Automatic CT Angiography Lesion Segmentation Compared to CT Perfusion in Ischemic Stroke Detection: a Feasibility Study

• Published in: Journal of digital imaging 2022-06, Vol.35 (3), p.551-563
• Main Authors: Mäkelä, Teemu, Öman, Olli, Hokkinen, Lasse, Wilppu, Ulla, Salli, Eero, Savolainen, Sauli, Kangasniemi, Marko
• Format: Article
• Language: English
• Subjects: Algorithms; Angiography; Artificial neural networks; Computed tomography; Computed Tomography Angiography; Confidence intervals; Feasibility Studies; Humans; Image segmentation; Imaging; Ischemia; Ischemic Stroke; Lesions; Lower bounds; Medical imaging; Medicine; Medicine & Public Health; Model accuracy; Neural networks; Original Paper; Perfusion; Radiology; Stroke; Stroke - diagnostic imaging; Substantia alba; Tomography, X-Ray Computed - methods
• ISSN: 0897-1889; 1618-727X
• DOI: 10.1007/s10278-022-00611-0

In stroke imaging, CT angiography (CTA) is used for detecting arterial occlusions. These images could also provide information on the extent of ischemia. The study aim was to develop and evaluate a convolutional neural network (CNN)–based algorithm for detecting and segmenting acute ischemic lesions from CTA images of patients with suspected middle cerebral artery stroke. These results were compared to volumes reported by widely used CT perfusion–based RAPID software (IschemaView). A 42-layer-deep CNN was trained on 50 CTA volumes with manually delineated targets. The lower bound for predicted lesion size to reliably discern stroke from false positives was estimated. The severity of false positives and false negatives was reviewed visually to assess the clinical applicability and to further guide the method development. The CNN model corresponded to the manual segmentations with voxel-wise sensitivity 0.54 (95% confidence interval: 0.44–0.63), precision 0.69 (0.60–0.76), and Sørensen–Dice coefficient 0.61 (0.52–0.67). Stroke/nonstroke differentiation accuracy 0.88 (0.81–0.94) was achieved when only considering the predicted lesion size (i.e., regardless of location). By visual estimation, 46% of cases showed some false findings, such as CNN highlighting chronic periventricular white matter changes or beam hardening artifacts, but only in 9% the errors were severe, translating to 0.91 accuracy. The CNN model had a moderately strong correlation to RAPID-reported T max  > 10 s volumes (Pearson’s r  = 0.76 (0.58–0.86)). The results suggest that detecting anterior circulation ischemic strokes from CTA using a CNN-based algorithm can be feasible when accompanied with physiological knowledge to rule out false positives.