A composite scaling network of EfficientNet for improving spatial domain identification performance
Yanan Zhao, Chunshen Long, Wenjing Shang, Zhihao Si, Zhigang Liu, Zhenxing Feng, Yongchun Zuo · 2024
Read A composite scaling network of EfficientNet for improving spatial domain identification performance by Yanan Zhao, Chunshen Long, Wenjing Shang, Zhihao Si, Zhigang Liu, Zhenxing Feng, Yongchun Zuo (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11589849.txt.
Description
Yanan Zhao and six co-authors present EfNST, a new computer method for finding regions in tissue from spatial data, in a 2024 research paper. The data pairs gene activity readings with images of the tissue slice. Such data are vast and noisy, so picking out fine regions is hard.
EfNST uses a scaled image network to learn features at several sizes at once. Tested on six data sets from three platforms, the method beat rival tools on accuracy and ran faster on modest hardware. It picked out small subregions in labelled tissue and found matching marker genes. In unlabelled tissue it still found tiny regions and their gene patterns. The work offers a faster way to map how cells are arranged in tissue.
Catalog record
| CREATOR | Yanan Zhao, Chunshen Long, Wenjing Shang, Zhihao Si, Zhigang Liu, Zhenxing Feng, Yongchun Zuo |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |