TY - JOUR
T1 - A convolutional neural network for anterior intra-arterial thrombus detection and segmentation on non-contrast computed tomography of patients with acute ischemic stroke
AU - Tolhuisen, Manon L.
AU - Ponomareva, Elena
AU - Boers, Anne M. M.
AU - Jansen, Ivo G. H.
AU - Koopman, Miou S.
AU - Barros, Renan Sales
AU - Berkhemer, Olvert A.
AU - van Zwam, Wim H.
AU - van der Lugt, Aad
AU - Majoie, Charles B. L. M.
AU - Marquering, Henk A.
PY - 2020/7/1
Y1 - 2020/7/1
N2 - The aim of this study was to develop a convolutional neural network (CNN) that automatically detects and segments intra-arterial thrombi on baseline non-contrast computed tomography (NCCT) scans. We retrospectively collected computed tomography (CT)-scans of patients with an anterior circulation large vessel occlusion (LVO) from the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands trial, both for training (n = 86) and validation (n = 43). For testing we included patients with (n = 58) and without (n = 45) an LVO from our comprehensive stroke center. Ground truth was established by consensus between two experts using both CT angiography and NCCT. We evaluated the CNN for correct identification of a thrombus, its location and thrombus segmentation and compared these with the results of a neurologist in training and expert neuroradiologist. Sensitivity of the CNN thrombus detection was 0.86, vs. 0.95 and 0.79 for the neuroradiologists. Specificity was 0.65 for the network vs. 0.58 and 0.82 for the neuroradiologists. The CNN correctly identified the location of the thrombus in 79% of the cases, compared to 81% and 77% for the neuroradiologists. The sensitivity and specificity for thrombus identification and the rate for correct thrombus location assessment by the CNN were similar to those of expert neuroradiologists.
AB - The aim of this study was to develop a convolutional neural network (CNN) that automatically detects and segments intra-arterial thrombi on baseline non-contrast computed tomography (NCCT) scans. We retrospectively collected computed tomography (CT)-scans of patients with an anterior circulation large vessel occlusion (LVO) from the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands trial, both for training (n = 86) and validation (n = 43). For testing we included patients with (n = 58) and without (n = 45) an LVO from our comprehensive stroke center. Ground truth was established by consensus between two experts using both CT angiography and NCCT. We evaluated the CNN for correct identification of a thrombus, its location and thrombus segmentation and compared these with the results of a neurologist in training and expert neuroradiologist. Sensitivity of the CNN thrombus detection was 0.86, vs. 0.95 and 0.79 for the neuroradiologists. Specificity was 0.65 for the network vs. 0.58 and 0.82 for the neuroradiologists. The CNN correctly identified the location of the thrombus in 79% of the cases, compared to 81% and 77% for the neuroradiologists. The sensitivity and specificity for thrombus identification and the rate for correct thrombus location assessment by the CNN were similar to those of expert neuroradiologists.
KW - Acute ischemic stroke
KW - Anterior large vessel occlusion detection
KW - Convolutional neural network
KW - Non-contrast computed tomography
UR - http://www.scopus.com/inward/record.url?scp=85088649064&partnerID=8YFLogxK
U2 - https://doi.org/10.3390/app10144861
DO - https://doi.org/10.3390/app10144861
M3 - Article
SN - 2076-3417
VL - 10
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 14
M1 - 4861
ER -