We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Fully Automated Thrombus Segmentation on CT Images of Patients with Acute Ischemic Stroke.
- Authors
Mojtahedi, Mahsa; Kappelhof, Manon; Ponomareva, Elena; Tolhuisen, Manon; Jansen, Ivo; Bruggeman, Agnetha A. E.; Dutra, Bruna G.; Yo, Lonneke; LeCouffe, Natalie; Hoving, Jan W.; van Voorst, Henk; Brouwer, Josje; Terreros, Nerea Arrarte; Konduri, Praneeta; Meijer, Frederick J. A.; Appelman, Auke; Treurniet, Kilian M.; Coutinho, Jonathan M.; Roos, Yvo; van Zwam, Wim
- Abstract
Thrombus imaging characteristics are associated with treatment success and functional outcomes in stroke patients. However, assessing these characteristics based on manual annotations is labor intensive and subject to observer bias. Therefore, we aimed to create an automated pipeline for consistent and fast full thrombus segmentation. We used multi-center, multi-scanner datasets of anterior circulation stroke patients with baseline NCCT and CTA for training (n = 228) and testing (n = 100). We first found the occlusion location using StrokeViewer LVO and created a bounding box around it. Subsequently, we trained dual modality U-Net based convolutional neural networks (CNNs) to segment the thrombus inside this bounding box. We experimented with: (1) U-Net with two input channels for NCCT and CTA, and U-Nets with two encoders where (2) concatenate, (3) add, and (4) weighted-sum operators were used for feature fusion. Furthermore, we proposed a dynamic bounding box algorithm to adjust the bounding box. The dynamic bounding box algorithm reduces the missed cases but does not improve Dice. The two-encoder U-Net with a weighted-sum feature fusion shows the best performance (surface Dice 0.78, Dice 0.62, and 4% missed cases). Final segmentation results have high spatial accuracies and can therefore be used to determine thrombus characteristics and potentially benefit radiologists in clinical practice.
- Subjects
STROKE patients; COMPUTED tomography; THROMBOSIS; IMAGE segmentation; CONVOLUTIONAL neural networks
- Publication
Diagnostics (2075-4418), 2022, Vol 12, Issue 3, p698
- ISSN
2075-4418
- Publication type
Article
- DOI
10.3390/diagnostics12030698