Interactive segmentation of medical images using deep learning

Abstract

Abstract Medical image segmentation algorithms based on deep learning has achieved good segmentation results in recent years, but it requires a large amount of labeled data. When performing pixel-level labeling on medical images, labeling a target requires marking ten or even hundreds of points along its edge, which requires a lot of time and labor costs. In order to reduce the labeling cost, we utilize a click-
based interactive segmentation method to generate high-quality segmentation labels. However, current interactive segmentation algorithms, only the interaction information clicked by the user and the image features are fused as the input of the backbone
network (so-called early fusion). The early fusion method has the problem that the interactive information is much sparse at this time. Furthermore, the interactive segmentation algorithms do not take into account the boundary problem, resulting
in poor model performance. So we propose early fusion and late fusion strategy to prevent the interaction information from being diluted prematurely and make better use of the interaction information. At the same time, we propose a decoupled head structure, by extracting the image boundary information, combining the boundary loss function to establish the boundary constraint term, so that the network can pay more attention to the boundary information and further improve the performance of the network. Finally, we conduct experiments on three medical datasets (Chaos, VerSe and Uterine Myoma ) to verify the effectiveness of our network. The experimental results show that our network has a large improvement compared with the baseline, and NoC@80 improved by 0.1, 0.1, and 0.2. In particular, we achieve 1.82 NoC@80 on Chaos. According to statistics, it takes 25 minutes to label a case(Uterine Myoma). Annotating a
medical image with our method can be done in only 2 or 3 clicks. Can save more than 50% of the cost.