Accelerated Optimization of Implicit Neural Representations for CT Reconstruction

Inspired by their success in solving challenging inverse prob-lems in computer vision, implicit neural representations (INRs) have been recently proposed for reconstruction in low-dose/sparse-view X-ray computed tomography (CT). An INR represents a CT image as a small-scale neural network that takes...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (International Symposium on Biomedical Imaging) S. 1 - 5
Hauptverfasser: Najaf, Mahrokh, Ongie, Gregory
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 14.04.2025
Schlagworte:
Computed tomography
Coor-dinate Based Neural Networks
CT Reconstruction
Fitting
Image reconstruction
Implicit Neural Representations
Iterative methods
Model-based Iterative Reconstruction
Neural networks
Optimization
Phantoms
Reconstruction algorithms
Training
X-ray imaging
ISSN:1945-8452
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Inspired by their success in solving challenging inverse prob-lems in computer vision, implicit neural representations (INRs) have been recently proposed for reconstruction in low-dose/sparse-view X-ray computed tomography (CT). An INR represents a CT image as a small-scale neural network that takes spatial coordinates as inputs and outputs attenuation values. Fitting an INR to sinogram data is similar to classical model-based iterative reconstruction methods. However, training INRs with losses and gradient-based algorithms can be prohibitively slow, taking many thousands of iterations to converge. This paper investigates strategies to accelerate the optimization of INRs for CT reconstruction. In particular, we propose two approaches: (1) using a modified loss function with improved conditioning, and (2) an algorithm based on the alternating direction method of multipliers. We illustrate that both of these approaches significantly accelerate INR-based reconstruction of a synthetic breast CT phantom in a sparse-view setting.
ISSN:1945-8452
DOI:10.1109/ISBI60581.2025.10981244