Evaluating multi-task network architectures for simultaneous breast lesion segmentation and classification in ultrasound images
Margarida R. Ferreira, Helena R. Torres, Bruno Oliveira, Augusto R. V. F. de Araújo, Pedro Morais, Paulo Novais, João L. Vilaça · 2026
Read Evaluating multi-task network architectures for simultaneous breast lesion segmentation and classification in ultrasound images by Margarida R. Ferreira, Helena R. Torres, Bruno Oliveira, Augusto R. V. F. de Araújo, Pedro Morais, Paulo Novais, João L. Vilaça (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-13269153.txt.
Description
Ferreira and six co-authors tested in twenty twenty-six net designs that trace and name breast lumps in sound scans at once. The two tasks share traits, so joint learning may lift each one. Sound scans are noisy and lumps vary a lot, which makes both tasks hard.
They built joint nets from a trace net and a name net in a few shared forms. On eight hundred ten scans from two sites, the best form shared the code from the trace net. It traced lumps with a high match score and named them with near-top scores. The team sees strong aid for breast checks by computer.
Catalog record
| CREATOR | Margarida R. Ferreira, Helena R. Torres, Bruno Oliveira, Augusto R. V. F. de Araújo, Pedro Morais, Paulo Novais, João L. Vilaça |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |