Registration Performance Research Articles

A Point Cloud Registration Framework with Color Information Integration

Point cloud registration serves as a critical tool for constructing 3D environmental maps. Both geometric and color information are instrumental in differentiating diverse point features. Specifically, when points appear similar based solely on geometric features, rendering them challenging to distinguish, the color information embedded in the point cloud carries significantly important features. In this study, the colored point cloud is utilized in the FCGCF algorithm, a refined version of the FCGF algorithm, incorporating color information. Moreover, we introduce the PointDSCC method, which amalgamates color consistency from the PointDSC method for outlier removal, thus enhancing registration performance when synergized with other pipeline stages. Comprehensive experiments across diverse datasets reveal that the integration of color information into the registration pipeline markedly surpasses the majority of existing methodologies and demonstrates robust generalizability.

SHC: soft-hard correspondences framework for simplifying point cloud registration

Point cloud registration is a multifaceted problem that involves a series of procedures. Many deep learning methods employ complex structured networks to achieve robust registration performance. However, these intricate structures can amplify the challenges of network learning and impede gradient propagation. To address this concern, the soft-hard correspondence (SHC) framework is introduced in the present paper to streamline the registration problem. The framework encompasses two modes: the hard correspondence mode, which transforms the registration problem into a correspondence pair search problem, and the soft correspondence mode, which addresses this new problem. The simplification of the problem provides two advantages. First, it eliminates the need for intermediate operations that lead to error fusion and counteraction, thereby improving gradient propagation. Second, a perfect solution is not necessary to solve the new problem, since accurate registration results can be achieved even in the presence of errors in the found pairs. The experimental results demonstrate that SHC successfully simplifies the registration problem. It achieves performance comparable to complex networks using a simple network and can achieve zero error on datasets with perfect correspondence pairs.

Automated three-dimensional image registration for longitudinal photoacoustic imaging.

Photoacoustic tomography (PAT) has great potential in monitoring disease progression and treatment response in breast cancer. However, due to variations in breast repositioning, there is a chance of geometric misalignment between images. Further, poor repositioning can affect light fluence distribution and imaging field-of-view, making images different from one another. The net effect is that it becomes challenging to distinguish between image changes due to repositioning effects and those due to true biological variations. The aim is to develop a three-dimensional image registration framework for geometrically aligning repeated PAT volumetric images, which are potentially affected by repositioning effects such as misalignment, changed radiant exposure conditions, and different fields-of-view. The proposed framework involves the use of a coordinate-based neural network to represent the displacement field between pairs of PAT volumetric images. A loss function based on normalized cross correlation and Frangi vesselness feature extraction at multiple scales was implemented. We refer to our image registration framework as MUVINN-reg, which stands for multiscale vesselness-based image registration using neural networks. The approach was tested on a longitudinal dataset of healthy volunteer breast PAT images acquired with the hybrid photoacoustic-ultrasound Photoacoustic Mammoscope 3 imaging system. The registration performance was also tested under unfavorable repositioning conditions such as intentional mispositioning, and variation in breast-supporting cup size between measurements. A total of 13 pairs of repeated PAT scans were included in this study. MUVINN-reg showed excellent performance in co-registering each pair of images. The proposed framework was shown to be robust to image intensity shifts and field-of-view changes. Furthermore, MUVINN-reg could align vessels at imaging depths greater than 4cm. The proposed framework will enable the use of PAT for quantitative and reproducible monitoring of disease progression and treatment response.

A high-accuracy multi-temporal laser point cloud registration method for providing a detailed expression of the urban environment

In consideration of the significant changes in urban environmental scenes and the impact of factors such as signal obstruction on positioning, the spatial positions of multi-temporal Mobile Laser Scanning (MLS) point clouds collected in the same area are inconsistent, which makes it challenging to provide a complete expression of the urban road environment. To address this issue, a precise registration algorithm based on pole-like targets is proposed. The core steps include registration primitive extraction: a cylindrical spatial neighborhood is established based on the distinctive key points, and precise extraction of pole-like geospatial point cloud data is performed using the Euclidean clustering method with the normal curvature constraint. Achieving optimal spatial transformation: a circle center fitting method with additional Mean Absolute Error (MAE) loss function constraints was developed based on the stable elemental unit which was utilized to accurately construct homonymous feature point pairs. Validation results from multiple real urban point cloud datasets collected from different experimental areas and platforms demonstrate that our method achieves superior registration performance, with mean residuals below 5 cm in both the planar and elevation directions. The proposed method exhibits strong universality and registration robustness for multi-temporal point cloud data of the homologous or cross-sources.

Robust registration of multi-modal remote sensing images based on multi-dimensional oriented self-similarity features

Registration of multi-modal remote sensing images (MRSI) is crucial for unlocking the full potential of heterogeneous remote sensing imagery. However, achieving accurate registration among MRSI is challenging due to the trade-off between geometric invariance and matching accuracy, caused by differences in signal-to-noise ratio and nonlinear radiometric distortion (NRD) arising from varying imaging mechanisms. To tackle the challenge, this paper proposes a lightweight and hybrid feature-guided registration algorithm for MRSI called the hybrid registration algorithm based on multi-dimensional oriented self-similarity features (MOSS). MOSS leverages the advantages of multi-dimensional oriented self-similarity features to progressively enhance registration performance. In the hybrid feature coarse matching stage, oriented self-similarity features are extracted from MRSI, and their directional information is utilized for feature description to estimate the initial affine transformation. The fine matching under multi-dimensional oriented self-similarity features stage takes the outputs of the coarse matching stage to perform a template-like matching process. To evaluate the performance of MOSS, comprehensive experiments are conducted using six different combinations of MRSI, and seven state-of-the-art registration algorithms are selected for comparison. The experimental results demonstrate that MOSS outperforms the compared methods, with the number of correct matches being at least about 1.6 times higher than the comparison methods. Moreover, MOSS exhibits the lowest root mean square error across all experiments, with an average RMSE of 1.86 pixels, achieving an RMSE within 2 pixels. This highlights its effectiveness in achieving precise alignment and robust registration of MRSI.

Using outlier elimination to assess learning-based correspondence matching methods

Recently, deep learning (DL) technology has been widely used in correspondence matching. The learning-based models are usually trained on benign image pairs with partial overlaps. Since DL model is usually data-dependent, non-overlapping images may be used as poison samples to fool the model and produce false registrations. In this study, we propose an outlier elimination-based assessment method (OEAM) to assess the registrations of learning-based correspondence matching method on partially overlapping and non-overlapping images. OEAM first eliminates outliers based on spatial paradox. Then OEAM implements registration assessment in two streams using the obtained core correspondence set. If the cardinality of the core set is sufficiently small, the input registration is assessed as a low-quality registration. Otherwise, it is assessed to be of high quality, and OEAM improves its registration performance using the core set. OEAM is a post-processing technique imposed on learning-based method. The comparison experiments are implemented on outdoor (YFCC100M) and indoor (SUN3D) datasets using four deep learning-based methods. The experimental results on registrations of partially overlapping images show that OEAM can reliably infer low-quality registrations and improve performance on high-quality registrations. The experiments on registrations of non-overlapping images demonstrate that learning-based methods are vulnerable to poisoning attacks launched by non-overlapping images, and OEAM is robust against poisoning attacks crafted by non-overlapping images.

3DMNDT: 3D Multi-View Registration Method Based on the Normal Distributions Transform

The normal distributions transform (NDT) is an effective paradigm for point set registration. This method was initially designed for pair-wise registration and suffers from the accumulated error problem when directly applied to multi-view registration. Under the framework of point-to-cluster correspondence, this paper proposes a novel multi-view registration method named 3D multi-view registration based on the normal distributions transform (3DMNDT), which integrates the k-means clustering and Lie algebra optimizer to achieve multi-view registration. More specifically, the multi-view registration is cast into the maximum likelihood estimation problem. Firstly, k-means clustering is utilized to divide all data points into different clusters, where one normal distribution is computed to locally model the probability of measuring a data point in each cluster. Subsequently, the multi-view registration problem is formulated by the NDT-based likelihood function. To maximize this likelihood function, the Lie algebra optimizer is introduced and developed to optimize each rigid transformation sequentially. 3DMNDT implements data point clustering, NDT computing, and rigid transformation optimization alternately until the desired registration results are obtained. Experimental results tested on benchmark data sets illustrate that 3DMNDT can achieve state-of-the-art performance for multi-view registration. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by solving the problem of registering multiple point sets. The normal distributions transform (NDT) is a well-known pair-wise registration method widely applied in the robotic domain. This paper extends the original NDT and proposes a novel registration method to simultaneously align more than two point sets. The multi-view registration is cast into the maximum likelihood estimation problem. Subsequently, the k-means clustering and Lie algebra optimizer are integrated to estimate registration parameters. Experimental results demonstrate its superior performance on the accuracy, efficiency, and robustness for multi-view registration of point sets.

