Diagnostic performance of deep learning models on ultrasound images for distinguishing benign from malignant ovarian cysts
Weimei Li, Yuhua Xia, Yongzhao Li, Xing Wu, Lin Shi · 2026
Read Diagnostic performance of deep learning models on ultrasound images for distinguishing benign from malignant ovarian cysts by Weimei Li, Yuhua Xia, Yongzhao Li, Xing Wu, Lin Shi (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-13191837.txt.
Description
Li and co-authors compared deep learning models with human readers for telling benign from malignant ovarian cysts on ultrasound. Reading such scans depends heavily on operator experience, which introduces subjectivity and uneven accuracy. Their best model, a DenseNet121 network, beat senior physicians' accuracy by a wide margin. It also outperformed a standard risk classification system on overall discrimination.
Ultrasound images are noisy and complex, yet the model handled them well. The authors see strong potential for clinical adoption as decision support. Objective model reads could steady diagnoses where expert sonographers are scarce. Such support matters because the benign or malignant call steers surgery and follow-up.
Catalog record
| CREATOR | Weimei Li, Yuhua Xia, Yongzhao Li, Xing Wu, Lin Shi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |