GeneSegNet: a deep learning framework for cell segmentation by integrating gene expression and imaging
Problem
Identifying cell boundaries and assigning RNA reads to cells in in situ RNA detection data, complicated by noisy training labels.
Why it matters
Cell segmentation is essential for studying gene expression and morphological features of cells.
What the AI did
GeneSegNet, a deep-learning framework, integrates gene expression and imaging information for segmentation, with a recursive training strategy for noisy labels.
Results
Claims significant improvement over existing methods; no numeric metrics in abstract
Impact
Peer-reviewed framework improving cell segmentation for in situ RNA analysis pipelines.
Record
| Venue | Genome biology |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Yuxing Wang, Wenguan Wang, Dongfang Liu, Wenpin Hou, Tianfei Zhou, Zhicheng Ji |
| Citations | 45 (OpenAlex, at import time) |
| References | 44 |
| Model or method | GeneSegNet (deep learning framework) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1186/s13059-023-03054-0 |
| Open access | gold |
| Keywords | deep learning, cell segmentation, gene expression, in situ RNA, GeneSegNet |
Importance rating
real but narrower advance
Cell segmentation is an essential step for in situ RNA analysis, but the abstract claims only significant improvement over existing methods with no scale or application breadth stated.