Purpose Deformable image registration (DIR) is a crucial technique in medical image analysis and is particularly important for 4D-CT–guided lung radiotherapy, where accurate spatiotemporal alignment and deformation plausibility are required for downstream tasks such as dose accumulation. However, many existing learning-based methods are limited in modeling global spatiotemporal dependencies and in preserving fine anatomical structures under large respiratory motion.    Methods To address these issues, this paper proposes a wavelet transform-based regularized hybrid recursive spatiotemporal fusion registration network (W-STFNet). The proposed method incorporates SwinLSTM to effectively capture global spatiotemporal dependencies. To achieve better semantic integration of features across scales and time steps, a multi-scale spatiotemporal attention fusion (MSTAF) module is proposed, which improves the network’s robustness and stability. Additionally, we design a novel frequency-domain loss function based on Discrete Wavelet Transform (DWT), which optimizes fine-grained structural matching by aligning high-frequency sub-bands, effectively improving the accuracy of high-frequency detail registration. The method is optimized in an unsupervised, patient-specific one-shot setting without anatomical annotations or multi-patient pretraining.    Results Experiments on two public 4D-CT datasets (DIR-Lab and POPI-model) show that W-STFNet achieves competitive registration accuracy and stable performance across cases with varying deformation amplitudes. On DIR-Lab, W-STFNet attains a mean TRE of     <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$1.13 \pm 0.72 \text {mm}$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>1.13</mn> <mo>±</mo> <mn>0.72</mn> <mtext>mm</mtext> </mrow> </math></EquationSource> </InlineEquation>, and on POPI-model a mean TRE of     <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$0.87 \pm 0.56 \text {mm}$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>0.87</mn> <mo>±</mo> <mn>0.56</mn> <mtext>mm</mtext> </mrow> </math></EquationSource> </InlineEquation>, substantially reducing the initial misalignment. A two-sided paired Wilcoxon signed-rank test further supports that W-STFNet differs significantly from several learning-based baselines under the reported settings, although the absolute differences should be interpreted with respect to image resolution and annotation uncertainty.    Conclusion W-STFNet provides an annotation-free, patient-specific one-shot registration framework that achieves robust and competitive performance for 4D-CT lung DIR, particularly in handling image registration scenarios involving large deformations and complex temporal dynamics.

W-STFNet: A Wavelet Transform-Based Regularized Hybrid Recursive Spatiotemporal Fusion Registration Network

期刊论文
发表日期：

2026年3月19日

查看全文

Xing Chen,
Xinyu Liu,
Zhijia Wang,
Ying Wei

摘要

Purpose

Deformable image registration (DIR) is a crucial technique in medical image analysis and is particularly important for 4D-CT–guided lung radiotherapy, where accurate spatiotemporal alignment and deformation plausibility are required for downstream tasks such as dose accumulation. However, many existing learning-based methods are limited in modeling global spatiotemporal dependencies and in preserving fine anatomical structures under large respiratory motion.

Methods

To address these issues, this paper proposes a wavelet transform-based regularized hybrid recursive spatiotemporal fusion registration network (W-STFNet). The proposed method incorporates SwinLSTM to effectively capture global spatiotemporal dependencies. To achieve better semantic integration of features across scales and time steps, a multi-scale spatiotemporal attention fusion (MSTAF) module is proposed, which improves the network’s robustness and stability. Additionally, we design a novel frequency-domain loss function based on Discrete Wavelet Transform (DWT), which optimizes fine-grained structural matching by aligning high-frequency sub-bands, effectively improving the accuracy of high-frequency detail registration. The method is optimized in an unsupervised, patient-specific one-shot setting without anatomical annotations or multi-patient pretraining.

Results

Experiments on two public 4D-CT datasets (DIR-Lab and POPI-model) show that W-STFNet achieves competitive registration accuracy and stable performance across cases with varying deformation amplitudes. On DIR-Lab, W-STFNet attains a mean TRE of $1.13 \pm 0.72 \text {mm}$ $1.13 \pm 0.72 mm$ , and on POPI-model a mean TRE of $0.87 \pm 0.56 \text {mm}$ $0.87 \pm 0.56 mm$ , substantially reducing the initial misalignment. A two-sided paired Wilcoxon signed-rank test further supports that W-STFNet differs significantly from several learning-based baselines under the reported settings, although the absolute differences should be interpreted with respect to image resolution and annotation uncertainty.

Conclusion

W-STFNet provides an annotation-free, patient-specific one-shot registration framework that achieves robust and competitive performance for 4D-CT lung DIR, particularly in handling image registration scenarios involving large deformations and complex temporal dynamics.