An unsupervised multi-scale framework with attention-based network (MANet) for lung 4D-CT registration

4D-CT deformable image registration using unsupervised recursive cascaded full-resolution residual networks

A novel recursive cascaded full-resolution residual network (RCFRR-Net) for abdominal four-dimensional computed tomography (4D-CT) image registration was proposed. The entire network was end-to-end and trained in the unsupervised approach, which meant that the deformation vector field, which presented the ground truth, was not needed during training. The network was designed by cascading three full-resolution residual subnetworks with different architectures. The training loss consisted of the image similarity loss and the deformation vector field regularization loss, which were calculated based on the final warped image and the fixed image, allowing all cascades to be trained jointly and perform the progressive registration cooperatively. Extensive network testing was conducted using diverse datasets, including an internal 4D-CT dataset, a public DIRLAB 4D-CT dataset, and a 4D cone-beam CT (4D-CBCT) dataset. Compared with the iteration-based demon method and two deep learning-based methods (VoxelMorph and recursive cascaded network), the RCFRR-Net achieved consistent and significant gains, which demonstrated that the proposed method had superior performance and generalization capability in medical image registration. The proposed RCFRR-Net was a promising tool for various clinical applications.

Deep learning-based lung image registration: A review

Lung image registration can effectively describe the relative motion of lung tissues, thereby helping to solve series problems in clinical applications. Since the lungs are soft and fairly passive organs, they are influenced by respiration and heartbeat, resulting in discontinuity of lung motion and large deformation of anatomic features. This poses great challenges for accurate registration of lung image and its applications. The recent application of deep learning (DL) methods in the field of medical image registration has brought promising results. However, a versatile registration framework has not yet emerged due to diverse challenges of registration for different regions of interest (ROI). DL-based image registration methods used for other ROI cannot achieve satisfactory results in lungs. In addition, there are few review articles available on DL-based lung image registration. In this review, the development of conventional methods for lung image registration is briefly described and a more comprehensive survey of DL-based methods for lung image registration is illustrated. The DL-based methods are classified according to different supervision types, including fully-supervised, weakly-supervised and unsupervised. The contributions of researchers in addressing various challenges are described, as well as the limitations of these approaches. This review also presents a comprehensive statistical analysis of the cited papers in terms of evaluation metrics and loss functions. In addition, publicly available datasets for lung image registration are also summarized. Finally, the remaining challenges and potential trends in DL-based lung image registration are discussed.

An unsupervised image registration method employing chest computed tomography images and deep neural networks

BACKGROUND

Deformable image registration is crucial for multiple radiation therapy applications. Fast registration of computed tomography (CT) lung images is challenging because of the large and nonlinear deformation between inspiration and expiration. With advancements in deep learning techniques, learning-based registration methods are considered efficient alternatives to traditional methods in terms of accuracy and computational cost.

METHOD

In this study, an unsupervised lung registration network (LRN) with cycle-consistent training is proposed to align two acquired CT-derived lung datasets during breath-holds at inspiratory and expiratory levels without utilizing any ground-truth registration results. Generally, the LRN model uses three loss functions: image similarity, regularization, and Jacobian determinant. Here, LRN was trained on the CT datasets of 705 subjects and tested using 10 pairs of public CT DIR-Lab datasets. Furthermore, to evaluate the effectiveness of the registration technique, target registration errors (TREs) of the LRN model were compared with those of the conventional algorithm (sum of squared tissue volume difference; SSTVD) and a state-of-the-art unsupervised registration method (VoxelMorph).

RESULTS

The results showed that the LRN with an average TRE of 1.78 ± 1.56 mm outperformed VoxelMorph with an average TRE of 2.43 ± 2.43 mm, which is comparable to that of SSTVD with an average TRE of 1.66 ± 1.49 mm. In addition, estimating the displacement vector field without any folding voxel consumed less than 2 s, demonstrating the superiority of the learning-based method with respect to fiducial marker tracking and the overall soft tissue alignment with a nearly real-time speed.

CONCLUSIONS

Therefore, this proposed method shows significant potential for use in time-sensitive pulmonary studies, such as lung motion tracking and image-guided surgery.