4.7 Article

Global Pixel Transformers for Virtual Staining of Microscopy Images

期刊

IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 39, 期 6, 页码 2256-2266

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.2968504

关键词

Microscopy; Task analysis; Predictive models; Convolution; Fuses; Tensors; Computational modeling; Cellular structures; microscopy images; fluorescence imaging; virtual staining; global pixel transformers; dense blocks; multi-scale inputs

资金

  1. National Science Foundation [IIS-1633359, IIS-1615035, DBI-1641223]

向作者/读者索取更多资源

Visualizing the details of different cellular structures is of great importance to elucidate cellular functions. However, it is challenging to obtain high quality images of different structures directly due to complex cellular environments. Fluorescence staining is a popular technique to label different structures but has several drawbacks. In particular, label staining is time consuming and may affect cell morphology, and simultaneous labels are inherently limited. This raises the need of building computational models to learn relationships between unlabeled microscopy images and labeled fluorescence images, and to infer fluorescence labels of other microscopy images excluding the physical staining process. We propose to develop a novel deep model for virtual staining of unlabeled microscopy images. We first propose a novel network layer, known as the global pixel transformer layer, that fuses global information from inputs effectively. The proposed global pixel transformer layer can generate outputs with arbitrary dimensions, and can be employed for all the regular, down-sampling, and up-sampling operators. We then incorporate our proposed global pixel transformer layers and dense blocks to build an U-Net like network. We believe such a design can promote feature reusing between layers. In addition, we propose a multi-scale input strategy to encourage networks to capture features at different scales. We conduct evaluations across various fluorescence image prediction tasks to demonstrate the effectiveness of our approach. Both quantitative and qualitative results show that our method outperforms the state-of-the-art approach significantly. It is also shown that our proposed global pixel transformer layer is useful to improve the fluorescence image prediction results.

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。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据