Breast ultrasound images for segmentation and classification using multi-task U-Net
Maddhi Anitha, Ch Rajendra Prasad, Joseph Bamidele Awotunde, Abidemi Emmanuel Adeniyi, Oluwasegun Julius Aroba · 2026
Read Breast ultrasound images for segmentation and classification using multi-task U-Net by Maddhi Anitha, Ch Rajendra Prasad, Joseph Bamidele Awotunde, Abidemi Emmanuel Adeniyi, Oluwasegun Julius Aroba (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-13328415.txt.
Description
Maddhi Anitha and co-authors present a 2026 paper on a deep learning model that reads breast ultrasound images. Ultrasound is a cheap, handy tool for early breast cancer checks, above all in dense breasts. Its use is marred by speckle noise, low contrast, and reader skill gaps.
Their model does two jobs at once: it outlines the lesion and classifies the tumor. Shared features feed both tasks, with a fix-up step that keeps the two outputs in accord. A focus mechanism sharpens lesion spots, and a cleaned data set removes duplicate and clashing samples. Set oversampling eases class imbalance. Scores beat baseline models on both tasks. The authors claim strong promise for clinic use.
Catalog record
| CREATOR | Maddhi Anitha, Ch Rajendra Prasad, Joseph Bamidele Awotunde, Abidemi Emmanuel Adeniyi, Oluwasegun Julius Aroba |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |