Radiomics-Based Machine Learning for Automated Detection and Rupture-Risk Stratification of Cerebral Vascular Malformations: A Retrospective Cohort Study
Sriwijaya Journal of Radiology and Imaging Research · 14.07.2026 · 3 (2) · 92-100
DOI: 10.59345/sjrir.v3i2.291 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift Sriwijaya Journal of Radiology and Imaging Research, online erschienen am 14.07.2026. Verfasst von Hesti Putri und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Cerebral vascular malformations (CVMs) are the leading cause of spontaneous intracranial haemorrhage, yet their detection on CT/MR angiography is operator-dependent and existing machine-learning models derive almost exclusively from Caucasian or East Asian cohorts. We developed and internally validated a population-specific radiomics pipeline for CVM detection and rupture-risk stratification in a Southeast Asian population.
Methods
In this retrospective diagnostic-and-prognostic cohort (STARD 2015; CLAIM) at a tertiary hospital in Palembang, Indonesia (2020–2025), 486 adults with diagnostic-quality CTA or TOF-MRA were analysed. After resampling and normalisation, 1,218 PyRadiomics features were reduced by LASSO and used to train Random Forest, SVM and XGBoost models (70/30 split). The reference standard was blinded consensus segmentation by two consultant neuroradiologists. Diagnostic accuracy (Wilson CI), AUC (DeLong), likelihood ratios, Cohen κ, McNemar test and a multivariable rupture model were computed.
Results
CVM prevalence was 42.8% (208/486). XGBoost was the best detector (AUC 0.963 (95% CI 0.950–0.977); sensitivity 88.5 (95% CI 83.4–92.1)%; specificity 92.4 (95% CI 88.7–95.0)%; LR+ 11.71 (95% CI 7.74–17.72)), outperforming a single radiologist (ΔAUC 0.128, p
Zitieren
APA
Putri, H., Diana, N., Pablo-Rodriguez, P. M., & Khoirina, N. (2026). Radiomics-Based Machine Learning for Automated Detection and Rupture-Risk Stratification of Cerebral Vascular Malformations: A Retrospective Cohort Study. Sriwijaya Journal of Radiology and Imaging Research, 3(2), 92-100. https://doi.org/10.59345/sjrir.v3i2.291
Vancouver
Putri H, Diana N, Pablo-Rodriguez PM, Khoirina N. Radiomics-Based Machine Learning for Automated Detection and Rupture-Risk Stratification of Cerebral Vascular Malformations: A Retrospective Cohort Study. Sriwijaya Journal of Radiology and Imaging Research. 2026;3(2):92-100. doi:10.59345/sjrir.v3i2.291
BibTeX
@article{Putri2026,
author = {Putri, Hesti and Diana, Nur and Pablo-Rodriguez, Paula Magna and Khoirina, Nadia},
title = {Radiomics-Based Machine Learning for Automated Detection and Rupture-Risk Stratification of Cerebral Vascular Malformations: A Retrospective Cohort Study},
journal = {Sriwijaya Journal of Radiology and Imaging Research},
year = {2026},
volume = {3},
number = {2},
pages = {92--100},
doi = {10.59345/sjrir.v3i2.291}
}
EUVIMED