Publications by authors named "T S Hatsukami"
Background: Carotid atherosclerosis is a major etiology of stroke. Although intraplaque hemorrhage (IPH) is known to increase stroke risk and plaque burden, its long-term effects on plaque dynamics remain unclear.
Objectives: This study aimed to evaluate the long-term impact of IPH on carotid plaque burden progression using deep learning-based segmentation on multi-contrast vessel wall imaging (VWI).
Purpose: Embolic stroke of unidentified source (ESUS) represents 10-25% of all ischemic strokes. Our goal was to determine whether ESUS could be reclassified to cardioembolic (CE) or large-artery atherosclerosis (LAA) with machine learning (ML) using conventional clinical data.
Methods: We retrospectively collected conventional clinical features, including patient, imaging (MRI, CT/CTA), cardiac, and serum data from established cases of CE and LAA stroke, and factors with p < 0.
Article Synopsis
- * A new model was developed using a variational autoencoder framework, which incorporated a unique dissimilarity loss to enhance the model's ability to learn key MRI features and improve segmentation accuracy.
- * The model outperformed nine existing methods in tests with 113 subjects, demonstrating significant improvements in various performance metrics for both segmentation and detection, suggesting it could greatly advance MRI analysis in clinical settings.
The clinical significance of measuring vessel wall thickness is widely acknowledged. Recent advancements have enabled high-resolution 3D scans of arteries and precise segmentation of their lumens and outer walls; however, most existing methods for assessing vessel wall thickness are 2D. Despite being valuable, reproducibility and accuracy of 2D techniques depend on the extracted 2D slices.
View Article and Find Full Text PDF