期刊
2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI)
卷 -, 期 -, 页码 419-423出版社
IEEE
DOI: 10.1109/ISBI48211.2021.9433930
关键词
Ultrasound; Style transfer; Segmentation
资金
- National Key R&D Program of China [2019YFC0118300]
- Shenzhen Peacock Plan [KQTD2016053112051497, KQJSCX201 80328095606003]
This paper proposed a robust segmentation method for unknown appearance shifts by embedding hierarchical style transfer units and adopting Dynamic Instance Normalization, which can achieve precise and dynamic style transfer in a fast and lightweight manner. Extensive experiments on a large dataset from three vendors demonstrate that the proposed method enhances the robustness of deep segmentation models.
Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis. Retraining models leads to high latency and complex pipelines, which are impractical in clinical settings. The situation becomes more severe for ultrasound image analysis because of their large appearance shifts. In this paper, we propose a novel method for robust segmentation under unknown appearance shifts. Our contribution is three-fold. First, we advance a one-stage plug-and-play solution by embedding hierarchical style transfer units into a segmentation architecture. Our solution can remove appearance shifts and perform segmentation simultaneously. Second, we adopt Dynamic Instance Normalization to conduct precise and dynamic style transfer in a learnable manner, rather than previously fixed style normalization. Third, our solution is fast and lightweight for routine clinical adoption. Given 400x400 image input, our solution only needs an additional 0.2 ms and 1.92M FLOPs to handle appearance shifts compared to the baseline pipeline. Extensive experiments are conducted on a large dataset from three vendors demonstrate our proposed method enhances the robustness of deep segmentation models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据