TGDBN: Topology-guided dual-backbone network for semi-supervised blastocyst segmentation in assisted reproductive technology
Yiming Li, Hua Wang, Jingfei Hu, Jicong Zhang · 2026
Read TGDBN: Topology-guided dual-backbone network for semi-supervised blastocyst segmentation in assisted reproductive technology by Yiming Li, Hua Wang, Jingfei Hu, Jicong Zhang (2026) 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/plos-pone-0355053.txt.
Description
Yiming Li, Hua Wang, and colleagues propose in 2026 a network for outlining embryo structures in images used during fertility treatment. Clear outlines help judge whether an embryo may implant, but embryos are see through, nested, and hard to label in bulk. Their single model has two heads: one paints the regions and one guides the overall shape using structure cues.
Two added modules sharpen hard, low contrast borders and gather features at several scales. On a public embryo dataset the method beat eleven rival semi supervised methods, and it also held up on a heart chamber dataset. Clearer outlines could support more consistent embryo grading.
Catalog record
| CREATOR | Yiming Li, Hua Wang, Jingfei Hu, Jicong Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38804 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |