OBJECTIVE: We aimed to develop and validate a radiomics nomogram based on dual-energy computed tomography (DECT) images and clinical features to classify the time since stroke (TSS), which could facilitate stroke decision-making.
METHODS: This retrospective three-center study consecutively included 488 stroke patients who underwent DECT between August 2016 and August 2022. The eligible patients were divided into training, test, and validation cohorts according to the center. The patients were classified into two groups based on an estimated TSS threshold of ≤ 4.5 h. Virtual images optimized the visibility of early ischemic lesions with more CT attenuation. A total of 535 radiomics features were extracted from polyenergetic, iodine concentration, virtual monoenergetic, and non-contrast images reconstructed using DECT. Demographic factors were assessed to build a clinical model. A radiomics nomogram was a tool that the Rad score and clinical factors to classify the TSS using multivariate logistic regression analysis. Predictive performance was evaluated using receiver operating characteristic (ROC) analysis, and decision curve analysis (DCA) was used to compare the clinical utility and benefits of different models.
RESULTS: Twelve features were used to build the radiomics model. The nomogram incorporating both clinical and radiomics features showed favorable predictive value for TSS. In the validation cohort, the nomogram showed a higher AUC than the radiomics-only and clinical-only models (AUC: 0.936 vs 0.905 vs 0.824). DCA demonstrated the clinical utility of the radiomics nomogram model.
CONCLUSIONS: The DECT-based radiomics nomogram provides a promising approach to predicting the TSS of patients.
CONCLUSIONS: The findings support the potential clinical use of DECT-based radiomics nomograms for predicting the TSS.
CONCLUSIONS: Accurately determining the TSS onset is crucial in deciding a treatment approach. The radiomics-clinical nomogram showed the best performance for predicting the TSS. Using the developed model to identify patients at different times since stroke can facilitate individualized management.

UNASSIGNED: To explore whether dual-energy computed tomography (DECT) angiography can provide reliable quantitative information on net water uptake (NWU) of ischemic brain to identify stroke patients within 4.5 h.
UNASSIGNED: We retrospectively reviewed 142 patients with stroke occurrence and who underwent DECT angiography between August 2016 and May 2022. DECT angiography manual drawn the ischemic area by referring to the normal area of the contralateral hemisphere and follow-up images. The NWU in the ischemic area was determined using virtual non-contrast and monoenergetic (VNC &VM) images acquired from DECT angiography. The NWU values in the ischemic area were compared between stroke patients within and beyond 4.5 h. The diagnostic performance of the NWU values derived from the VNC and VM images was assessed through receiver operating characteristic curve analysis. Additionally, Furthermore, we examined the correlation between the NWU values and the stroke onset time.
UNASSIGNED: Seventy-eight (54.93 %) stroke patients underwent DECT angiography and within 4.5 h. These patients with lower median National Institute of Health stroke scale (NIHSS) scores on admission than those beyond 4.5 h (p < 0.05). Furthermore, the group within 4.5 h had lower NWU values than did the group beyond 4.5 h on all VNC and VM images (p < 0.001). The analysis revealed that the NWU values determined using the VM (60 keV) images had the highest predictive efficiency (AUC, 0.95; sensitivity, 100 %; and specificity, 89.06 %) and showed the strongest positive correlation with stroke onset time (r-value = 0.58, p < 0.001).
UNASSIGNED: Our findings showed that DECT angiography-based quantification of NWU helps identify the stroke patients within 4.5 h with high predictive efficiency. Thus, NWU values determined using VM (60 keV) images could serve as a significant biomarker for stroke onset time.