Automated CT angiography collateral scoring in anterior large vessel occlusion stroke: A multireader study

Background: Computed tomography (CT) angiography collateral score (CTA-CS) is an important clinical outcome predictor following mechanical thrombectomy for ischemic stroke with large vessel occlusion (LVO). The present multireader study aimed to evaluate the performance of e-CTA software for automated assistance in CTA-CS scoring.

Materials and methods: Brain CTA images of 56 patients with anterior LVO were retrospectively processed. Twelve readers of various clinical training graded collateral flow using the visual CTA-CS scale in two sessions separated by a washout period; the reference standard was the consensus of three expert readers. Reading time, inter-rater reliability, and performance metrics were compared between the e-CTA-assisted and unassisted sessions.

Results: e-CTA assistance significantly increased mean accuracy (58.6% to 67.5%, p = 0.003), F1 score (0.574 to 0.676), precision, and recall, especially with slight filling deficit. Mean reading time was reduced (103.4 to 59.7 s, p = 0.001), inter-rater agreement increased (Krippendorff's alpha 0.366 to 0.676), and occlusion laterality detection improved (92.9% to 96.8%).

Conclusion: Automated assistance for CTA-CS using e-CTA software provided helpful decision support, improving scoring accuracy and reading efficiency for physicians across a range of experience and significantly improving inter-rater agreement.