|
Carotid arteries vulnerable plaques are a crucial factor in the screening of atherosclerosis by ultrasound technique. However, manual plaque segmentation may be time-consuming and variable, moreover, the unstable plaques are contaminated by various noises such as artifacts and speckle noise. This paper proposes an automatic convolutional neural network (CNN) method for plaque segmentation in carotid ultrasound images using a small dataset. Firstly, a parallel network with three independent scale decoders is utilized as our base segmentation network, and pyramid dilated convolutions are used to enlarge receptive fields in three decoder sub-networks. Subsequently, the merged feature maps from the three decoders are rectified by the SENet. Thirdly, in the testing, the initial segmented plaque is refined by the maximal contour postprocessing method to obtain the final segmentation result. The dataset consists of 30 carotid ultrasound images with severe stenosis plaques from 30 patients. Test results show that the proposed method yields a Dice value of 0.820, IoU of 0.701, Accuracy of 0.969, and modified Hausdorff distance (MHD) of 1.43 by 10-fold cross-validation, it outperforms some CNN-based methods on these metrics. Additionally, we apply an ablation experiment to show the validity of each proposed module. Our method may be useful in actual applications for carotid unstable (easily ruptured or severe stenosis) plaques segmentation from ultrasound images.
|
