Dual-Domain Sparse-View 4D CBCT Reconstruction with Spatial-Temporal Consistency Learning

Qi Lai; YuTong He

cs.CVOct 13, 2026

Dual-Domain Sparse-View 4D CBCT Reconstruction with Spatial-Temporal Consistency Learning

Authors: Qi Lai, YuTong He

Abstract

Four-dimensional cone-beam computed tomography (4D CBCT) provides phase-resolved volumetric images for image-guided radiotherapy. Yet good reconstruction quality usually needs many projections. This increases scan time and radiation dose. We propose STCNet, a sparse-view 4D CBCT reconstruction framework that uses spatial-temporal consistency learning. STCNet reconstructs high-quality images from only 16 projections in each respiratory phase. STCNet integrates physics-driven positional encoding to enforce geometric consistency in the projection domain and introduces temporal encoding in latent space to capture respiratory motion dynamics across phases to capture dynamic respiratory motion across phases. A dual-domain collaborative strategy jointly optimizes both projection and image domains, enhancing structural fidelity and temporal coherence. We tested STCNet on the TCIA-LUNG dataset and a CIRS thorax phantom dataset. STCNet performed better than conventional methods and recent deep learning baselines in image quality, artifact reduction, and structural preservation. On TCIA-LUNG, STCNet reached PSNR values of 33.311, 32.695, and 32.658 dB at phases 2, 5, and 8. The corresponding SSIM values were 0.845, 0.823, and 0.825. On CIRS, STCNet achieved PSNR values up to 36.497 dB and SSIM values up to 0.877. These results support STCNet as a promising framework for low-dose, phase-resolved 4D CBCT reconstruction in image-guided radiotherapy.

Figures & tables

Figure 1: Overview of the proposed STCNet framework for dual-domain sparse-view 4D CBCT reconstruction with spatial-temporal consistency learning. Sparse-view projections are sorted into $P=10$ respiratory phases, with $N=16$ projections per phase. The projection-domain generation module (PDGM) incorporates physics-aware positional encoding of acquisition angles and LSTM-based temporal consistency encoding to generate $K=256$ dense-view projections per phase. FDK reconstruction converts the generated projections into initial phase-resolved volumes, which are subsequently refined by the image-domain correction module (IDCM) to produce the final 4D CBCT sequence.

Parameter	TCIA-LUNG Roman et al. (2012) ; Balik et al. (2013) ; Clark et al. (2013) ; Hugo et al. (2016)	CIRS phantom
DSD/DSO (mm)	1500/1000	1800/1000
Pixel size (mm 2 )	0.95 $\times$ 0.95	0.95 $\times$ 0.95
Detector size	1024 $\times$ 1024	1024 $\times$ 1024
Angle range	0 ∘ –360 ∘	0 ∘ –360 ∘
Voxel size (mm 3 )	0.98 $\times$ 0.98 $\times$ 1	0.98 $\times$ 0.98 $\times$ 1
Dimension	512 $\times$ 512 $\times$ N z	512 $\times$ 512 $\times$ N z

Table 1: Acquisition parameters for the TCIA-LUNG and CIRS phantom datasets

Methods	CIRS Phantom
	Phase2			Phase5			Phase8
	MAE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	MAE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	MAE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$
FDK Feldkamp et al. (1984)	0.196	22.316	0.324	0.194	22.289	0.349	0.189	22.326	0.335
SART Andersen and Kak (1984)	0.129	25.893	0.349	0.123	25.719	0.346	0.124	25.892	0.349
SART-TV Mascolo-Fortin et al. (2018)	0.113	26.735	0.457	0.117	26.741	0.461	0.121	26.658	0.449
N-Net Zhi et al. (2021)	0.071	20.322	0.506	0.071	20.313	0.505	0.072	20.126	0.499

Table 2: Quantitative comparison of reconstruction performance on axial slices from the CIRS Phantom and TCIA-LUNG datasets.

Figure 2: Quantitative comparison across planes and phases: The figure shows PSNR and SSIM results for representative phases in coronal and sagittal views. Panel (a) shows TCIA-LUNG coronal results. Panel (b) shows TCIA-LUNG sagittal results. Panel (c) shows CIRS coronal results. Panel (d) shows CIRS sagittal results.

Figure 3: Reconstruction results on the CIRS phantom dataset: The figure shows coronal, sagittal, and axial slices at phases 2, 5, and 8 for different methods. The red and yellow dashed lines mark tumor marker boundary positions across phases.

Figure 4: Reconstruction results on the TCIA-LUNG dataset: The figure shows coronal, sagittal, and axial slices at phases 2, 5, and 8 for different methods. The red and yellow dashed lines mark the highest and lowest diaphragm positions and show the motion path across phases.

Figure 5: HU difference maps on the TCIA-LUNG dataset: The maps show axial, coronal, and sagittal differences between reconstructed images and ground truth. Red and blue represent positive and negative HU errors.

