Sparse-View X-ray 3D Foot Reconstruction aims to reconstruct the three-dimensional structure of the foot from sparse-view X-ray images, a challenging task due to data sparsity and limited viewpoints.
Objective:
This paper presents a novel method using a multi-scale geometric Transformer to enhance reconstruction accuracy and detail representation.
Methods:
Geometric position encoding technology and a window mechanism are introduced to divide X-ray images into local areas, finely capturing local features. A multi-scale Transformer module based on Neural Radiance Fields (NeRF) enhances the model’s ability to express and capture details in complex structures. An adaptive weight learning strategy further optimizes the Transformer’s feature extraction and long-range dependency modelling.
Results:
Experimental results demonstrate that the proposed method significantly improves the reconstruction accuracy and detail preservation of the foot structure under sparse-view X-ray conditions. The multi-scale geometric Transformer effectively captures local and global features, leading to more accurate and detailed 3D reconstructions.
Conclusions:
The proposed method advances medical image reconstruction, significantly improving the accuracy and detail preservation of 3D foot reconstructions from sparse-view X-ray images.
LinYYangJWangH, et al. Cˆ 2rv: cross-regional and cross-view learning for sparse-view cbct reconstruction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp.11205–11214.
2.
XuKLuSHuangB, et al. Stage-by-stage wavelet optimization refinement diffusion model for sparse-view CT reconstruction. IEEE Trans Med Imaging2024; 1–1. DOI: 10.1109/TMI.2024.3355455.
3.
RiesADorostiTThalhammerJ, et al. Improving image quality of sparse-view lung tumor CT images with U-net. Eur Radio Exp2024; 8: 54.
4.
XiYZhouPYuH, et al. Adaptive-weighted high order TV algorithm for sparse-view CT reconstruction. Med Phys2023; 50: 5568–5584.
5.
EvangelistaDMorottiEPiccolominiEL. Rising: a new framework for model-based few-view CT image reconstruction with deep learning. Comput Med Imaging Graph2023; 103: 102156.
6.
LuSYangBXiaoY, et al. Iterative reconstruction of low-dose ct based on differential sparse. Biomed Signal Process Control2023; 79: 104204.
7.
WuQFengRWeiH, et al. Self-supervised coordinate projection network for sparse-view computed tomography. IEEE Trans Comput Imaging2023; 9: 517–529.
8.
ChengWHeJLiuY, et al. CAIR: combining integrated attention with iterative optimization learning for sparse-view ct reconstruction. Comput Biol Med2023; 163: 107161.
9.
LinYWangHChenJ, et al. Learning 3D gaussians for extremely sparse-view cone-beam CT reconstruction, arXiv preprint arXiv:2407.01090.
10.
MildenhallBSrinivasanPPTancikM, et al. NERF: representing scenes as neural radiance fields for view synthesis. Commun ACM2021; 65: 99–106.
11.
LiQLiRWangT, et al. A cascade-based dual-domain data correction network for sparse view CT image reconstruction. Comput Biol Med2023; 165: 107345.
12.
AyadILarueNNguyenMK. Qn-mixer: a quasi-newton mlp-mixer model for sparse-view CT reconstruction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp.25317–25326.
13.
GaoXSuTZhangY, et al. Attention-based dual-branch deep network for sparse-view computed tomography image reconstruction. Quant Imaging Med Surg2023; 13: 1360.
14.
LinJLiJDouJ, et al. DDENET: a dual-domain end-to-end network combining pale-transformer and laplacian convolution for sparse view CT reconstruction. Biomed Signal Process Control2024; 96: 106593.
15.
KimSAhnJKimB, et al. Convolutional neural network–based metal and streak artifacts reduction in dental ct images with sparse-view sampling scheme. Med Phys2022; 49: 6253–6277.
16.
HuangMLiGZhangJ, et al. Synchrotron radiation sparse-view CT artifact correction through deep learning neural networks. Nondestr Test Eval2024; 1–18.
17.
HongS-WKimS-YParkK, et al. Mechanical property evaluation of 3D multi-phase cement paste microstructures reconstructed using generative adversarial networks. Cem Concr Compos2024; 152: 105646.
