Deep learning-based frame synthesis enables radiation dose reduction in digital subtraction angiography imaging: a multicenter study
Ruibo Liu, Ruixuan Zhang, Wei Qian, Guobiao Liang, Guangxin Chu, Yuwei Han, Xiaochuan Xu, Hai Jin, Ligang Chen, Jing Li, He Ma · 2026
Read Deep learning-based frame synthesis enables radiation dose reduction in digital subtraction angiography imaging: a multicenter study by Ruibo Liu, Ruixuan Zhang, Wei Qian, Guobiao Liang, Guangxin Chu, Yuwei Han, Xiaochuan Xu, Hai Jin, Ligang Chen, Jing Li, He Ma (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-13219322.txt.
Description
Ruibo Liu and ten co-authors present a deep learning system that could cut radiation during brain vessel imaging. Their 2026 study targets digital subtraction angiography, a scan method used to find and treat blood vessel disease in the brain. Each scan exposes patients and staff to radiation, so fewer frames would mean less risk.
Their model, SAVE-Net, creates in-between frames for a scan sequence, so fewer real scans are needed. It trained on over 17,000 sequences from one hospital and was tested on more from two others. Created frames scored close to real ones on image quality measures. Five specialists also rated the sequences and often could not tell the fake frames from real ones.
Catalog record
| CREATOR | Ruibo Liu, Ruixuan Zhang, Wei Qian, Guobiao Liang, Guangxin Chu, Yuwei Han, Xiaochuan Xu, Hai Jin, Ligang Chen, Jing Li, He Ma |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |