eess.IVNov 9, 2026

A four-step validation protocol for radiomic survival analysis in small cohorts: a body composition case study

Authors: Mariela Talavera-Muñoz, Cecilia Diana-Albelda, Miguel Antonio Sampedro-Nuñez, Victor Rodriguez-Laval, Jesus Bescos, Álvaro García-Martín

Organizations: Video Processing and Understanding Lab, Escuela Politécnica Superior, Universidad Autónoma de Madrid, Calle Francisco Tomás y Valiente 11, Madrid, 28049, Madrid, Spain · Department of Endocrinology and Nutrition, Hospital Universitario de La Princesa, Instituto de Investigación Sanitaria de La Princesa, Calle de Diego de León 62, Madrid, 28006, Madrid, Spain · Instituto de Investigación Sanitaria del Hospital Universitario de La Princesa, Calle de Diego de León 62, Madrid, 28006, Madrid, Spain · Department of Radiodiagnostics, Hospital Universitario de La Princesa, Calle de Diego de León 62, Madrid, 28006, Madrid, Spain

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.

Figures & tables

Explore similar work

CardsList
  1. Segmentation Robustness and Predictive Utility in Glioblastoma Radiomics: Evidence for a Trade-off in Survival Modelling

    Jul 26, 2026Mariya Miteva, Maria Nisheva-PavlovaCancer Survival PredictionRadiomics

  2. How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts

    Oct 19, 2026Yannick Sodonougbo, Marlene Schnieders, Alexia Rizoudis +3RadiomicsFeature Selection

  3. Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices

    Jul 1, 2026Nils Neukirch, Martin Maurer, Nils StrodthoffMedical Imaging Foundation ModelsCancer Survival Prediction