Thrombus Localization in Middle Cerebral Artery of Patient with Acute Ischemic Stroke on ncCT Image

Beesomboon, Donlawit; Kaothanthong, Natsuda; Songsaeng, Dittapong; Chansumpao, Tanapon; Sarampakhul, Soawapot

doi:10.1109/stud49732.2019.9018823

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thrombus segmentation on CT scans was first reported by Santos et al [11] who developed a semi-automated method, which uses manually selected proximal and distal seed points and the contralateral artery to segment the thrombus on CTA scans. Beesomboon et al [15] extract a number of brain regions with similar intensity on NCCT and then proceed to eliminate the non-thrombus regions with a rule-based algorithm. However, they only provide visual comparison with ground truth without reporting any quantifiable measures.…”

Section: Introductionmentioning

confidence: 99%

Fully Automated Thrombus Segmentation on CT Images of Patients with Acute Ischemic Stroke

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%