Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT
This work addresses the need for scalable and generalizable CT reconstruction, which is crucial for reducing radiation and scanning time in medical imaging, though it appears incremental as it builds on neural operator concepts for a specific domain.
The paper tackles the problem of sparse-view CT reconstruction, where deep learning methods often fail to generalize across different sampling rates and image resolutions, by proposing CTO, a neural operator framework that achieves consistent multi-sampling-rate and cross-resolution performance with over 4dB PSNR gain compared to CNNs and is 500 times faster than diffusion methods with a 3dB gain.
Sparse-view Computed Tomography (CT) reconstructs images from a limited number of X-ray projections to reduce radiation and scanning time, which makes reconstruction an ill-posed inverse problem. Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup, failing to generalize across sampling rates and image resolutions. For example, convolutional neural networks (CNNs) use the same learned kernels across resolutions, leading to artifacts when data resolution changes. We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space, enabling generalization (without retraining) across sampling rates and image resolutions. CTO operates jointly in the sinogram and image domains through rotation-equivariant Discrete-Continuous convolutions parametrized in the function space, making it inherently resolution- and sampling-agnostic. Empirically, CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs. Compared to state-of-the-art diffusion methods, CTO is 500$\times$ faster in inference time with on average 3dB gain. Empirical results also validate our design choices behind CTO's sinogram-space operator learning and rotation-equivariant convolution. Overall, CTO outperforms state-of-the-art baselines across sampling rates and resolutions, offering a scalable and generalizable solution that makes automated CT reconstruction more practical for deployment.