Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays

• URL: http://arxiv.org/abs/2603.26509v1
• Date: Fri, 27 Mar 2026 15:21:47 GMT
• Title: Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays
• Abstract summary: AXON is a framework that reconstructs high-fidelity 3D CT volumes directly from real X-rays.<n>A super-resolution network is integrated to upscale the generated volumes to achieve diagnostic-grade resolution.
• Score: 12.064203765676817
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Computed tomography (CT) provides rich 3D anatomical details but is often constrained by high radiation exposure, substantial costs, and limited availability. While standard chest X-rays are cost-effective and widely accessible, they only provide 2D projections with limited pathological information. Reconstructing 3D CT volumes from 2D X-rays offers a transformative solution to increase diagnostic accessibility, yet existing methods predominantly rely on synthetic X-ray projections, limiting clinical generalization. In this work, we propose AXON, a multi-stage diffusion-based framework that reconstructs high-fidelity 3D CT volumes directly from real X-rays. AXON employs a coarse-to-fine strategy, with a Brownian Bridge diffusion model-based initial stage for global structural synthesis, followed by a ControlNet-based refinement stage for local intensity optimization. It also supports bi-planar X-ray input to mitigate depth ambiguities inherent in 2D-to-3D reconstruction. A super-resolution network is integrated to upscale the generated volumes to achieve diagnostic-grade resolution. Evaluations on both public and external datasets demonstrate that AXON significantly outperforms state-of-the-art baselines, achieving a 11.9% improvement in PSNR and a 11.0% increase in SSIM with robust generalizability across disparate clinical distributions. Our code is available at https://github.com/ai-med/AXON.

Related papers

• X-ray Insights Unleashed: Pioneering the Enhancement of Multi-Label Long-Tail Data [86.52299247918637]
  Long-tailed pulmonary anomalies in chest radiography present formidable diagnostic challenges.<n>Despite the recent strides in diffusion-based methods for enhancing the representation of tailed lesions, the paucity of rare lesion exemplars curtails the generative capabilities of these approaches.<n>We propose a novel data synthesis pipeline designed to augment tail lesions utilizing a copious supply of conventional normal X-rays.
  arXiv  Detail & Related papers  (2025-12-24T06:14:55Z)
• Zero-shot Volumetric CT Super-Resolution using 3D Gaussian Splatting with Upsampled 2D X-ray Projection Priors [3.3659467814492654]
  We propose a novel zero-shot 3D CT SR framework that leverages upsampled 2D X-ray projection priors generated by a diffusion model.<n>Experiments on two datasets show that our method achieves superior quantitative and qualitative results for 3D CT SR.
  arXiv  Detail & Related papers  (2025-08-21T01:24:06Z)
• Latent Space Consistency for Sparse-View CT Reconstruction [10.057432803124167]
  Latent Diffusion Model (LDM) has demonstrated promising potential in the domain of 3D CT reconstruction.<n>Cross-modal feature contrastive learning is used to efficiently extract latent 3D information from 2D Xray images.<n>Results indicate that CLS-DM outperforms classical and state-of-the-art generative models in terms of standard voxel-level metrics.
  arXiv  Detail & Related papers  (2025-07-15T10:02:19Z)
• X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography [89.84588038174721]
  Computed Tomography serves as an indispensable tool in clinical, providing non-invasive visualization of internal anatomical structures.<n>Existing CT reconstruction works are limited to small-capacity model architecture and inflexible volume representation.<n>We present X-GRM, a large feedforward model for reconstructing 3D CT volumes from sparse-view 2D X-ray projections.
  arXiv  Detail & Related papers  (2025-05-21T08:14:10Z)
• X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction [25.13707706037451]
  X-ray imaging is indispensable in medical diagnostics, yet its use is tightly regulated due to potential health risks.<n>Recent research focuses on generating novel views from sparse inputs and reconstructing Computed Tomography (CT) volumes.<n>We introduce X-Field, the first 3D representation specifically designed for X-ray imaging.
  arXiv  Detail & Related papers  (2025-03-11T16:31:56Z)
• X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Second [52.11676689269379]
  Sparse-view 3D CT reconstruction aims to recover structures from a limited number of 2D X-ray projections.<n>Existing feedforward methods are constrained by the limited capacity of CNN-based architectures and the scarcity of large-scale training datasets.<n>We propose an X-ray Large Reconstruction Model (X-LRM) for extremely sparse-view (10 views) CT reconstruction.
  arXiv  Detail & Related papers  (2025-03-09T01:39:59Z)
• DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rays [41.393567374399524]
  We propose DiffuX2CT, which models CT reconstruction from ultra-sparse X-rays as a conditional diffusion process. By doing so, DiffuX2CT achieves structure-controllable reconstruction, which enables 3D structural information to be recovered from 2D X-rays. As an extra contribution, we collect a real-world lumbar CT dataset, called LumbarV, as a new benchmark to verify the clinical significance and performance of CT reconstruction from X-rays.
  arXiv  Detail & Related papers  (2024-07-18T14:20:04Z)
• X-ray2CTPA: Leveraging Diffusion Models to Enhance Pulmonary Embolism Classification [24.233484690096898]
  Chest X-rays or chest radiography (CXR) enables limited imaging compared to computed tomography (CT) scans.<n>CT scans entail higher costs, greater radiation exposure, and are less accessible than CXRs.<n>In this work we explore cross-modal translation from a 2D low contrast-resolution X-ray input to a 3D high contrast and spatial-resolutionA scan.
  arXiv  Detail & Related papers  (2024-06-23T13:53:35Z)
• R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
  3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction. This paper introduces R2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
  arXiv  Detail & Related papers  (2024-05-31T08:39:02Z)
• A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning [56.52933974838905]
  Current medical workflow requires manual delineation of organs-at-risk (OAR) In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation. Our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging.
  arXiv  Detail & Related papers  (2022-03-01T17:08:41Z)
• Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices [48.85784310158493]
  We propose a Modified Pseudo-3D Feature Pyramid Network (MP3D FPN) to efficiently extract 3D context enhanced 2D features for universal lesion detection in CT slices. With the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset. The proposed 3D pre-trained weights can potentially be used to boost the performance of other 3D medical image analysis tasks.
  arXiv  Detail & Related papers  (2020-12-16T07:11:16Z)

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.