Automatic segmentation of bioabsorbable vascular stents in Intravascular optical coherence images using weakly supervised attention network

Abstract Coronary heart disease has become a disease with high mortality in the world. The main treatment for coronary heart disease is stent implantation, and there is now a consensus that bioabsorbable stent is the most advanced stent. However, the accuracy of all methods to detect and segment the bioabsorbable stents is still not perfect enough to meet the medical needs, or it is difficult to generalize. Meanwhile, due to the influence of blood artifact, the grey-based method also has great errors and uncertainties. In this paper, we propose a new framework to segment the bioabsorbable stent to observe accuracy of the effect after implantation. In order to segment the contour of BVS and improve the existing algorithm, we use the U-Net network as the main part of the proposed network structure, add convolutional attention layer and dilated convolution module, and finally use weakly supervised learning strategy to further enhance segmentation. Extensive experiments demonstrate that each designed module in our proposed network can effectively improve the accuracy of the result, and when compared with other state-of-the-art methods, the experimental performance under the overall network structure is higher.