An unsupervised physics-informed neural network for dual-energy CT material decomposition achieves lower projection RMSE and better VMI quality than conventional methods on the AAPM dataset by enforcing consistency with a polychromatic forward model.
Dual- and multi-energy CT: principles, technical approaches, and clinical applications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.med-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised Physics-Informed Deep Learning for Dual-Energy CT Material Decomposition
An unsupervised physics-informed neural network for dual-energy CT material decomposition achieves lower projection RMSE and better VMI quality than conventional methods on the AAPM dataset by enforcing consistency with a polychromatic forward model.