Development and internal validation of CTA-based radiomics models for differentiating symptomatic from asymptomatic unruptured spontaneous intracranial vertebrobasilar artery dissection
- 1Department of Neurosurgery, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University
Abstract
Background: Spontaneous intracranial vertebrobasilar artery dissection (sIVBD) has heterogeneous clinical presentations, and conventional clinical and morphologic assessment may not fully characterize lesion heterogeneity. We aimed to develop and internally validate CTA-based radiomics models for differentiating symptomatic from asymptomatic unruptured sIVBD and to evaluate the incremental contribution of radiomics beyond conventional clinical and CTA features.
Methods: This retrospective single-center study included 173 patients with unruptured sIVBD, comprising 56 symptomatic and 117 asymptomatic patients. Patients were stratified into a development cohort ( n = 138) and an independent internal validation cohort ( n = 35). Radiomic features were extracted from subtraction CTA images after three-dimensional lesion segmentation. Feature reproducibility was assessed using inter-reader intraclass correlation coefficients. Four models were developed: a conventional CTA model (M1), a clinical plus conventional CTA model (M2), a radiomics XGBoost model (M3), and a combined model integrating M2 predictors with a cross-fitted radiomics probability (M4). Primary development-cohort evaluation used five-times-repeated five-fold stratified nested cross-validation. Discrimination, calibration, Brier score, and decision-curve analysis were assessed.
Results: Of 851 radiomic features, 722 (84.8%) met the prespecified reproducibility criterion. In patient-averaged out-of-fold evaluation, AUCs were 0.630 for M1, 0.681 for M2, 0.676 for M3, and 0.723 for M4. Compared with M2, M4 increased AUC by 0.0416 (95% CI, −0.0130 to 0.0962; p = 0.136) and reduced the Brier score by 0.0101 (95% bootstrap CI, −0.0208 to 0.0006). Across 25 outer folds, M4 had the highest mean AUC (0.715) and the lowest between-fold variability. In the independent internal validation cohort, AUCs were 0.814, 0.807, 0.803, and 0.966 for M1 through M4, respectively.
Conclusion: A combined model integrating clinical variables, conventional CTA features, and cross-fitted radiomics information showed the best overall performance for differentiating symptomatic from asymptomatic unruptured sIVBD. Radiomics may provide complementary quantitative information beyond conventional assessment.
Related
- Comparable Norovirus Shedding in Symptomatic and Asymptomatic Individuals: A Hospital-Based Study in Bangladesh
- Asymptomatic and symptomatic recurrence of TB among cured pulmonary TB patients
- Clinical Characteristics and In-Hospital Course of Symptomatic Intracranial Hemorrhage After Intravenous Alteplase in Older Adults with Acute Ischemic Stroke: A Retrospective Cohort Study
- The clinical application of a low-profile stent for symptomatic intracranial atherosclerotic stenosis in the middle cerebral artery: a retrospective study of the Atlas stent
- Clinical Outcomes of Endoscopic Treatment for Asymptomatic and Symptomatic Common Bile Duct Stones: Incidence and Risk Factors for Post-ERCP Pancreatitis
BibTeX
@article{jiang2026development,
title = {{Development and internal validation of CTA-based radiomics models for differentiating symptomatic from asymptomatic unruptured spontaneous intracranial vertebrobasilar artery dissection}},
author = {Jia Jiang and Sheng Bi and Siming Gui and Lu Zheng and Youxiang Li and Qinglin Liu},
journal = {Frontiers in Neurology},
year = {2026},
month = oct,
doi = {10.3389/fneur.2026.1883223},
url = {https://www.frontiersin.org/articles/10.3389/fneur.2026.1883223/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Development and internal validation of CTA-based radiomics models for differentiating symptomatic from asymptomatic unruptured spontaneous intracranial vertebrobasilar artery dissection
AU - Jia Jiang
AU - Sheng Bi
AU - Siming Gui
AU - Lu Zheng
AU - Youxiang Li
AU - Qinglin Liu
PY - 2026
DA - 2026/10/23
JO - Frontiers in Neurology
DO - 10.3389/fneur.2026.1883223
UR - https://www.frontiersin.org/articles/10.3389/fneur.2026.1883223/full
AB - Background: Spontaneous intracranial vertebrobasilar artery dissection (sIVBD) has heterogeneous clinical presentations, and conventional clinical and morphologic assessment may not fully characterize lesion heterogeneity. We aimed to develop and internally validate CTA-based radiomics models for differentiating symptomatic from asymptomatic unruptured sIVBD and to evaluate the incremental contribution of radiomics beyond conventional clinical and CTA features. Methods: This retrospective single-center study included 173 patients with unruptured sIVBD, comprising 56 symptomatic and 117 asymptomatic patients. Patients were stratified into a development cohort ( n = 138) and an independent internal validation cohort ( n = 35). Radiomic features were extracted from subtraction CTA images after three-dimensional lesion segmentation. Feature reproducibility was assessed using inter-reader intraclass correlation coefficients. Four models were developed: a conventional CTA model (M1), a clinical plus conventional CTA model (M2), a radiomics XGBoost model (M3), and a combined model integrating M2 predictors with a cross-fitted radiomics probability (M4). Primary development-cohort evaluation used five-times-repeated five-fold stratified nested cross-validation. Discrimination, calibration, Brier score, and decision-curve analysis were assessed. Results: Of 851 radiomic features, 722 (84.8%) met the prespecified reproducibility criterion. In patient-averaged out-of-fold evaluation, AUCs were 0.630 for M1, 0.681 for M2, 0.676 for M3, and 0.723 for M4. Compared with M2, M4 increased AUC by 0.0416 (95% CI, −0.0130 to 0.0962; p = 0.136) and reduced the Brier score by 0.0101 (95% bootstrap CI, −0.0208 to 0.0006). Across 25 outer folds, M4 had the highest mean AUC (0.715) and the lowest between-fold variability. In the independent internal validation cohort, AUCs were 0.814, 0.807, 0.803, and 0.966 for M1 through M4, respectively. Conclusion: A combined model integrating clinical variables, conventional CTA features, and cross-fitted radiomics information showed the best overall performance for differentiating symptomatic from asymptomatic unruptured sIVBD. Radiomics may provide complementary quantitative information beyond conventional assessment.
SN - 1664-2295
ER -