Head CT deep learning model is highly accurate for early infarct estimation

Non-contrast head CT (NCCT) is extremely insensitive for early (<3-6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61-66% (specificity 90-92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r(2)>0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70 mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.

Automated summary

Non-contrast head CT is not sensitive for early acute infarct identification. We developed a deep learning model that detects and delineates suspected early infarcts on NCCT using diffusion MRI as ground truth. The model outperformed expert neuroradiologists in sensitivity and specificity for detecting stroke, and showed strong correlation with diffusion MRI for infarct volume estimation.