Skip to content
Open access

Stroke onset time estimation from NCCT with censoring-aware learning and robustness to infarct segmentation uncertainty

Sep 2026 · Scientific Reports · Vol 16 · 0 citations · 32 references

TL;DR

A fully automated onset time estimation pipeline based on non-contrast CT (NCCT) using radiomics features extracted from automatically segmented infarct regions is proposed, highlighting the potential of NCCT-based regression models for continuous and interpretable onset time estimation.

Abstract

In patients with acute ischemic stroke and unknown symptom onset, reliable estimation of time since stroke onset is important for guiding reperfusion treatment decisions, particularly in settings where advanced imaging is unavailable. In this study, we propose a fully automated onset time estimation pipeline based on non-contrast CT (NCCT) using radiomics features extracted from automatically segmented infarct regions. A segmentation network is used to localize the infarct core, after which radiomics features are derived from both the lesion and the corresponding contralateral region. These features are used to train machine learning regressors, including kernel-based models and a multilayer perceptron, and are compared against pure attenuation-based baselines reflecting net water uptake (NWU). As approximately 25% of patients present without exact onset time and only a last-known-well time (LKWT) is available, these cases are commonly omitted from model development, further reducing already limited training cohorts. To address this problem, we investigate multiple strategies for incorporating LKWT, including surrogate target assignment, stochastic target sampling, and censoring-aware learning formulations. In addition, we assess the robustness of the deployed models to variations in infarct delineation by simulating multiple plausible segmentation boundaries at inference. The literature-parameterized NWU model remained a competitive baseline, while radiomics-based censoring-aware models achieved the lowest errors. Incorporating LKWT through censoring-aware formulations reduced the error compared with known-onset-only training, although this difference was not statistically significant. On the external test set of 32 patients with documented onset time, the censoring-aware support vector regression formulation achieved the lowest median absolute error of 1.12 h (95% BCa CI: 0.91–1.42 h). Censoring-aware formulations also showed low variability under the investigated infarct-boundary perturbations. These findings highlight the potential of NCCT-based regression models for continuous and interpretable onset time estimation. By incorporating LKWT cases, the proposed framework can expand otherwise limited training cohorts, while providing flexible predictions independent of fixed decision thresholds and demonstrating robustness to segmentation uncertainty. Together, these properties suggest that the proposed framework may have future value for clinical decision support, although validation in larger cohorts and prospective studies remains necessary before clinical translation.

Read PDF

Similar papers

Open access Sep 2026

Ischemic Stroke Detection, Segmentation, and Volume Estimation using Multi-sequence MRI Data with Missing Sequences

A unified framework that leverages graph neural networks and sequence-specific feature modeling for comprehensive ischemic stroke analysis from MRI is presented, designed to detect ischemic stroke, segment lesions, and estimate lesion volume from multi-sequence MRI data, while accommodating incomplete combinations of M...

Z. Lu, S. Uddin, S. Uribe et al. · 0 citations
Open access Sep 2026

Parameter-free dual-student ensemble for semi-supervised ischemic stroke segmentation on follow-up NCCT

An ensemble-based semi-supervised segmentation framework to reduce the dependence of convolutional neural networks (CNNs) on a large number of manual annotations and achieves the highest Dice coefficient among all compared methods under all four labeled-data ratios.

Yu-Qing Sha, Long Wang, Chao Huang et al. · 0 citations
Review Oct 2026

Artificial intelligence in acute stroke imaging: A comprehensive survey from imaging assessment to outcome prediction.

Acute strokes encompass two main types: acute ischemic stroke (AIS) and intracerebral hemorrhage (ICH). Each type involves specific imaging techniques and entails different clinical considerations. While deep learning has facilitated the analysis of stroke imaging autonomously, the technical differences between these t...

Lu-Yao Sun, N. Manshor, Ahmad Sobri Muda et al. · 0 citations
Sep 2026

Ischemic Stroke Segmentation and Net Water Uptake Quantification on Multicenter Non-Contrast CT Using Supervised Target-Domain Adaptation

The approach enabled low-error NWU quantification from baseline NCCT without advanced imaging, supporting further prospective clinical evaluation and targeting NCCT-only infarct segmentation across heterogeneous external cohorts, although performance varied across domains.

Linus Britt, M. Nielsen, S. Klapproth et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.