building prognostic models from small datasets.
Tested on one dataset.
Authors
Mariela Talavera-Muñoz, Cecilia Diana-Albelda, Miguel Antonio Sampedro-Nuñez, Victor Rodriguez-Laval, Jesus Bescos, Álvaro García-Martín
Abstract
Gastroenteropancreatic neuroendocrine tumors (GEP-NET) lack prognostic biomarkers, and computed tomography (CT)-based body composition radiomics at the third lumbar vertebra (L3) is a promising candidate. Small cohorts make high-dimensional radiomic models prone to overfitting and single-split evaluations variable and optimistic. This methodological study proposes a four-step validation protocol for radiomic survival analysis in small cohorts: (1) false discovery rate (FDR)-corrected feature selection, (2) a dual-path comparison of prior feature selection versus embedded regularization, (3) repeated nested cross-validation (CV) and (4) a negative control with Gaussian noise features. In 78 GEP-NET patients, 535 radiomic features from five L3 compartments were used to evaluate five survival models with Harrell's concordance index (C-index), time-dependent area under the curve (AUC) and integrated Brier score (IBS). Step 1 selected at least one feature in 18% of outer folds under noise (nominal level 20%) versus 84% with radiomic features. The dual-path comparison showed no consistent difference between strategies. Repeated nested CV reduced variability across seeds (41% median reduction in C-index standard deviation), but not enough to distinguish models. The nested CV C-index exceeded chance by 0.07-0.15 with radiomic features but not clearly under noise (0.40-0.42 with prior feature selection, 0.47-0.55 with embedded regularization). Frequently selected features tentatively linked greater subcutaneous fat, skeletal muscle compactness and texture to better prognosis. These findings suggest a modest prognostic signal in L3 radiomics, with considerable uncertainty that the protocol quantifies. The protocol may transfer to other small-cohort radiomic survival studies. Code: https://github.com/marielatalaveram/radiomics-survival-validation-protocol.