Correlation Attention Registration Based on Deep Learning from Histopathology to MRI of Prostate.

Deep learning offers a promising methodology for the registration of prostate cancer images from histopathology to MRI. We explored how to effectively leverage key information from images to achieve improved end-to-end registration. We developed an approach based on a correlation attention registration framework to register segmentation labels of histopathology onto MRI. The network was trained using paired prostate datasets of histopathology and MRI from the Cancer Imaging Archive. We introduced An L2-Pearson correlation layer to enhance feature matching. Furthermore, our model employed an enhanced attention regression network to distinguish between key and nonkey features. For data analysis, we used the Kolmogorov-Smirnov test and a one-sample t-test, with the statistical significance level for the one-sample t-test set at 0.001. Compared with two other models (ProsRegNet and CNNGeo), our model exhibited improved performance in Dice coefficient, with increases of 9.893% and 2.753%, respectively. The Hausdorff distance was reduced by approximately 50% and 50%, while the average label error (ALE) was reduced by 0.389% and 15.021%. The proposed improved multimodal prostate registration framework demonstrated high performance in statistical analysis. The results indicate that our enhanced strategy significantly improves registration performance and enables faster registration of histopathological images of patients undergoing radical prostatectomy to preoperative MRI. More accurate registration can prevent over-diagnosing low-risk cancers and frequent false positives due to observer differences.

DTR-GAN: An Unsupervised Bidirectional Translation Generative Adversarial Network for MRI-CT Registration

Medical image registration is a fundamental and indispensable element in medical image analysis, which can establish spatial consistency among corresponding anatomical structures across various medical images. Since images with different modalities exhibit different features, it remains a challenge to find their exact correspondence. Most of the current methods based on image-to-image translation cannot fully leverage the available information, which will affect the subsequent registration performance. To solve the problem, we develop an unsupervised multimodal image registration method named DTR-GAN. Firstly, we design a multimodal registration framework via a bidirectional translation network to transform the multimodal image registration into a unimodal registration, which can effectively use the complementary information of different modalities. Then, to enhance the quality of the transformed images in the translation network, we design a multiscale encoder–decoder network that effectively captures both local and global features in images. Finally, we propose a mixed similarity loss to encourage the warped image to be closer to the target image in deep features. We extensively evaluate methods for MRI-CT image registration tasks of the abdominal cavity with advanced unsupervised multimodal image registration approaches. The results indicate that DTR-GAN obtains a competitive performance compared to other methods in MRI-CT registration. Compared with DFR, DTR-GAN has not only obtained performance improvements of 2.35% and 2.08% in the dice similarity coefficient (DSC) of MRI-CT registration and CT-MRI registration on the Learn2Reg dataset but has also decreased the average symmetric surface distance (ASD) by 0.33 mm and 0.12 mm on the Learn2Reg dataset.

Semantic enhancement based adaptive geometric encoding network for low overlap point cloud registration

The presence of partial or low overlaps in real point cloud pairs poses significant challenges to obtain robust registration. There is an absence of a unified framework that localizes reliable overlapping regions and correspondences. This work proposes an adaptive point cloud geometric encoding network based on semantic enhancement that generates overlap information with geometric-and-semantic consistency in various scenarios. This enables the network to further ensure distinctive geometric representation when the low overlap point cloud pairs have scarce differences in the geometric structures. In addition, our study includes experiments conducted on a self-created semantic-assisted dataset designed to facilitate in-depth research on point cloud registration. The experimental results clearly demonstrate the efficacy and overall improvements of the registration performance, particularly highlighting the potential of our approach in addressing the challenges associated with low overlap scenarios that have repetitive geometry patterns.

HCS-Net: Multi-level deformation strategy combined with quadruple attention for image registration

Background and objectiveNon-rigid image registration plays a significant role in computer-aided diagnosis and surgical navigation for brain diseases. Registration methods that utilize convolutional neural networks (CNNs) have shown excellent accuracy when applied to brain magnetic resonance images (MRI). However, CNNs have limitations in understanding long-range spatial relationships in images, which makes it challenging to incorporate contextual information. And in intricate image registration tasks, it is difficult to achieve a satisfactory dense prediction field, resulting in poor registration performance. MethodsThis paper proposes a multi-level deformable unsupervised registration model that combines Transformer and CNN to achieve non-rigid registration of brain MRI. Firstly, utilizing a dual encoder structure to establish the dependency relationship between the global features of two images and to merge features of varying scales, as well as to preserve the relative spatial position information of feature maps at different scales. Then the proposed multi-level deformation strategy utilizes different deformable fields of varying resolutions generated by the decoding structure to progressively deform the moving image. Ultimately, the proposed quadruple attention module is incorporated into the decoding structure to merge feature information from various directions and emphasize the spatial features in the dominant channels. ResultsThe experimental results on multiple brain MR datasets demonstrate that the promising network could provide accurate registration and is comparable to state-of-the-art methods. ConclusionThe proposed registration model can generate superior deformable fields and achieve more precise registration effects, enhancing the auxiliary role of medical image registration in various fields and advancing the development of computer-aided diagnosis, surgical navigation, and related domains.

Comparative performance of national civil registration and vital statistics systems: a global assessment.

To assess the current state of the world's civil registration and vital statistics systems based on publicly available data and to propose strategic development pathways, including priority interventions, for countries at different levels of civil registration and vital statistics performance. We applied a performance assessment framework to publicly available data, using a composite indicator highly correlated with civil registration and vital statistics performance which we then adjusted for data incomparability and missing values. Globally, civil registration and vital statistics systems score on average 0.70 (0-1 scale), with substantial variations across countries and regions. Scores ranged from less than 0.50 in emerging systems to nearly 1.00 in the most developed systems. Approximately one fifth of the world's population live in the 43 countries with low system performance (< 0.477). Irrespective of system development, health sector indicators consistently scored lower than other determinants of civil registration and vital statistics performance. From our assessment, we provide three main recommendations for how the health sector can contribute to improving civil registration and vital statistics systems: (i)enhanced health sector engagement in birth and death notification; (ii) a more systematic approach to training cause of death diagnostics; and (iii) leadership in the implementation of verbal autopsy methods. Four different civil registration and vital statistics improvement pathways for countries at different levels of system development are proposed, that can constitute a blueprint for regional civil registration and vital statistics strengthening activities that countries can adapt and refine to suit their capabilities, resources, and particular challenges.

MSCAReg‐Net: Multi‐scale complexity‐aware convolutional neural network for deformable image registration

AbstractDeep learning‐based image registration (DLIR) has been widely developed, but it remains challenging in perceiving small and large deformations. Besides, the effectiveness of the DLIR methods was also rarely validated on the downstream tasks. In the study, a multi‐scale complexity‐aware registration network (MSCAReg‐Net) was proposed by devising a complexity‐aware technique to facilitate DLIR under a single‐resolution framework. Specifically, the complexity‐aware technique devised a multi‐scale complexity‐aware module (MSCA‐Module) to perceive deformations with distinct complexities, and employed a feature calibration module (FC‐Module) and a feature aggregation module (FA‐Module) to facilitate the MSCA‐Module by generating more distinguishable deformation features. Experimental results demonstrated the superiority of the proposed MSCAReg‐Net over the existing methods in terms of registration accuracy. Besides, other than the indices of Dice similarity coefficient (DSC) and percentage of voxels with non‐positive Jacobian determinant (), a comprehensive evaluation of the registration performance was performed by applying this method on a downstream task of multi‐atlas hippocampus segmentation (MAHS). Experimental results demonstrated that this method contributed to a better hippocampus segmentation over other DLIR methods, and a comparable segmentation performance with the leading SyN method. The comprehensive assessment including DSC, , and the downstream application on MAHS demonstrated the advances of this method.

A method of UAV visible light remote sensing image registration based on eigenvector technique

As the advancement of unmanned aerial vehicle technology and deep learning technology, many deep learning technologies have been applied in the field of unmanned aerial vehicle image research. To improve the registration precision and efficiency of unmanned aerial vehicle visible light remote sensing images, this study uses the idea of eigenvectors to build an unmanned aerial vehicle visible light remote sensing image registration model. Firstly, the traditional registration model is optimized by multi-branch attention mechanism, and then the final remote sensing image registration model was constructed by combining convolutional neural network and mask prediction module. Testing the performance of the model, and the experiment findings expresses that the registration error of the final model is about 0.05, the registration precision is more than 0.95, and the registration time is within 2s, so it has a good performance of image registration. In conclusion, the image registration model designed by this research institute can improve the existing problems in the current registration field and provide new ideas for improving the image registration effect.

Quatro++: Robust global registration exploiting ground segmentation for loop closing in LiDAR SLAM

Global registration is a fundamental task that estimates the relative pose between two viewpoints of 3D point clouds. However, there are two issues that degrade the performance of global registration in LiDAR SLAM: one is the sparsity issue and the other is degeneracy. The sparsity issue is caused by the sparse characteristics of the 3D point cloud measurements in a mechanically spinning LiDAR sensor. The degeneracy issue sometimes occurs because the outlier-rejection methods reject too many correspondences, leaving less than three inliers. These two issues have become more severe as the pose discrepancy between the two viewpoints of 3D point clouds becomes greater. To tackle these problems, we propose a robust global registration framework, called Quatro++. Extending our previous work that solely focused on the global registration itself, we address the robust global registration in terms of the loop closing in LiDAR SLAM. To this end, ground segmentation is exploited to achieve robust global registration. Through the experiments, we demonstrate that our proposed method shows a higher success rate than the state-of-the-art global registration methods, overcoming the sparsity and degeneracy issues. In addition, we show that ground segmentation significantly helps to increase the success rate for the ground vehicles. Finally, we apply our proposed method to the loop closing module in LiDAR SLAM and confirm that the quality of the loop constraints is improved, showing more precise mapping results. Therefore, the experimental evidence corroborated the suitability of our method as an initial alignment in the loop closing. Our code is available at https://quatro-plusplus.github.io.

OPSNet: Point Cloud Registration Based on Overlapping Predictive Segmentation

Registration is a critical task in the field of point clouds, aiming to align data acquired at different times or from different viewpoints for accurate matching. Deep learning methods have made important progress in point cloud registration tasks. However, most existing approaches do not handle the non-overlapping parts of point clouds, resulting in poor performance in low-overlap and noisy scenarios. We propose a registration model called OPSNet, which achieves optimal alignment transformation estimation and overlapping region prediction through an iterative process. OPSNet consists of modules including global feature extraction, overlapping region prediction segmentation, and alignment registration. By utilizing a segmentation algorithm to deal with the non-overlapping parts of data, OPSNet reduces the adverse effects caused by non-overlapping regions in point cloud registration. The model learns feature representations and performs iterative optimization to achieve precise point cloud alignment. We conduct comprehensive experiments on common point cloud registration datasets and compare OPSNet with several classical point cloud registration methods. The experimental results display that OPSNet achieves outstanding performance in terms of rotation and translation errors, outperforming other methods. Additionally, we evaluate the registration performance under different overlap ratios and find that OPSNet can achieve better registration results even in low-overlap scenarios.

Exploring the performance of implicit neural representations for brain image registration

Pairwise image registration is a necessary prerequisite for brain image comparison and data integration in neuroscience and radiology. In this work, we explore the efficacy of implicit neural representations (INRs) in improving the performance of brain image registration in magnetic resonance imaging. In this setting, INRs serve as a continuous and coordinate based approximation of the deformation field obtained through a multi-layer perceptron. Previous research has demonstrated that sinusoidal representation networks (SIRENs) surpass ReLU models in performance. In this study, we first broaden the range of activation functions to further investigate the registration performance of implicit networks equipped with activation functions that exhibit diverse oscillatory properties. Specifically, in addition to the SIRENs and ReLU, we evaluate activation functions based on snake, sine+, chirp and Morlet wavelet functions. Second, we conduct experiments to relate the hyper-parameters of the models to registration performance. Third, we propose and assess various techniques, including cycle consistency loss, ensembles and cascades of implicit networks, as well as a combined image fusion and registration objective, to enhance the performance of implicit registration networks beyond the standard approach. The investigated implicit methods are compared to the VoxelMorph convolutional neural network and to the symmetric image normalization (SyN) registration algorithm from the Advanced Normalization Tools (ANTs). Our findings not only highlight the remarkable capabilities of implicit networks in addressing pairwise image registration challenges, but also showcase their potential as a powerful and versatile off-the-shelf tool in the fields of neuroscience and radiology.

Ultra-fast multi-parametric 4D-MRI image reconstruction for real-time applications using a downsampling-invariant deformable registration (D2R) model

Background and purposeMotion estimation from severely downsampled 4D-MRI is essential for real-time imaging and tumor tracking. This simulation study developed a novel deep learning model for simultaneous MR image reconstruction and motion estimation, named the Downsampling-Invariant Deformable Registration (D2R) model. Materials and methodsForty-three patients undergoing radiotherapy for liver tumors were recruited for model training and internal validation. Five prospective patients from another center were recruited for external validation. Patients received 4D-MRI scans and 3D MRI scans. The 4D-MRI was retrospectively down-sampled to simulate real-time acquisition. Motion estimation was performed using the proposed D2R model. The accuracy and robustness of the proposed D2R model and baseline methods, including Demons, Elastix, the parametric total variation (pTV) algorithm, and VoxelMorph, were compared. High-quality (HQ) 4D-MR images were also constructed using the D2R model for real-time imaging feasibility verification. The image quality and motion accuracy of the constructed HQ 4D-MRI were evaluated. ResultsThe D2R model showed significantly superior and robust registration performance than all the baseline methods at downsampling factors up to 500. HQ T1-weighted and T2-weighted 4D-MR images were also successfully constructed with significantly improved image quality, sub-voxel level motion error, and real-time efficiency. External validation demonstrated the robustness and generalizability of the technique. ConclusionIn this study, we developed a novel D2R model for deformation estimation of downsampled 4D-MR images. HQ 4D-MR images were successfully constructed using the D2R model. This model may expand the clinical implementation of 4D-MRI for real-time motion management during liver cancer treatment.

A transformer-based hierarchical registration framework for multimodality deformable image registration.

Deformable image registration (DIR) between daily and reference images is fundamentally important for adaptive radiotherapy. In the last decade, deep learning-based image registration methods have been developed with faster computation time and improved robustness compared to traditional methods. However, the registration performance is often degraded in extra-cranial sites with large volume containing multiple anatomic regions, such as Computed Tomography (CT)/Magnetic Resonance (MR) images used in head and neck (HN) radiotherapy. In this study, we developed a hierarchical deformable image registration (DIR) framework, Patch-based Registration Network (Patch-RegNet), to improve the accuracy and speed of CT-MR and MR-MR registration for head-and-neck MR-Linac treatments. Patch-RegNet includes three steps: a whole volume global registration, a patch-based local registration, and a patch-based deformable registration. Following a whole-volume rigid registration, the input images were divided into overlapping patches. Then a patch-based rigid registration was applied to achieve accurate local alignment for subsequent DIR. We developed a ViT-Morph model, a combination of a convolutional neural network (CNN) and the Vision Transformer (ViT), for the patch-based DIR. A modality independent neighborhood descriptor was adopted in our model as the similarity metric to account for both inter-modality and intra-modality registration. The CT-MR and MR-MR DIR models were trained with 242 CT-MR and 213 MR-MR image pairs from 36 patients, respectively, and both tested with 24 image pairs (CT-MR and MR-MR) from 6 other patients. The registration performance was evaluated with 7 manually contoured organs (brainstem, spinal cord, mandible, left/right parotids, left/right submandibular glands) by comparing with the traditional registration methods in Monaco treatment planning system and the popular deep learning-based DIR framework, Voxelmorph. Evaluation results show that our method outperformed VoxelMorph by 6 % for CT-MR registration, and 4 % for MR-MR registration based on DSC measurements. Our hierarchical registration framework has been demonstrated achieving significantly improved DIR accuracy of both CT-MR and MR-MR registration for head-and-neck MR-guided adaptive radiotherapy.

MD-SGT: Multi-dilation spherical graph transformer for unsupervised medical image registration.

Deformable medical image registration is an essential preprocess step for several clinical applications. Even though the existing convolutional neural network and transformer based methods achieved the promising results, the limited long-range spatial dependence and non-uniform attention span of these models prohibit further improving the registration performance. To deal with this issue, we proposed a multi-dilation spherical graph transformer (MD-SGT), in which the encoder combined the advantages of convolutional and graph transformer blocks to distinguish effectively the differences between the reference and the template images at various scales. Specifically, the features of each voxel were obtained by aggregating the information from its neighbors sampled from different spherical regions with different dilation rates. The implicit convolution inductive bias and long-range uniform attention span induced by such information aggregation manner made the features more representative for registration. Through the qualitative and quantitative comparisons with state-of-the-art methods on two datasets, we demonstrated that combining long-range uniform attention span and inductive bias are beneficial for promoting the image registration performance, with the Dice score, ASD and HD95 being improved at least by 0.5%, 2.2% and 1.1%, respectively.