Image quality improvement of liver ultrasound using unsupervised deep learning
Jaeyoung Huh, Joo Hyeok Choi, Eun Sun Lee, Jong Chul Ye, Jeong Eun Lee, Hyun Jeong Park, Byung Ihn Choi · 2026
Read Image quality improvement of liver ultrasound using unsupervised deep learning by Jaeyoung Huh, Joo Hyeok Choi, Eun Sun Lee, Jong Chul Ye, Jeong Eun Lee, Hyun Jeong Park, Byung Ihn Choi (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/plos-pone-0348137.txt.
Description
Jaeyoung Huh and colleagues teach an artificial intelligence system to upgrade liver ultrasound images from old machines, in this 2026 PLOS ONE imaging paper. Ultrasound is the first test for liver disease worldwide, but aging scanners produce murky pictures that can hide tumors and mislead diagnosis.
Their network learned without paired examples, using images from a twelve-year-old device as input and from a four-year-old device as the quality target, translating between the two styles. Two experienced reviewers judged the enhanced images better. If the gains hold in clinic, hospitals could stretch the useful life of older scanners, a real concern where new equipment budgets are thin.
Catalog record
| CREATOR | Jaeyoung Huh, Joo Hyeok Choi, Eun Sun Lee, Jong Chul Ye, Jeong Eun Lee, Hyun Jeong Park, Byung Ihn Choi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51506 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |