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

Journal Article (Journal Article)

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 (r2 > 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.

Full Text

Duke Authors

Cited Authors

  • Gauriau, R; Bizzo, BC; Comeau, DS; Hillis, JM; Bridge, CP; Chin, JK; Pawar, J; Pourvaziri, A; Sesic, I; Sharaf, E; Cao, J; Noro, FTC; Wiggins, WF; Caton, MT; Kitamura, F; Dreyer, KJ; Kalafut, JF; Andriole, KP; Pomerantz, SR; Gonzalez, RG; Lev, MH

Published Date

  • January 5, 2023

Published In

Volume / Issue

  • 13 / 1

Start / End Page

  • 189 -

PubMed ID

  • 36604467

Pubmed Central ID

  • PMC9814956

Electronic International Standard Serial Number (EISSN)

  • 2045-2322

Digital Object Identifier (DOI)

  • 10.1038/s41598-023-27496-5


  • eng

Conference Location

  • England