An unsupervised anatomy-aware dual-constraint cascade network for lung computed tomography deformable image registration

Deformable image registration (DIR) of lung computed tomography (CT) facilitates precise radiotherapy for lung cancer by aligning images from different respiratory states or time points. Due to the high resolution of lung CT image data , the large amplitude of lung motion, and significant differences in image intensity, achieving fast and accurate DIR of lung CT is challenging. In this study, we propose an unsupervised Anatomy-aware Dual-constraint Cascade network, called ADC-Net. We construct an efficient single-level network based on fully convolutional networks, into which a tri-directional deformation capture (TDC) block is designed and integrated. The TDC block calculates voxel correlations along three spatial dimensions separately, comprehensively capturing deformations in different directions, particularly large deformations along the lung's vertical axis. To further enhance the awareness of large deformations as well as internal anatomical details, we propose a dual-constraint cascade mode. In this mode, contour-enhanced and vessel-enhanced images used as constraints, along with the original images, are fed into three single-level networks, which enables accurate registration of large deformations while maintaining precise alignment of internal details. Compared to the state-of-the-art cascade method, MANet, ADC-Net achieves a registration accuracy improvement of 3 % and 4 % on the Dir-lab and ThoraxCBCT datasets, respectively, with a notable accuracy increase of 16 % for images with large deformations. Additionally, the low-computational-cost upsampling structure adopted by the single-level network ensures efficiency and makes ADC-Net 21 % faster than MANet. ADC-Net's high accuracy, rapid processing speed, and robust applicability in DIR of lung CT suggest its potential value for clinical engineering applications . We propose an unsupervised Anatomy-aware Dual-constraint Cascade network, called ADC-Net. Compared to state-of-the-art methods, it achieved the best performance on both the Dir-lab and ThoraxCBCT datasets. The high accuracy, rapid processing speed, and robust applicability of ADC-Net suggest its potential value for clinical engineering applications in the DIR of lung CT. • An artificial intelligence deep learning model for clinical engineering applications. • Fast and accurate unsupervised deformable image registration for lung CT. • Dual anatomical constraints for lung contours and internal vessels. • Anatomical awareness for large deformations and internal details. • Uncertainty estimations and subjective evaluations for results.