NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

Zha, Ruyi; Zhang, Yanhao; Li, Hongdong

doi:10.1007/978-3-031-16446-0_42

Cited by 38 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the medical field is primarily focused on exploring the potential of NERF technology in 3D reconstruction and has achieved some initial progress. When multiple reference projections (more than 50) are available, NAF (Zha et al 2022) restores 3D CT data by modifying the rendering technique of radiation fields. SNAF (Fang et al 2022) further enhances data quality and reduces the input of projections (requiring over 30) by utilizing a pre-trained denoising module.…”

Section: Nerf In Medicinementioning

confidence: 99%

ACnerf: enhancement of neural radiance field by alignment and correction of pose to reconstruct new views from a single x-ray*

Sun,

Zhu,

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective:Computed tomography (CT) is widely used in medical research and clinical diagnosis. However, acquiring CT data requires patients to be exposed to con siderable ionizing Radiance, leading to physical harm. Recent studies have considered using Neural Radiance Field(NERF) techniques to infer the full-view CT projections from single view X-ray projection, thus aiding physician judgment and reducing Radiance hazards. This paper enhances this technique in two directions:(1) Accurate generalization capabilities for control models. (2) Consider different ranges of viewpoints.Approach: Building upon Generative Radiance Fields (GRAF), we propose a method called ACnerf to enhance the generalization of the Neural Radiance Field through alignment and pose correction. ACnerf aligns with a reference single X-ray by utilizing a combination of positional encoding with Gaussian random noise (latent code) obtained from GRAF training. This approach avoids compromising the 3D structure caused by altering the generator. During inference, a pose judgment network is employed to correct the pose and optimize the rendered viewpoint. Additionally, when generating a narrow range of views, ACnerf employs frequency-domain regularization to fine-tune the generator and achieve precise projections.Main results: The proposed ACnerf method surpasses the state-of-the-art NERF technique in terms of rendering quality for knee and chest data with varying contrasts. It achieved an average improvement of 2.496 dB in PSNR and 41% in LPIPS for 0° to 360° projections. Additionally, for -15° to 15° projections, ACnerf achieved an average improvement of 0.691 dB in PSNR and 25.8% in LPIPS.Significance:With adjustments in alignment, inference, and rendering range, our experiments and evaluations on knee and chest data of different contrasts show that ACnerf effectively reduces artifacts and aberrations in the new view. ACnerf’s ability to recover more accurate 3D structures from single X-rays has excellent potential for reducing damage from ionising radiation in clinical diagnostics.

show abstract

Section: Nerf In Medicinementioning

confidence: 99%

ACnerf: enhancement of neural radiance field by alignment and correction of pose to reconstruct new views from a single x-ray*

Sun,

Zhu,

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…NeMAR is designed to generate a metal-artifact-reduced CT image by optimizing M θ . This optimization process involves updating weights using the acquired projections S (i.e., sinogram) with a differentiable forward projection layer FP as in the previous works [14,21]. However, a significant challenge arises when dealing with the metallic objects, as the sinogram values become unreliable when corresponding X-ray intersects with such high attenuation objects.…”

Section: Metal Trace-masked Lossmentioning

confidence: 99%

Neural attenuation fields for metal artifact reduction in dental CT

Lee,

Ahn,

Baek

2024

Medical Imaging 2024: Physics of Medical Imaging

View full text Add to dashboard Cite

Metal Artifact Reduction (MAR) is one of the notorious problems in dental CT imaging. The presence of metallic implants often introduces severe metal artifacts in the reconstructed CT images, which obstruct the visualization of dental structures. This highly ill-posed problem has been addressed with the rise of artificial intelligence in respect to deep learning. However, majority of the approaches rely on the supervision of large paired dataset, which is often infeasible in the clinical practice. In this work, we present NeMAR, a Neural fields-based Metal Artifact Reduction method for dental CT. NeMAR leverages coordinate-based neural representation along with two key components: the masked loss and the regularization loss. These elements synergistically empower the neural fields to generate metal-artifact-reduced CT image with high fidelity. Notably, NeMAR requires only the original metal-artifact-corrupted image as an input, thus eliminating the need for extensive paired data. The validation using simulated dental CT datasets demonstrates the effectiveness of NeMAR in accurately recovering the shape of dental structures. In essence, NeMAR presents a promising data-free approach to enhance dental CT imaging.

show abstract

“…Such a technique, using a prior anatomical model, can be affected by the imaging system/protocol mismatches between the prior and new acquisitions. Another study by Zha et al (2022) introduced a sparse-view CBCT reconstruction approach that parametrized an attenuation coefficient field using an INR. They augmented the INR with a learning-based position encoder to enhance the learning efficiency of fine anatomical structures.…”

Section: Related Workmentioning

confidence: 99%

Dynamic CBCT imaging using prior model-free spatiotemporal implicit neural representation (PMF-STINR)

Shao,

Mengke,

Pan

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Dynamic cone-beam computed tomography (CBCT) can capture high-spatial-resolution, time-varying images for motion monitoring, patient setup, and adaptive planning of radiotherapy. However, dynamic CBCT reconstruction is an extremely ill-posed spatiotemporal inverse problem, as each CBCT volume in the dynamic sequence is only captured by one or a few X-ray projections, due to the slow gantry rotation speed and the fast anatomical motion (e.g., breathing). Approach: We developed a machine learning-based technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), to reconstruct dynamic CBCTs from sequentially acquired X-ray projections. PMF-STINR employs a joint image reconstruction and registration approach to address the under-sampling challenge, enabling dynamic CBCT reconstruction from singular X-ray projections. Specifically, PMF-STINR uses spatial implicit neural representations to reconstruct a reference CBCT volume, and it applies temporal INR to represent the intra-scan dynamic motion with respect to the reference CBCT to yield dynamic CBCTs. PMF-STINR couples the temporal INR with a learning-based B-spline motion model to capture time-varying deformable motion during the reconstruction. Compared with the previous methods, the spatial INR, the temporal INR, and the B-spline model of PMF-STINR are all learned on the fly during reconstruction in a one-shot fashion, without using any patient-specific prior knowledge or motion sorting/binning. Main results: PMF-STINR was evaluated via digital phantom simulations, physical phantom measurements, and a multi-institutional patient dataset featuring various imaging protocols (half-fan/full-fan, full sampling/sparse sampling, different energy and mAs settings, etc.). The results showed that the one-shot learning-based PMF-STINR can accurately and robustly reconstruct dynamic CBCTs and capture highly irregular motion with high temporal (~0.1s) resolution and sub-millimeter accuracy.Significance: PMF-STINR can reconstruct dynamic CBCTs and solve the intra-scan motion problem from conventional 3D CBCT scans without using any prior anatomical/motion model or motion sorting/binning. It can be a promising tool for motion management by offering richer motion information than traditional 4D-CBCTs.

show abstract

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

Cited by 38 publications

References 23 publications

ACnerf: enhancement of neural radiance field by alignment and correction of pose to reconstruct new views from a single x-ray*

ACnerf: enhancement of neural radiance field by alignment and correction of pose to reconstruct new views from a single x-ray*

Neural attenuation fields for metal artifact reduction in dental CT

Dynamic CBCT imaging using prior model-free spatiotemporal implicit neural representation (PMF-STINR)

Contact Info

Product

Resources

About