Baseline	PDGM	IDCM	MAE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$
$\surd$			0.162	23.916	0.382
$\surd$	$\surd$		0.059	30.352	0.747
$\surd$		$\surd$	0.162	22.360	0.695
$\surd$	$\surd$	$\surd$	0.036	32.536	0.824

Table 3: Ablation study of PDGM and IDCM on the TCIA-LUNG dataset

Baseline	PDGM	IDCM	MAE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$
$\surd$			0.102	24.916	0.332
$\surd$	$\surd$		0.064	31.134	0.783
$\surd$		$\surd$	0.162	29.697	0.695
$\surd$	$\surd$	$\surd$	0.018	36.543	0.878

Table 4: Ablation study of PDGM and IDCM on the CIRS phantom dataset

Figure 6: Ablation study of STCNet: The figure shows phase-wise PSNR and SSIM results for the baseline, baseline + PDGM, baseline + IDCM, and STCNet. Panels (a) and (b) show TCIA-LUNG results. Panels (c) and (d) show CIRS results.

Figure 7: Overview of the STCNet framework: The workflow starts with sparse-view projections sorted by respiratory phase. The PDGM uses a Swin-UNet backbone with positional and temporal encoding to generate dense-view projections. The method then applies FDK reconstruction. The IDCM refines the reconstructed volumes and outputs final phase-resolved 4D CBCT images.

Explore similar work

Dual-domain U-Nets with embedded back projection operators for motion-resolved 4D CBCT reconstruction
Aug 4, 2026Ivo Herzig, Pascal Paysan, Daniel Barco +8Cone-Beam CT 4D Reconstruction
Zurich University of Applied Sciences ZHAW, Institute for Applied Mathematics and Physics IAMP, Winterthur, Switzerland · Varian Medical Systems Imaging Laboratory GmbH, Baden-Dättwil, Switzerland · Zurich University of Applied Sciences ZHAW, Centre for Artificial Intelligence CAI, Winterthur, Switzerland +1
SONAR: A Structure-Consistent Neural Operator for Null-Space-Aware Sparse View CT Reconstruction
Sep 12, 2026Song Ni, Haijun Yu, Haodong Li +4Sparse-View CT Reconstruction Image Inverse Problems
Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, MA 01854
RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstruction
Oct 8, 2026Mengrui Yin, Tianxingjian Ding, Wufan Zhao +2Image Reconstruction Sparse-View CT Reconstruction
University of Central Florida · The Hong Kong University of Science and Technology (Guangzhou) · Tampere University +1

Aug 4, 2026J/K move · Enter open · S save

Dual-domain U-Nets with embedded back projection operators for motion-resolved 4D CBCT reconstruction

Ivo Herzig, Pascal Paysan, Daniel Barco, Marc André Stadelmann+7

Zurich University of Applied Sciences ZHAW, Institute for Applied Mathematics and Physics IAMP, Winterthur, Switzerland · Varian Medical Systems Imaging Laboratory GmbH, Baden-Dättwil, Switzerland · Zurich University of Applied Sciences ZHAW, Centre for Artificial Intelligence CAI, Winterthur, Switzerland+1

Cone-Beam CT 4D Reconstruction U-Net

Open paper AskPDF arXiv

Four-dimensional cone beam CT (4D CBCT) is important for image-guided radiation therapy of thoracic cancers, but its use is limited by long scan times, causing high patient dose and motion/sparse-sampling artifacts. We propose a deep learning method for motion-resolved 4D CBCT reconstruction from conventional free-breathing scans, without a respiratory signal or explicit projection binning. Our CNN takes free-breathing 3D CBCT projections as input and predicts a static volume at maximum inhalation plus ten displacement vector fields (DVFs) spanning a breathing cycle. The network extends U-Net: the encoder acts on filtered projection stacks, the decoder acts in the volume domain, and skip connections are replaced with non-trainable back-projection functions at multiple resolutions to transfer features between domains. The model is trained on simulated CBCT scans and evaluated on 11 unseen simulated patients and 13 clinical free-breathing scans. Two additional models (60 s and 6 s scans) were evaluated by clinical experts on three and two scans, comparing single phases of our 4D reconstruction to reference 3D SART-TV images for tumor and esophagus visibility. Experts preferred our method for tumor visibility (59% vs. 36% no preference, 5% reference) and esophagus visibility (47% vs. 42%, 11%). On simulated data, image quality matched SART-TV (mean RMSE: -1.19 HU, PSNR: +0.09 dB, SSIM: -0.009) while enabling 4D reconstruction. On clinical scans, our method showed sharper dynamic structures (e.g., diaphragm) and fewer motion streak artifacts than traditional reconstruction. This non-patient-specific CNN predicts static volumes and full 4D respiratory motion models from a single free-breathing scan, without a respiratory surrogate or projection binning, reducing motion artifacts while adding motion-modeling capability.

Abstract

Explore similar work

Dual-domain U-Nets with embedded back projection operators for motion-resolved 4D CBCT reconstruction

SONAR: A Structure-Consistent Neural Operator for Null-Space-Aware Sparse View CT Reconstruction

RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstruction