Deep Learning for Tumor Segmentation and Multiclass Classification in Breast Ultrasound Images Using Pretrained Models
K. E. ArunKumar, Matthew E. Wilson, Nathan E. Blake, Tylor J. Yost, Matthew Walker · 2025
Read Deep Learning for Tumor Segmentation and Multiclass Classification in Breast Ultrasound Images Using Pretrained Models by K. E. ArunKumar, Matthew E. Wilson, Nathan E. Blake, Tylor J. Yost, Matthew Walker (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-12736871.txt.
Description
K. E. ArunKumar and colleagues published a medical imaging study in 2025 on breast ultrasound analysis. Ultrasound is a common first tool for checking breast lesions. The authors built artificial intelligence tools to outline tumors and classify them. Classes covered normal tissue, harmless lumps, and cancerous ones.
They trained pretrained image models on a public ultrasound dataset. Expert-drawn masks in that dataset taught the outlining step. Several encoder and decoder pairings were compared for accuracy. One design added a frequency-based feature booster to sharpen detail. Separate classifier models then labeled each image. The workflow aims to support radiologists with faster, more consistent reads. Both outlining and labeling run inside one pipeline.
Catalog record
| CREATOR | K. E. ArunKumar, Matthew E. Wilson, Nathan E. Blake, Tylor J. Yost, Matthew Walker |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |