2022
DOI: 10.1007/978-3-031-16446-0_42
|View full text |Cite
|
Sign up to set email alerts
|

NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction

Abstract: This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction (Cone Beam Computed Tomography) that requires no external training data. Specifically, the desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. We synthesize projections discretely and train the network by minimizing the error between real and synthesized projections. A learning-based encoder entailing hash codi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
4
1

Relationship

0
10

Authors

Journals

citations
Cited by 38 publications
(8 citation statements)
references
References 23 publications
0
8
0
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%
“…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%
“…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%
“…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%