Time‐resolved PET imaging using a joint dynamic reconstruction and motion estimation framework (DREME‐PET)
Ruizhi Zuo, Hua‐Chieh Shao, Rameshwar Prasad, Jing Wang, You Zhang · 2026
Read Time‐resolved PET imaging using a joint dynamic reconstruction and motion estimation framework (DREME‐PET) by Ruizhi Zuo, Hua‐Chieh Shao, Rameshwar Prasad, Jing Wang, You Zhang (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/PMC13438130.txt.
Description
Zuo and colleagues present a method for filming the breathing motion of tumors during PET scanning in this 2026 imaging study. Positron emission tomography guides radiotherapy. But a tumor moves with each breath. Capturing that motion means reconstructing images from very short slices of data. Each slice holds as little as half a second, when counts are extremely sparse. Their framework, DREME-PET, reconstructs the moving sequence and learns a patient-specific motion model simultaneously.
The system represents a reference image with a neural network and maps it through a low-rank motion model whose scores come from a convolutional network reading the raw scan data. In a digital phantom simulation it tracked tumor centers to within about 1.7 millimeters on average, and a physical phantom test gave a contrast error near seven percent. After training, it predicted new frames in 28 milliseconds each.
Catalog record
| CREATOR | Ruizhi Zuo, Hua‐Chieh Shao, Rameshwar Prasad, Jing Wang, You Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 98 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |