Abstract: Objective To investigate the predictive value of CT perfusion imaging (CTP) for early neurological deterioration (END) within 72 h after onset in patients with minor stroke caused by acute anterior circulation large vessel occlusion (mLVO-AIS) treated with medical therapy alone.Methods Retrospective analysis was conducted on 116 patients with mLVO-AIS who were admitted to the Stroke Center of Yancheng First People's Hospital between January 2021 and December 2024, within 24 h after onset. Neurological function was assessed using the National Institutes of Health Stroke Scale (NIHSS). END was defined as an increase in NIHSS score of ≥4 points within 72 h compared with the score at admission. The patients were divided into a deterioration group (n=32; including 14 patients who underwent rescue endovascular treatment EVT) and a stable group (n=84). Clinical characteristics were compared between groups. Multivariate logistic regression was performed to identify independent predictors of END, and receiver operating characteristic (ROC) curves were plotted to evaluate the predictive performance of CTP parameters.Results Univariate analysis showed that the two groups differed significantly in the prevalence of diabetes, proportion of first-ever stroke, Tmax-ASPECTS score, CBF-ASPECTS score, and CBV-ASPECTS score (all P<0.05). Multivariate logistic regression demonstrated that diabetes and CBV-ASPECTS score were independent predictors of END within 72 h in patients with mLVO-AIS. The area under the ROC curve (AUC) of CBV-ASPECTS score for predicting END was 0.808, with a sensitivity of 0.688 and specificity of 0.893. In the deterioration group, patients receiving rescue EVT showed significant differences in NIHSS score at discharge and the rate of favorable outcome at 90 days, compared with those who continued conservative treatment (both P<0.05). However, there were no significant differences in the incidence of symptomatic intracerebral hemorrhage (sICH) or mortality (P>0.05).Conclusions CTP-related parameters can help identify patients with mLVO-AIS at high risk of END at an early stage, providing useful guidance for clinical intervention.