Deep learning-based detection of murine congenital heart defects from µCT scans
Hoa Nguyen, Audrey Desgrange, Amaia Ochandorena-Saa, Vanessa Benhamo, Ségolène Bernheim, Lucile Houyel, Sigolène M Meilhac, Christophe Zimmer · 2025
Read Deep learning-based detection of murine congenital heart defects from µCT scans by Hoa Nguyen, Audrey Desgrange, Amaia Ochandorena-Saa, Vanessa Benhamo, Ségolène Bernheim, Lucile Houyel, Sigolène M Meilhac, Christophe Zimmer (2025) 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-12727836.txt.
Description
Hoa Nguyen and co-authors train deep learning to spot heart defects in mouse embryos from three dimensional scans, in a study from 2025. Tiny CT imaging reveals malformed hearts clearly, but reading each scan by hand is slow expert work. Automating the screen would speed studies of how heart defects arise.
On a set of one hundred thirty nine scans from normal and mutant mice, their model separated healthy from malformed hearts with very high accuracy. Fresh scans gathered after training scored even better. A harder set with new mutation types scored lower until the model was briefly retrained, after which accuracy recovered well. A free viewing plugin lets biologists without coding skills run and retrain the tool themselves.
Catalog record
| CREATOR | Hoa Nguyen, Audrey Desgrange, Amaia Ochandorena-Saa, Vanessa Benhamo, Ségolène Bernheim, Lucile Houyel, Sigolène M Meilhac, Christophe Zimmer |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |