Sparse-view Cone Beam CT Reconstruction using Data-consistent Supervised and Adversarial Learning from Scarce Training Data

TL;DR

This paper introduces a novel deep learning-based method for sparse-view cone beam CT reconstruction that performs well even with extremely limited projections and training data, using a staged approach with data consistency and adversarial training.

Contribution

It proposes a data-efficient, staged deep learning framework combining adversarial destreaking and data consistency for 3D CT reconstruction with scarce data and projections.

Findings

Outperforms traditional methods in limited-data scenarios

Effective with extremely few projections and training samples

Uses a hybrid 3D-to-2D network for efficient learning

Abstract

Reconstruction of CT images from a limited set of projections through an object is important in several applications ranging from medical imaging to industrial settings. As the number of available projections decreases, traditional reconstruction techniques such as the FDK algorithm and model-based iterative reconstruction methods perform poorly. Recently, data-driven methods such as deep learning-based reconstruction have garnered a lot of attention in applications because they yield better performance when enough training data is available. However, even these methods have their limitations when there is a scarcity of available training data. This work focuses on image reconstruction in such settings, i.e., when both the number of available CT projections and the training data is extremely limited. We adopt a sequential reconstruction approach over several stages using an adversarially trained shallow network for 'destreaking' followed by a data-consistency update in each stage. To deal with the challenge of limited data, we use image subvolumes to train our method, and patch aggregation during testing. To deal with the computational challenge of learning on 3D datasets for 3D reconstruction, we use a hybrid 3D-to-2D mapping network for the 'destreaking' part. Comparisons to other methods over several test examples indicate that the proposed method has much potential, when both the number of projections and available training data are highly limited.