Key result
DualPlaqueNet outperformed U-Net, ResUnet, and TransUNet in carotid plaque semantic segmentation, achieving a Mean Intersection over Union of 88.91% and an Accuracy of 95.98%.
Why the study?
Carotid ultrasound images suffer from high noise, low contrast, and blurred edges, making it difficult for traditional image processing methods to accurately extract plaque information.
Does the DualPlaqueNet model improve semantic segmentation and size prediction of carotid plaques in ultrasound images compared to other deep learning models?
Does the DualPlaqueNet model improve semantic segmentation and size prediction of carotid plaques in ultrasound images compared to other deep learning models?
The DualPlaqueNet model provides highly accurate semantic segmentation and size prediction of carotid plaques in ultrasound images, outperforming traditional deep learning models.
May aid carotid plaque assessment on ultrasound; leaves open prospective validation against clinical outcomes.
Background With global aging and lifestyle changes, carotid atherosclerotic plaques are a major cause of cerebrovascular disease and ischemic stroke. However, ultrasound images suffer from high noise, low contrast, and blurred edges, making it difficult for traditional image processing methods to accurately extract plaque information. Objective To establish a deep learning-based DualPlaqueNet model for semantic segmentation and size prediction of plaques in carotid ultrasound images, thereby providing comprehensive and accurate auxiliary information for clinical risk assessment and personalized diagnosis and treatment. Methods DualPlaqueNet uses a dual-branch architecture combined with attention mechanisms and joint loss functions to optimize segmentation and regression. Notably, a multi-layer one-dimensional convolutional structure is introduced within the Efficient Channel Attention (ECA) module. The original dataset contained 287 carotid ultrasound images from patients at Zhengzhou First People’s Hospital, which were divided into training, validation, and test sets. Model training, validation, and testing were performed after preprocessing and data augmentation of the training set. Its performance was compared with three other models. Results In the plaque semantic segmentation task, DualPlaqueNet outperformed the other three models across all metrics, achieving MIoU of 88.91 ± 1.027 (%), IoU (excluding background) of 88.22 ± 1.065 (%), DSC of 89.95 ± 1.102 (%), and Accuracy of 95.98 ± 0.073 (%). For plaque size prediction, this model demonstrated lower MSE and MAE, along with a higher coefficient of determination R 2 , proving its ability to accurately extract plaque size information from ultrasound images. Conclusion The dual-branch design and attention mechanisms of DualPlaqueNet effectively address the challenges of ultrasound images, achieving precise segmentation and size prediction, demonstrating its potential as an auxiliary tool for future clinical applications.
No takes yet. Share an insight, caveat, or question.
Deng et al. (2025) studied Carotid atherosclerotic plaques (n=287). DualPlaqueNet vs. U-Net, ResUnet, and TransUNet was evaluated on Mean Intersection over Union (MIoU) for plaque semantic segmentation. DualPlaqueNet outperformed U-Net, ResUnet, and TransUNet in carotid plaque semantic segmentation, achieving a Mean Intersection over Union of 88.91% and an Accuracy of 95.98%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: