SONAR: A Structure-Consistent Neural Operator for Null-Space-Aware Sparse View CT Reconstruction

• URL: http://arxiv.org/abs/2609.13688v1
• Date: Sat, 12 Sep 2026 03:46:54 GMT
• Title: SONAR: A Structure-Consistent Neural Operator for Null-Space-Aware Sparse View CT Reconstruction
• Abstract summary: We propose SONAR, a structure-consistent Neural Operator for Null-Space-Aware Reconstruction.<n>It separates measurement and pseudo-measurement residuals, lifts them into the image domain through physics operators, and applies independent neural operators to constrain their structural effects.<n> Experiments on simulated AAPM and clinical MARS photon-counting CT data demonstrate consistent improvements across seen and unseen view settings and unseen image resolutions.
• Score: 5.1854427179061675
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse-view computed tomography (CT) reduces radiation dose and acquisition time but remains severely ill-posed because incomplete projections poorly constrain null-space information. Existing learning-based methods often estimate this information in high-dimensional image space, conflate physical measurement errors with prediction errors, and depend on fixed discretizations. We propose SONAR, a Structure-Consistent Neural Operator for Null-Space-Aware Reconstruction. Instead of recovering the full null-space component, SONAR predicts a low-dimensional null-space-aware representation from the acquired projections as pseudo-measurements. It separates measurement and pseudo-measurement residuals, lifts them into the image domain through physics operators, and applies independent neural operators to constrain their structural effects, thereby accommodating admissible errors while suppressing unsupported structures. To support cross-discretization reconstruction, an anisotropic U-shaped neural operator models the periodic angular and nonperiodic detector dimensions using direction-dependent continuous supports, while image-domain neural operators re-discretize continuous kernels on target grids. These components form an optimization-inspired unrolled network. Experiments on simulated AAPM and clinical MARS photon-counting CT data demonstrate consistent improvements across seen and unseen view settings and unseen image resolutions. On AAPM dataset, SONAR improves PSNR by 1.87~dB at 62 views and by 7.63~dB under zero-shot transfer to a $512\times512$ grid over the strongest competing methods. SONAR also achieves the best overall performance in all clinical settings evaluated, demonstrating accurate, structurally reliable, and discretization-robust sparse-view CT reconstruction.

Related papers

• Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models [71.59431204970339]
  STORM is a spatial-aware token reduction framework.<n>It reformulates reduction into a structured operation on spatial units.<n>It achieves state-of-the-art pruning accuracy across diverse vision Mamba backbones.
  arXiv  Detail & Related papers  (2026-06-18T08:31:11Z)
• DenOiS: Dual-Domain Denoising of Observation and Solution in Ultrasound Image Reconstruction [1.711666249985278]
  Medical imaging aims to recover underlying tissue properties, using infidelity (simplified/linearized) imaging models and often from inaccurate and incomplete measurements.<n> Analytical reconstruction methods rely on hand-crafted regularization, sensitive to noise assumptions and parameter tuning domains.<n>We propose DeniS, a framework that denoise improves both input observations and imaging model accuracy.<n>We demonstrate this for speed-of-sound imaging as a challenging setting for quantitative ultrasound image reconstruction.
  arXiv  Detail & Related papers  (2026-04-02T14:35:43Z)
• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT [67.14700058302016]
  Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup.<n>We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space.<n>CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs.
  arXiv  Detail & Related papers  (2025-12-13T08:31:46Z)
• Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary CT Reconstruction: NAF Meets Diffusion Model [20.480681036392173]
  Multi-source stationary computed tomography (CT) has recently attracted attention for its ability to achieve rapid image reconstruction.<n>This study proposes Diffusion-Refined Neural Attenuation Fields (Diff-NAF), an iterative framework tailored for multi-source stationary CT under ultra-sparse-view conditions.
  arXiv  Detail & Related papers  (2025-11-18T10:14:28Z)
• NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems [25.35772762396095]
  Non-linear Projections of the Null-Space (NPN) is a novel class of regularization.<n>NPN promotes solutions that lie in a low-dimensional projection of the sensing matrix's null-space with a neural network.<n>We provide theoretical guarantees on convergence and reconstruction accuracy when used within plug-and-play methods.
  arXiv  Detail & Related papers  (2025-10-02T02:45:06Z)
• Accelerating 3D Photoacoustic Computed Tomography with End-to-End Physics-Aware Neural Operators [74.65171736966131]
  Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit.<n>Current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation.<n>We introduce Pano, an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions.
  arXiv  Detail & Related papers  (2025-09-11T23:12:55Z)
• Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction [8.291709892315993]
  We introduce Self-prior embedding neural representation (Spener) for sparse-view computed tomography (SVCT) inverse problems.<n>During each iteration, Spener extracts local image prior features from the previous iteration and embeds them to constrain the solution space.<n> Experimental results on multiple CT datasets show that our unsupervised Spener method achieves performance comparable to supervised state-of-the-art (SOTA) methods on in-domain data.
  arXiv  Detail & Related papers  (2025-02-08T04:36:00Z)
• Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction [48.30341580103962]
  We propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues.<n>We design a deep unfolding network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction.<n> Experiments conducted on the fastMRI and IXI datasets demonstrate that our method significantly outperforms state-of-the-art approaches in terms of reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-07T12:29:32Z)
• CoCPF: Coordinate-based Continuous Projection Field for Ill-Posed Inverse Problem in Imaging [78.734927709231]
  Sparse-view computed tomography (SVCT) reconstruction aims to acquire CT images based on sparsely-sampled measurements. Due to ill-posedness, implicit neural representation (INR) techniques may leave considerable holes'' (i.e., unmodeled spaces) in their fields, leading to sub-optimal results. We propose the Coordinate-based Continuous Projection Field (CoCPF), which aims to build hole-free representation fields for SVCT reconstruction.
  arXiv  Detail & Related papers  (2024-06-21T08:38:30Z)
• DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction [45.00528216648563]
  Diffusion Prior Driven Neural Representation (DPER) is an unsupervised framework designed to address the exceptionally ill-posed CT reconstruction inverse problems. DPER adopts the Half Quadratic Splitting (HQS) algorithm to decompose the inverse problem into data fidelity and distribution prior sub-problems. We conduct comprehensive experiments to evaluate the performance of DPER on LACT and ultra-SVCT reconstruction with two public datasets.
  arXiv  Detail & Related papers  (2024-04-27T12:55:13Z)
• Low-Dose CT Denoising Using a Structure-Preserving Kernel Prediction Network [10.09577595969254]
  CNN-based approaches treat all regions of the CT image equally and can be inefficient when fine-grained structures coexist with non-uniformly distributed noises. We propose a Structure-preserving Kernel Prediction Network (StructKPN) that combines the kernel prediction network with a structure-aware loss function. Our approach achieved superior performance on both synthetic and non-synthetic datasets, and better preserves structures that are highly desired in clinical screening and low-dose protocol optimization.
  arXiv  Detail & Related papers  (2021-05-31T07:42:21Z)
• Appearance Learning for Image-based Motion Estimation in Tomography [60.980769164955454]
  In tomographic imaging, anatomical structures are reconstructed by applying a pseudo-inverse forward model to acquired signals. Patient motion corrupts the geometry alignment in the reconstruction process resulting in motion artifacts. We propose an appearance learning approach recognizing the structures of rigid motion independently from the scanned object.
  arXiv  Detail & Related papers  (2020-06-18T09:49:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.