REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT
Reconstruction from a single 3D CBCT Acquisition
- URL: http://arxiv.org/abs/2208.08048v1
- Date: Wed, 17 Aug 2022 03:42:19 GMT
- Title: REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT
Reconstruction from a single 3D CBCT Acquisition
- Authors: Cheng Peng, Haofu Liao, S. Kevin Zhou, Rama Chellappa
- Abstract summary: 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.
- Score: 75.64791080418162
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: It is a long-standing challenge to reconstruct Cone Beam Computed Tomography
(CBCT) of the lung under respiratory motion. This work takes a step further to
address a challenging setting in reconstructing a multi-phase}4D lung image
from just a single}3D CBCT acquisition. To this end, we introduce
REpiratory-GAted Synthesis of views, or REGAS. REGAS proposes a self-supervised
method to synthesize the undersampled tomographic views and mitigate aliasing
artifacts in reconstructed images. This method allows a much better estimation
of between-phase Deformation Vector Fields (DVFs), which are used to enhance
reconstruction quality from direct observations without synthesis. 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. REGAS require no additional measurements
like prior scans, air-flow volume, or breathing velocity. Our extensive
experiments show that REGAS significantly outperforms comparable methods in
quantitative metrics and visual quality.
Related papers
- X-Recon: Learning-based Patient-specific High-Resolution CT Reconstruction from Orthogonal X-Ray Images [14.04604990570727]
X-Recon is a reconstruction network based on ortho-lateral chest X-ray images.
PTX-Seg is a zero-shot pneumothorax segmentation algorithm.
The reconstruction metrics achieved state-of-the-art performance in terms of several metrics including peak signal-to-noise ratio.
arXiv Detail & Related papers (2024-07-22T03:55:36Z) - 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) - RSTAR: Rotational Streak Artifact Reduction in 4D CBCT using Separable and Circular Convolutions [13.11070841951523]
We propose RSTAR-Net to encode dynamic image features, facilitating the recovery of 4D CBCT images.
We find that streak artifacts exhibit a periodic rotational motion along with the patient's respiration.
This unique pattern inspires us to distinguish the artifacts from the desired anatomical structures in the setemporal domain.
arXiv Detail & Related papers (2024-03-25T01:54:57Z) - Fast and accurate sparse-view CBCT reconstruction using meta-learned
neural attenuation field and hash-encoding regularization [13.01191568245715]
Cone beam computed tomography (CBCT) is an emerging medical imaging technique to visualize the internal anatomical structures of patients.
reducing the number of projections in a CBCT scan while preserving the quality of a reconstructed image is challenging.
We propose a fast and accurate sparse-view CBCT reconstruction (FACT) method to provide better reconstruction quality and faster optimization speed.
arXiv Detail & Related papers (2023-12-04T07:23:44Z) - Geometry-Aware Attenuation Field Learning for Sparse-View CBCT
Reconstruction [61.48254686722434]
Cone Beam Computed Tomography (CBCT) is the most widely used imaging method in dentistry.
sparse-view CBCT reconstruction has become a main focus to reduce radiation dose.
This paper proposes a novel attenuation field encoder-decoder framework by first encoding the volumetric feature from multi-view X-ray projections.
arXiv Detail & Related papers (2023-03-26T14:38:42Z) - LARO: Learned Acquisition and Reconstruction Optimization to accelerate
Quantitative Susceptibility Mapping [24.665782241561185]
Learned Acquisition and Reconstruction Optimization (LARO) aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for Quantitative susceptibility mapping (QSM)
Our approach involves optimizing a Cartesian multi-echo k-space sampling pattern with a deep reconstruction network.
Our ablation studies show that both the optimized sampling pattern and proposed reconstruction strategy help improve the quality of the multi-echo image reconstructions.
arXiv Detail & Related papers (2022-11-01T20:04:29Z) - Towards performant and reliable undersampled MR reconstruction via
diffusion model sampling [67.73698021297022]
DiffuseRecon is a novel diffusion model-based MR reconstruction method.
It guides the generation process based on the observed signals.
It does not require additional training on specific acceleration factors.
arXiv Detail & Related papers (2022-03-08T02:25:38Z) - ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer [60.27951773998535]
We propose a recurrent transformer model, namely textbfReconFormer, for MRI reconstruction.
It can iteratively reconstruct high fertility magnetic resonance images from highly under-sampled k-space data.
We show that it achieves significant improvements over the state-of-the-art methods with better parameter efficiency.
arXiv Detail & Related papers (2022-01-23T21:58:19Z) - Sparse-View CT Reconstruction using Recurrent Stacked Back Projection [3.91278924473622]
We introduce a direct-reconstruction method called Recurrent Stacked Back Projection (RSBP)
RSBP uses sequentially-acquired backprojections of individual views as input to a recurrent convolutional LSTM network.
We demonstrate that RSBP outperforms both post-processing of FBP images and basic MBIR, with a lower computational cost than MBIR.
arXiv Detail & Related papers (2021-12-09T15:44:35Z) - 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)
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.