Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet
Donya Khaledyan, Thomas J. Marini, Timothy M. Baran, Avice O’Connell, Kevin Parker · 2023
Read Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet by Donya Khaledyan, Thomas J. Marini, Timothy M. Baran, Avice O’Connell, Kevin Parker (2023) 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-10718429.txt.
Description
Donya Khaledyan and co-authors design a sharper neural network for outlining tumors in breast ultrasound images, in a 2023 study. Drawing the border of a breast mass by hand is slow and varies between readers, so aid tools matter for diagnosis. The team combined two known network designs, one built for crisp edges and one that pays attention to key regions, and tuned the blend carefully.
Their combined model scored highest on overlap and detection measures against the parent designs and a standard network, with statistical tests backing the gaps. Preprocessing and tuning choices each moved the scores. The authors present the model as a step toward more reliable computer-aided breast diagnosis.
Catalog record
| CREATOR | Donya Khaledyan, Thomas J. Marini, Timothy M. Baran, Avice O’Connell, Kevin Parker |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |