Deep Learning-Based Collateral Scoring on Multiphase CTA in Patients with Acute Ischemic Stroke in the MCA Region

Collateral circulation is a critical determinant of clinical outcomes in patients with acute ischemic stroke (AIS) and plays a key role in patient selection for endovascular therapy. This study aimed to develop an automated method for assessing and quantifying collateral circulation on multiphase CTA (mCTA), aiming to reduce observer variability and improve diagnostic efficiency.

This retrospective study included mCTA images from 420 patients with AIS within 14 hours of stroke symptom onset. A deep learning-based classification method with a tailored preprocessing module was developed to assess collateral circulation status. Manual evaluations using the simplified Menon method served as the ground truth. Model performance was assessed through 5-fold cross-validation using metrics including accuracy, F1 score, precision, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).

The median age of the 420 patients was 73 years (interquartile range [IQR], 64-80 years; 222 men), and the median time from symptom onset to mCTA acquisition was 123 minutes (IQR, 79-245.5 minutes). The proposed framework achieved an accuracy of 87.6% for 3-class collateral scores (good, intermediate, poor), with the F1 score (85.7%), precision (83.8%), sensitivity (89.3%), specificity (92.9%), AUC (93.7%), intraclass coordination coefficient (ICC) (0.832), and κ (0.781). For 2-class collateral scores, we obtained 94.0% accuracy for good-versus-nongood scores (F1 score [94.4%], precision [95.9%], sensitivity [93.0%], specificity [94.1%], AUC [97.1%], ICC [0.882]), κ [0.881]), and 97.1% for poor-versus-nonpoor scores ([F1 score [98.5%], precision [98.0%], sensitivity [99.0%], specificity [84.8%], AUC [95.6%], ICC [0.740], κ [0.738]). Additional analyses demonstrated that multiphase CTA showed improved performance over single- or 2-phase CTA in the collateral assessment.

The proposed deep learning (DL) framework demonstrated high accuracy and consistency with radiologist-assigned scores for evaluating collateral circulation with mCTA in patients with AIS. This method may offer a useful tool to aid in clinical decision-making, reducing variability and improving diagnostic workflow.