Dynamic Chest Radiograph Simulation Technique with Deep Convolutional Neural Networks: A Proof-of-Concept Study
Dongrong Yang, Yuhua Huang, Bing Li, Jing Cai, Ge Ren, Michał Strzelecki, Adam Piórkowski, Rafał Obuchowicz · 2023
Read Dynamic Chest Radiograph Simulation Technique with Deep Convolutional Neural Networks: A Proof-of-Concept Study by Dongrong Yang, Yuhua Huang, Bing Li, Jing Cai, Ge Ren, Michał Strzelecki, Adam Piórkowski, Rafał Obuchowicz (2023) 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-10741831.txt.
Description
A research team teaches a neural network to predict breathing motion from a single chest X-ray, in a 2023 proof-of-concept study. Knowing how a patient's lungs move helps spot disease early and plan treatment, but motion usually needs repeated imaging. Their network pairs a U-Net with a memory module and warps the input image with a spatial transformer to simulate the cycle.
The simulated motion matched lung mechanics well and even sharpened disease details. Overlap scores against real motion topped 0.96 across breathing phases, and predicted lung lengths stayed within about five millimeters of measured values. The authors present patient-specific motion profiles from one static image as a realistic aid for early lung cancer work.
Catalog record
| CREATOR | Dongrong Yang, Yuhua Huang, Bing Li, Jing Cai, Ge Ren, Michał Strzelecki, Adam Piórkowski, Rafał Obuchowicz |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |