Deep ensemble optimized models for probabilistic CTV breast segmentation
Cecilia Riani, Maria Giulia Ubeira-Gabellini, Gabriele Palazzo, Giuseppe Ricciardi, Antonella del Vecchio, Alessandra Palma, Anna Balsamo, Angela Coniglio, Claudio Fiorino · 2026
Read Deep ensemble optimized models for probabilistic CTV breast segmentation by Cecilia Riani, Maria Giulia Ubeira-Gabellini, Gabriele Palazzo, Giuseppe Ricciardi, Antonella del Vecchio, Alessandra Palma, Anna Balsamo, Angela Coniglio, Claudio Fiorino (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/pmc-13171566.txt.
Description
Cecilia Riani and colleagues build chance maps for breast targets with deep model teams, in work from 2026. Radiation care needs exact outlines of target and risk organs to limit harm. Hand drawn outlines vary between clinicians, so model outputs must face that doubt head on rather than hide it.
Close to one thousand planning scans trained six deep models for both breast sides. All models matched expert spread on overlap scores in the test set. Four models led on surface distance scores with close results among them. Two models trailed the pack in paired statistical checks on the same scans. Top models then formed chance maps that show where outlines agree or split.
Catalog record
| CREATOR | Cecilia Riani, Maria Giulia Ubeira-Gabellini, Gabriele Palazzo, Giuseppe Ricciardi, Antonella del Vecchio, Alessandra Palma, Anna Balsamo, Angela Coniglio, Claudio Fiorino |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |