Key result
Deep learning for carotid plaque segmentation achieves a top 0.73 Dice score using ROI-guided U-Net.
Why the study?
Most deep learning studies on carotid plaque detection focus on longitudinal views of the common carotid artery, leaving cross-sectional imaging and regions like the bulb and split largely uninvestigated.
Do deep learning models accurately segment atherosclerotic plaque in cross-sectional carotid ultrasound images compared to manual annotations?
Cross-Sectional
Do deep learning models accurately segment atherosclerotic plaque in cross-sectional carotid ultrasound images compared to manual annotations?
Deep learning models, particularly DeepLabV3 and U-Net architectures, demonstrate strong potential for automated plaque segmentation in cross-sectional carotid ultrasound imaging, with performance substantially improved by ROI-based anatomical guidance.
May support automated carotid plaque analysis in research; leaves open prospective validation before clinical use.
OBJECTIVE: Detection of atherosclerotic plaque in the carotid arteries is essential for early cardiovascular risk assessment. While B-mode ultrasound is the standard imaging modality, most deep learning studies focus on longitudinal views of the common carotid artery, with limited investigation of cross-sectional imaging and other clinically relevant regions such as the carotid bulb and split. To the best of our knowledge, this study presents the first region-specific evaluation of plaque segmentation using deep learning models in cross-sectional carotid ultrasound images. METHODS: Cross-sectional carotid ultrasound images from the 6 y follow-up of the population-based VIPVIZA cohort were analyzed. Two segmentation configurations were investigated: Case 1, where plaque segmentation was performed directly on the full field of view, and Case 2, where segmentation was guided by artery-centered regions of interest (ROIs) derived from manual ground truth annotations. Six deep learning architectures were evaluated: YOLOv8, U-Net, Attention U-Net, U-Net++, Swin U-Net and DeepLabV3. All images were pre-processed using intensity normalization and contrast-limited adaptive histogram equalization to enhance boundary visibility. RESULTS: In the full field of view configuration (Case 1), DeepLabV3 achieved the highest overall Dice score (0.65), followed by Swin U-Net (Dice = 0.64) and U-Net++ (Dice = 0.62), while YOLOv8 and Attention U-Net showed comparable performance (Dice = 0.61). In the ROI-based configuration (Case 2), U-Net achieved the highest segmentation performance in the common carotid artery (Dice = 0.73), while YOLOv8 achieved the best performance in the carotid bulb (Dice = 0.66). In the carotid split region, U-Net++ achieved the highest Dice score (0.87), followed closely by DeepLabV3 (Dice = 0.86) and Attention U-Net (Dice = 0.84). CONCLUSION: Region-specific results from this study support the development of automated plaque segmentation in cross-sectional carotid ultrasound imaging. The findings highlight the importance of anatomical guidance and demonstrate that ROI-based approaches substantially improve segmentation performance. DeepLabV3 and transformer-based models show strong potential in full-image settings, while U-Net-based architectures remain highly effective at ROI-based segmentation.
No takes yet. Share an insight, caveat, or question.
Saboori et al. (2026) conducted a cross-sectional in Sub-clinical atherosclerosis. Deep learning models (DeepLabV3, U-Net, YOLOv8, etc.) vs. Manual ground truth annotations was evaluated on Plaque segmentation performance (Dice score). Deep learning models for plaque segmentation in cross-sectional carotid ultrasounds achieved highest Dice scores using DeepLabV3 (0.65) for full images and U-Net (0.73) for ROI-guided approaches.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: