In this study, the authors investigated how feasible it was to use 3D convolutional neural networks (CNN) to detect ischemic stroke from computed tomography angiography source images (CTA-SI). The study used CTA-SI from 60 randomly selected patients who had a suspected acute ischemic stroke of the middle cerebral artery; half of the patients were used in the neural network training, and the subsequent testing was performed using the remaining 30 patients. The authors found that the results of the study supported their hypothesis that 3D convolutional neural network-based software from CTA-SI can be used to detect an acute ischemic stroke lesion.
- This is the first study applying three-dimensional convolutional neural networks (3D CNN) to computed tomography angiography (CTA) source images for ischemic stroke detection
- Stroke detection was improved when cerebral hemispheric comparison and non-contrast computed tomography (NCCT) were included in the CNN analysis.
- High sensitivity and specificity in the detection of stroke lesions was achieved
Authors: Olli Öman, Teemu Mäkelä, Eero Salli, Sauli Savolainen and Marko Kangasniemi