The alignment of images through deformable image registration is vital to clinical applications (e.g., atlas creation, image fusion, and tumor targeting in image-guided navigation systems) and is still a challenging problem. Recent progress in the field of deep learning has significantly advanced the performance of medical image registration. In this review, we present a comprehensive survey on deep learning-based deformable medical image registration methods. These methods are classified into five categories: Deep Iterative Methods, Supervised Methods, Unsupervised Methods, Weakly Supervised Methods, and Latest Methods. A detailed review of each category is provided with discussions about contributions, tasks, and inadequacies. We also provide statistical analysis for the selected papers from the point of view of image modality, the region of interest (ROI), evaluation metrics, and method categories. In addition, we summarize 33 publicly available datasets that are used for benchmarking the registration algorithms. Finally, the remaining challenges, future directions, and potential trends are discussed in our review.

No abstract

Deformable lung CT image registration is an essential task for computer-assisted interventions and other clinical applications, especially when organ motion is involved. While deep-learning-based image registration methods have recently achieved promising results by inferring deformation fields in an end-to-end manner, large and irregular deformations caused by organ motion still pose a significant challenge. In this paper, we present a method for registering lung CT images that is tailored to the specific patient being imaged. To address the challenge of large deformations between the source and target images, we break the deformation down into multiple continuous intermediate fields. These fields are then combined to create a spatio-temporal motion field. We further refine this field using a self-attention layer that aggregates information along motion trajectories. By leveraging temporal information from a respiratory cycle, our proposed methods can generate intermediate images that facilitate image-guided tumor tracking. We evaluated our approach extensively on a public dataset, and our numerical and visual results demonstrate the effectiveness of the proposed method.

A vehicle charging network system has to access large-scale heterogeneous terminals to collect charging pile status information, which may also give malicious terminals an opportunity to access. Though some general access authentication solutions aimed at only allowing trusted terminals have been proposed, they are difficult to work with in a vehicle charging network system. First, among various heterogeneous terminals with significant differences in computing capabilities, there are inevitably terminals that cannot support computations required for cryptography-based access authentication schemes. Second, though access authentication schemes based on device fingerprints are independent of terminal computing capabilities, their authentication performance is weak in robustness and high in overhead. Third, the access authentication delay is huge since the system cannot withstand heavy concurrent access requests from large-scale terminals. To address the above problems, we propose a reliable and lightweight trusted access authentication solution for terminals in the vehicle charging network system. By cloud, edge, and local servers cooperating to execute authentication tasks, our Cloud-Edge-End Collaborative architecture effectively alleviates the authentication delay caused by high concurrent requests. Each server in the architecture deploys our well-designed unified trusted access authentication (UATT) model based on device fingerprints. With ingenious data construction and the powerful swin-transformer network, the UATT model can provide robust and low-overhead authentication services for heterogeneous terminals. To minimize authentication latency, we further design an A2C-based authentication task scheduling scheme to decide which server executes the current task. Comprehensive experiments demonstrate our solution can authenticate terminals with an accuracy higher than 98% while reducing the required data packets by two orders of magnitude, and it can effectively reduce authentication latency.