Automated delineation of acute ischemic stroke lesions on non-contrast CT using 3D deep learning: A promising step towards efficient diagnosis and treatment

•SwinUNETR + uncertainty quantification aids acute ischemic stroke diagnosis via NCCT.•The proposed model predicted lesion volume with a mean Dice score: 46.7 %.•Our method was tested on the public AISD dataset, resulting in a Dice score: 61.9 %.•The study explores feasibility of the model’s applications in the clinical scenario. We adopt the existing Deep learning architecture to support diagnosing acute ischemic stroke by automatically detecting lesion location on 3D non-contrast CT brain scans. We also investigate the feasibility of the model’s applications in the clinical scenario by data analysis. We retrospectively collected 3D non-contrast CT scans of 317 patients with acute ischemic stroke from the China Medical University Hospital. All patients underwent standard baseline non-contrast CT scanning followed by diffusion-weighted imaging. We utilized these data for training the existing model – SwinUNETR, which includes a self-attention module as an encoder and a convolutional-based decoder. Moreover, the software innovatively incorporates uncertainty quantification to enhance model performance. In the test set, the AI model predicted lesion volume with a mean Dice score of 46.7 % compared to diffusion-weighted imaging verified by experts. The model completed the analysis on a 3D non-contrast CT scan in approximately 30 s. The average difference between the model-segmented acute ischemic stroke lesion volume (67.11 ml) and diffusion-weighted imaging lesion volume (35.2 ml) was 27.09 ml. Pearson correlation of lesion volume between prediction and ground truth is 83.46 %. We also found our model has superior performance in the CT scan with lesion volume > 40 ml and 3 h < onset-to-CT time