Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT: From Simulated to Real Data

• URL: http://arxiv.org/abs/2512.21180v1
• Date: Wed, 24 Dec 2025 13:59:43 GMT
• Title: Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT: From Simulated to Real Data
• Authors: Nikita Moriakov, Efstratios Gavves, Jonathan H. Mason, Carmen Seller-Oria, Jonas Teuwen, Jan-Jakob Sonke,
• Abstract summary: LIRE++ is an end-to-end rotationally-equivariant multiscale learned invertible primal-dual scheme for fast and memory-efficient CBCT reconstruction.<n>LIRE++ was trained on simulated projection data from a fast quasi-Monte Carlo CBCT projection simulator.<n>On real clinical data, LIRE++ improved the average Mean Absolute Error between the reconstruction and the corresponding planning CT by 10 Hounsfield Units.
• Score: 28.21267815130768
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cone Beam CT (CBCT) is an important imaging modality nowadays, however lower image quality of CBCT compared to more conventional Computed Tomography (CT) remains a limiting factor in CBCT applications. Deep learning reconstruction methods are a promising alternative to classical analytical and iterative reconstruction methods, but applying such methods to CBCT is often difficult due to the lack of ground truth data, memory limitations and the need for fast inference at clinically-relevant resolutions. In this work we propose LIRE++, an end-to-end rotationally-equivariant multiscale learned invertible primal-dual scheme for fast and memory-efficient CBCT reconstruction. Memory optimizations and multiscale reconstruction allow for fast training and inference, while rotational equivariance improves parameter efficiency. LIRE++ was trained on simulated projection data from a fast quasi-Monte Carlo CBCT projection simulator that we developed as well. Evaluated on synthetic data, LIRE++ gave an average improvement of 1 dB in Peak Signal-to-Noise Ratio over alternative deep learning baselines. On real clinical data, LIRE++ improved the average Mean Absolute Error between the reconstruction and the corresponding planning CT by 10 Hounsfield Units with respect to current proprietary state-of-the-art hybrid deep-learning/iterative method.

Related papers

• Efficient Flow Matching for Sparse-View CT Reconstruction [7.05503627528473]
  Flow Matching (FM) models exhibit smooth trajectories without noise injection.<n>Motivated by this, we propose an FM-based CT reconstruction framework (FMCT)<n>We show that FMCT/EFMCT achieve competitive reconstruction quality while significantly improving computational efficiency compared with diffusion-based methods.
  arXiv  Detail & Related papers  (2026-02-27T11:13:43Z)
• 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)
• NeRF-based CBCT Reconstruction needs Normalization and Initialization [53.58395475423445]
  NeRF-based methods suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network.<n>We introduce a Normalized Hash, which enhances feature consistency and mitigates the mismatch.<n>The neural network exhibits improved stability during early training, enabling faster convergence and enhanced reconstruction performance.
  arXiv  Detail & Related papers  (2025-06-24T16:01:45Z)
• Continuous Filtered Backprojection by Learnable Interpolation Network [48.52134830162271]
  In this study, we propose a novel deep learning model, named Leanable-Interpolation-based FBP or LInFBP.<n>In the proposed LInFBP, we formulate every local piece of the latent continuous function of discrete sinogram data as a linear combination of selected basis functions.<n>Then, the learned latent continuous function is exploited for in backprojection step, which first time takes the advantage of deep learning for the in FBP.
  arXiv  Detail & Related papers  (2025-05-03T09:50:27Z)
• Fast Training of Recurrent Neural Networks with Stationary State Feedbacks [48.22082789438538]
  Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers.<n>We propose a novel method that replaces BPTT with a fixed gradient feedback mechanism.
  arXiv  Detail & Related papers  (2025-03-29T14:45:52Z)
• On the Foundation Model for Cardiac MRI Reconstruction [6.284878525302227]
  We propose a foundation model that uses adaptive unrolling, channel-shifting, and Pattern and Contrast-Prompt-UNet to tackle the problem. The PCP-UNet is equipped with an image contrast and sampling pattern prompt.
  arXiv  Detail & Related papers  (2024-11-15T18:15:56Z)
• AC-IND: Sparse CT reconstruction based on attenuation coefficient estimation and implicit neural distribution [12.503822675024054]
  Computed tomography (CT) reconstruction plays a crucial role in industrial nondestructive testing and medical diagnosis. Sparse view CT reconstruction aims to reconstruct high-quality CT images while only using a small number of projections. We introduce AC-IND, a self-supervised method based on Attenuation Coefficient Estimation and Implicit Neural Distribution.
  arXiv  Detail & Related papers  (2024-09-11T10:34:41Z)
• Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT [7.497397088625152]
  We propose LIRE+, a learned iterative scheme for fast and memory-efficient CBCT reconstruction. LIRE+ is a rotationally-equivariant multiscale learned invertible primal-dual iterative scheme for CBCT reconstruction. Our method surpasses classical and deep learning baselines, including LIRE, on the thorax test set.
  arXiv  Detail & Related papers  (2024-01-20T15:29:29Z)
• Enhancing Low-dose CT Image Reconstruction by Integrating Supervised and Unsupervised Learning [13.17680480211064]
  We propose a hybrid supervised-unsupervised learning framework for X-ray computed tomography (CT) image reconstruction. Each proposed trained block consists of a deterministic MBIR solver and a neural network. We demonstrate the efficacy of this learned hybrid model for low-dose CT image reconstruction with limited training data.
  arXiv  Detail & Related papers  (2023-11-19T20:23:59Z)
• Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction [53.93674177236367]
  Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. We introduce a novel geometry-aware encoder-decoder framework to solve this problem.
  arXiv  Detail & Related papers  (2023-03-26T14:38:42Z)
• REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT Reconstruction from a single 3D CBCT Acquisition [75.64791080418162]
  REGAS proposes a self-supervised method to synthesize the undersampled tomographic views and mitigate aliasing artifacts in reconstructed images. To address the large memory cost of deep neural networks on high resolution 4D data, REGAS introduces a novel Ray Path Transformation (RPT) that allows for distributed, differentiable forward projections.
  arXiv  Detail & Related papers  (2022-08-17T03:42:19Z)
• Reference-based Magnetic Resonance Image Reconstruction Using Texture Transforme [86.6394254676369]
  We propose a novel Texture Transformer Module (TTM) for accelerated MRI reconstruction. We formulate the under-sampled data and reference data as queries and keys in a transformer. The proposed TTM can be stacked on prior MRI reconstruction approaches to further improve their performance.
  arXiv  Detail & Related papers  (2021-11-18T03:06:25Z)
• Iterative Reconstruction for Low-Dose CT using Deep Gradient Priors of Generative Model [24.024765099719886]
  Iterative reconstruction is one of the most promising ways to compensate for the increased noise due to reduction of photon flux. In this work we integrate the data-consistency as a conditional term into the iterative generative model for low-dose CT. The distance between the reconstructed image and the manifold is minimized along with data fidelity during reconstruction.
  arXiv  Detail & Related papers  (2020-09-27T06:36:39Z)

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.