18.
ZhangTLiuJWuF, et al. Artifact suppression for sparse view CT via transformer-based generative adversarial network. Biomed Signal Process Control2024; 95: 106297.
19.
ZhangCXieYLiangX. XGENRECON: a new perspective in ultra-sparse volumetric CBCT reconstruction through geometry-controlled x-ray projection generation. IEEE Trans Radi Plasma Med Sci2024; 1–1. DOI: 10.1109/TRPMS.2024.3420742.
20.
KangYLiuJWuF, et al. Deep convolutional dictionary learning network for sparse view CT reconstruction with a group sparse prior. Comput Methods Programs Biomed2024; 244: 108010.
21.
QinZMaYMaL, et al. Convolutional sparse coding for compressed sensing photoacoustic CT reconstruction with partially known support. Biomed Opt Express2024; 15: 524–539.
22.
ChengSChenQZhangQ, et al. SDCT-gan: reconstructing CT from biplanar x-rays with self-driven generative adversarial networks, arXiv preprint arXiv:2309.04960.
23.
WangYSunZ-LZengZ, et al. TRCT-gan: CT reconstruction from biplane x-rays using transformer and generative adversarial networks. Digit Signal Process2023; 140: 104123.
24.
XuYHanSWangD, et al. Hybrid u-net and swin-transformer network for limited-angle cardiac computed tomography. Phys Med Biol2024; 69: 105012.
25.
QiaoZLiuPFangC, et al. Directional TV algorithm for image reconstruction from sparse-view projections in epr imaging. Phys Med Biol2024; 69: 115051.
26.
AdisheshaASVanselowDJLa RiviereP, et al. Sinogram domain angular upsampling of sparse-view micro-ct with dense residual hierarchical transformer and attention-weighted loss. Comput Methods Programs Biomed2023; 242: 107802.
27.
ZhangCLiuLDaiJ, et al. XTRANSCT: ultra-fast volumetric CT reconstruction using two orthogonal x-ray projections for image-guided radiation therapy via a transformer network. Phys Med Biol2024; 69: 085010.
28.
LiZMaCChenJ, et al. Learning to distill global representation for sparse-view CT. In: Proceedings of the IEEE/CVF international conference on computer vision, 2023, pp.21196–21207.
29.
FuYLiuJShiJ. TSCA-net: transformer based spatial-channel attention segmentation network for medical images. Comput Biol Med2024; 170: 107938.
30.
LiYSunXWangS, et al. MDST: multi-domain sparse-view CT reconstruction based on convolution and swin transformer. Phys Med Biol2023; 68: 095019.
31.
LiuPFangCQiaoZ. A dense and u-shaped transformer with dual-domain multi-loss function for sparse-view CT reconstruction. J X-Ray Sci Technol (Preprint)2024; 32: 1–22.
32.
VoREscodaJVienneC, et al. Neural field regularization by denoising for 3D sparse-view x-ray computed tomography. In: 2024 International conference on 3D vision (3DV), 2024, pp.1166–1176. IEEE.
33.
SunMZhuYLiH, et al. ACNERF: enhancement of neural radiance field by alignment and correction of pose to reconstruct new views from a single x-ray. Phys Med Biol2024; 69: 045016.
34.
HatzellKZhengY. Ultra-sparse view x-ray computed tomography for 4-D imaging.
35.
CaiYWangJYuilleA, et al. Structure-aware sparse-view x-ray 3D reconstruction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, pp.11174–11183.
36.
ZhaRZhangYLiH. NAF: neural attenuation fields for sparse-view CBCT reconstruction. In: International conference on medical image computing and computer-assisted intervention, 2022, pp.442–452. Springer.
37.
ZangGIdoughiRLiR, et al. INTRATOMO: self-supervised learning-based tomography via sinogram synthesis and prediction. In: Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp.1960–1970.
38.
ChenAXuZGeigerA, et al. TENSORF: tensorial radiance fields. In: European conference on computer vision, 2022, pp.333–350. Springer.
