Performance of e-ASPECTS software in comparison to that of stroke physicians on assessing CT scans of acute ischemic stroke patients

Background: ASPECTS is an established 10-point quantitative topographic CT scan score to assess early ischemic changes. The authors compared the performance of the e-ASPECTS software with those of stroke physicians at different professional levels.

Methods: Baseline CT scans of acute stroke patients (with CT and DWI obtained less than two hours apart) were retrospectively scored by e-ASPECTS, three stroke experts, and three neurology trainees blinded to clinical information. Ground truth was the ASPECTS on DWI scored by two non-blinded independent experts on consensus. Sensitivity, specificity, ROC curves, Bland–Altman plots, and Matthews correlation coefficients were calculated against DWI as the ground truth.

Results: 34 patients were included (680 ASPECTS regions scored). Region-based sensitivity (46.46%) of e-ASPECTS was better than three trainees and one expert and not different from two other experts. Specificity (94.15%) was lower than one expert and one trainee and not different from the other four. e-ASPECTS had the best Matthews correlation coefficient (0.44) and the lowest mean score error (0.56).

Conclusion: e-ASPECTS showed a similar performance to that of stroke experts in the assessment of brain CTs of acute ischemic stroke patients with the ASPECTS method.