Registration Accuracy Research Articles

Enhancing registration precision of multispectral breast images by fusing multi-wavelength information based on an improved gradient descent method

Multispectral transmission imaging is widely recognized as a developmental approach for early breast cancer screening. However, a persistent challenge exists in image registration, particularly in processing human images, where registration often relies solely on single-wavelength information, leading to inadequate accuracy. This paper purposes a novel image registration method that involves summing pixel values from three color channels at identical pixel coordinates and utilizes an improved gradient descent algorithm to achieve image registration. Multispectral maps at wavelengths of 445 nm, 520 nm, and 620 nm serve as examples for testing and evaluation, with frames summed for registered images at each wavelength. Experimental results demonstrate the superior registration accuracy of this method compared to registering images of a single-wavelength independently. This advancement enhances the accuracy and reliability of multispectral transmission imaging in the early detection of breast cancer.

Medical image registration via neural fields

Image registration is an essential step in many medical image analysis tasks. Traditional methods for image registration are primarily optimization-driven, finding the optimal deformations that maximize the similarity between two images. Recent learning-based methods, trained to directly predict transformations between two images, run much faster, but suffer from performance deficiencies due to domain shift. Here we present a new neural network based image registration framework, called NIR (Neural Image Registration), which is based on optimization but utilizes deep neural networks to model deformations between image pairs. NIR represents the transformation between two images with a continuous function implemented via neural fields, receiving a 3D coordinate as input and outputting the corresponding deformation vector. NIR provides two ways of generating deformation field: directly output a displacement vector field for general deformable registration, or output a velocity vector field and integrate the velocity field to derive the deformation field for diffeomorphic image registration. The optimal registration is discovered by updating the parameters of the neural field via stochastic mini-batch gradient descent. We describe several design choices that facilitate model optimization, including coordinate encoding, sinusoidal activation, coordinate sampling, and intensity sampling. NIR is evaluated on two 3D MR brain scan datasets, demonstrating highly competitive performance in terms of both registration accuracy and regularity. Compared to traditional optimization-based methods, our approach achieves better results in shorter computation times. In addition, our methods exhibit performance on a cross-dataset registration task, compared to the pre-trained learning-based methods.

Variational image registration with learned prior using multi-stage VAEs

Variational Autoencoders (VAEs) are an efficient variational inference technique coupled with the generated network. Due to the uncertainty provided by variational inference, VAEs have been applied in medical image registration. However, a critical problem in VAEs is that the simple prior cannot provide suitable regularization, which leads to the mismatch between the variational posterior and prior. An optimal prior can close the gap between the evidence’s real and variational posterior. In this paper, we propose a multi-stage VAE to learn the optimal prior, which is the aggregated posterior. A lightweight VAE is used to generate the aggregated posterior as a whole. It is an effective way to estimate the distribution of the high-dimensional aggregated posterior that commonly exists in medical image registration based on VAEs. A factorized telescoping classifier is trained to estimate the density ratio of a simple given prior and aggregated posterior, aiming to calculate the KL divergence between the variational and aggregated posterior more accurately. We analyze the KL divergence and find that the finer the factorization, the smaller the KL divergence is. However, too fine a partition is not conducive to registration accuracy. Moreover, the diagonal hypothesis of the variational posterior’s covariance ignores the relationship between latent variables in image registration. To address this issue, we learn a covariance matrix with low-rank information to enable correlations with each dimension of the variational posterior. The covariance matrix is further used as a measure to reduce the uncertainty of deformation fields. Experimental results on four public medical image datasets demonstrate that our proposed method outperforms other methods in negative log-likelihood (NLL) and achieves better registration accuracy.

Constructing the KOR152 Korean Young Adult Brain Atlas Utilizing the State-of-the-Art Method for the Age-Specific Population.

Spatial normalization is an essential process for comparative analyses that heavily depends on the standard brain template used. Brain morphological differences are observed in different populations due to genetic and environmental factors, causing mismatches in regions when the data are normalized to different population templates. Recent studies have indicated differences between Caucasian and East Asian populations as well as within East Asian populations, suggesting the necessity of population-specific brain templates. Thus, this study aimed to construct a Korean young adult age-specific brain template utilizing an advanced method of template construction to update the currently available Korean template. The KOR152 template was constructed via affine and nonlinear iterative procedures based on prior studies. We compared the morphological features of different population templates (MNI152, Indian_157, and CN200). The distance and volumetric changes before and after registering the data to these templates were calculated for registration accuracy. The KOR152 global brain features revealed a shorter overall length than the other population templates. The registration accuracy by distance and volumetric change was significantly lower than that of the other population templates, implying that the KOR152 was more accurate than other templates for the young adult Korean population. This study provided evidence for the need for a population-specific template that may be more appropriate for structural and functional studies in Korean populations.

Point cloud registration via sampling-based evolutionary multitasking

Point cloud registration (PCR) is an important task in both computer vision and pattern recognition. However, since the success of most existing two-stage PCR methods largely depends on the implicit assumption that the first coarse registration stage can provide an approximately optimal initial transformation for the second fine stage, these methods suffer from low success rate when the assumption is not satisfied. Evolutionary multitasking can find better solutions for multiple tasks simultaneously by transferring knowledge among multiple related tasks. Inspired by evolutionary multitasking, this study proposes a sampling-based multitask optimization method for PCR, which solves the problem of low registration success rate by sharing knowledge between two related tasks generated by a dataset. Specifically, one task is for roughly aligning the sampled point cloud, and the other is for the original unsampled point cloud. The main purpose of the first task is to continuously provide useful knowledge to the second task so that it can achieve precise alignment. Then, a new knowledge transfer mechanism guided by historical information is proposed, which can effectively adjust the search behavior of the original unsampled task. In addition, we develop a dynamic task complement strategy to complement the accuracy that may be lost by downsampling. The results on five different datasets show that the proposed method can achieve higher registration accuracy with higher success rate compared to other state-of-the-art PCR methods.

D2BGAN: Dual Discriminator Bayesian Generative Adversarial Network for Deformable MR-Ultrasound Registration Applied to Brain Shift Compensation.

During neurosurgical procedures, the neuro-navigation system's accuracy is affected by the brain shift phenomenon. One popular strategy is to compensate for brain shift using intraoperative ultrasound (iUS) registration with pre-operative magnetic resonance (MR) scans. This requires a satisfactory multimodal image registration method, which is challenging due to the low image quality of ultrasound and the unpredictable nature of brain deformation during surgery. In this paper, we propose an automatic unsupervised end-to-end MR-iUS registration approach named the Dual Discriminator Bayesian Generative Adversarial Network (D2BGAN). The proposed network consists of two discriminators and a generator optimized by a Bayesian loss function to improve the functionality of the generator, and we add a mutual information loss function to the discriminator for similarity measurements. Extensive validation was performed on the RESECT and BITE datasets, where the mean target registration error (mTRE) of MR-iUS registration using D2BGAN was determined to be 0.75 ± 0.3 mm. The D2BGAN illustrated a clear advantage by achieving an 85% improvement in the mTRE over the initial error. Moreover, the results confirmed that the proposed Bayesian loss function, rather than the typical loss function, improved the accuracy of MR-iUS registration by 23%. The improvement in registration accuracy was further enhanced by the preservation of the intensity and anatomical information of the input images.

Remote sensing image registration method based on synchronous atmospheric correction.

Image registration is a crucial preprocessing step in remote sensing applications, integrating information from multiple images to achieve synergistic advantages. Nevertheless, aerosols characterized by spatiotemporal heterogeneity can result in the blurring of remote-sensing images, thereby compromising the accuracy of image registration. This paper begins by analyzing the basic principles of atmospheric correction and image registration. The variations in atmospheric radiative contribution caused by aerosol changes in real-world scenarios were simulated, along with an examination of the relationship between atmospheric effects and the quantity of image features. Subsequently, addressing the challenge posed by insufficient synchronicity in aerosol parameters and the influence of atmospheric effects on remote sensing image registration, we propose a registration method based on synchronous atmospheric correction. This approach utilizes the Airborne Synchronous Monitoring Atmospheric Corrector (ASMAC) to obtain aerosol optical depth and column water vapor images for synchronous atmospheric correction of remote sensing images, along with the assessment of the registration transformation matrix. Finally, airborne experiments involving ASMAC and high-resolution cameras are conducted to validate the proposed method's improvement in remote sensing image registration accuracy. Experimental results demonstrate the effectiveness of the proposed method, showcasing an increase in the number of features and improvements in quantitative evaluation metrics. Specifically, the normalized correlation coefficient improved by up to 2.408%, while the normalized mutual information increased by a maximum of 1.395%, a maximum feature count and successfully matched features improvement of 21.1% and 38.5.

Indirect deformable image registration using synthetic image generated by unsupervised deep learning

Background and purpose3D image registration is now common in many medical domains. Multimodal registration implies the use of different imaging modalities, which results in lower accuracy compared to monomodal registration. The aim of this study was to propose a novel approach for deformable image registration (DIR) that incorporates an unsupervised deep learning (DL)-based generation step. The objective was to reduce the challenge of multimodal registration to monomodal registration. Material and methodsTwo datasets from prostate radiotherapy patients were used to evaluate the proposed method. The first dataset consisted of Computed Tomography (CT)/ Cone Beam Computed Tomography (CBCT) pairs from 23 patients using different CBCT devices. The second dataset included Magnetic Resonance Imaging (MRI)/CT pairs from two different care centers, utilizing different MRI devices (0.35 T MRIdian MR-Linac, 1.5 T GE lightspeed MRI). Following a preprocessing step essential for ensuring DL synthesis accuracy and standardizing the database, synthetic CTs (sCTreg) were generated using an unsupervised conditional Generative Adversarial Network (cGAN). The generated sCTs from CBCT or MRI were then utilized for deformable registration with CT scans. This registration method was compared to three standard methods: rigid registration, Elastix registration based on BSplines, and VoxelMorph-based registration (applied exclusively to CBCT/CT). The endpoints of comparison were the dice coefficients calculated between delineated structures for both datasets. ResultsFor both datasets, intermediary sCT generation provided the highest dice coefficients. Dices reached 0.85, 0.85 and 0.75 for the prostate, bladder and rectum for the dataset 1 and 0.90, 0.95 and 0.87 respectively for the dataset 2. When the sCT were not used, dices reached 0.66, 0.78, 0.66 for the dataset 1 and 0.93, 0.87 and 0.84 for the dataset 2. Furthermore, the evaluation of the impact of registration on sCT generation showed that lower Mean Absolute Errors were obtained when the registration was conducted with a sCT. ConclusionsUsing unsupervised deep learning to synthesize intermediate sCT has led to improved registration accuracy in radiotherapy applications employing two distinct imaging modalities.

High-Precision Monitoring Method for Bridge Deformation Measurement and Error Analysis Based on Terrestrial Laser Scanning

In bridge structure monitoring and evaluation, deformation data serve as a crucial basis for assessing structural conditions. Different from discrete monitoring points, spatially continuous deformation modes provide a comprehensive understanding of deformation and potential information. Terrestrial laser scanning (TLS) is a three-dimensional deformation monitoring technique that has gained wide attention in recent years, demonstrating its potential in capturing structural deformation models. In this study, a TLS-based bridge deformation mode monitoring method is proposed, and a deformation mode calculation method combining sliding windows and surface fitting is developed, which is called the SWSF method for short. On the basis of the general characteristics of bridge structures, a deformation error model is established for the SWSF method, with a detailed quantitative analysis of each error component. The analysis results show that the deformation monitoring error of the SWSF method consists of four parts, which are related to the selection of the fitting function, the density of point clouds, the noise of point clouds, and the registration accuracy of point clouds. The error caused by point cloud noise is the main error component. Under the condition that the noise level of point clouds is determined, the calculation error of the SWSF method can be significantly reduced by increasing the number of points of point clouds in the sliding window. Then, deformation testing experiments were conducted under different measurement distances, proving that the proposed SWSF method can achieve a deformation monitoring accuracy of up to 0.1 mm. Finally, the proposed deformation mode monitoring method based on TLS and SWSF was tested on a railway bridge with a span of 65 m. The test results showed that in comparison with the commonly used total station method, the proposed method does not require any preset reflective markers, thereby improving the deformation monitoring accuracy from millimeter level to submillimeter level and transforming the discrete measurement point data form into spatially continuous deformation modes. Overall, this study introduces a new method for accurate deformation monitoring of bridges, demonstrating the significant potential for its application in health monitoring and damage diagnosis of bridge structures.

A Point Cloud Registration Algorithm Based on Weighting Strategy for 3D Indoor Spaces

Point cloud registration is a technology that aligns point cloud data from different viewpoints by computing coordinate transformations to integrate them into a specified coordinate system. Many cutting-edge fields, including autonomous driving, industrial automation, and augmented reality, require the registration of point cloud data generated by millimeter-wave radar for map reconstruction and path planning in 3D environments. This paper proposes a novel point cloud registration algorithm based on a weighting strategy to enhance the accuracy and efficiency of point cloud registration in 3D environments. This method combines a statistical weighting strategy with a point cloud registration algorithm, which can improve registration accuracy while also increasing computational efficiency. First, in 3D indoor spaces, we apply PointNet to the semantic segmentation of the point cloud. We then propose an objective weighting strategy to assign different weights to the segmented parts of the point cloud. The Iterative Closest Point (ICP) algorithm uses these weights as reference values to register the entire 3D indoor space’s point cloud. We also show a new way to perform nonlinear calculations that yield exact closed-form answers for the ICP algorithm in generalized 3D measurements. We test the proposed algorithm’s accuracy and efficiency by registering point clouds on public datasets of 3D indoor spaces. The results show that it works better in both qualitative and quantitative assessments.

The Application Characteristics and Creation of Digital Sculpture Based on Parameter Model

Recently, digital sculpture based on parametric models has emerged both domestically and internationally. To improve the accuracy and efficiency of constructing digital sculpture parameter models, this study proposes a method for constructing digital sculpture parameter models based on improved point cloud registration algorithms by iterating the nearest point algorithm and multi-scale matrix descriptors to increase the iteration efficiency and accuracy of point cloud registration algorithms. The results show that under the Bunny model, the number of three scale feature points is 2146, and the coarse registration error is 0.925 * 10-6 m; As the noise increases, the efficiency of the algorithm proposed in the study increases by an average of 10.1%. The average relative rotation error is reduced by 1-2 orders of magnitude, and the registration time is shortened by 62.7% on average. For a 30dB noise point cloud, it is reduced by one order of magnitude, and as the noise increases, the efficiency of the algorithm proposed in the study increases by an average of 10.1%. In the Dragon model, the number of three scale feature points is 2235, the coarse registration time is only 26 seconds, and the registration error is 0.285 * 10-5m; The average relative rotation error is reduced by 1-2 orders of magnitude, and the registration time is shortened by 62.7% on average. The digital sculpture creation method on the ground of parameter models proposed in this study has improved the registration accuracy and efficiency of parameter models.

RCFI-Net: A reliable correspondences evaluation and feature interaction network for fast and accurate point cloud registration

3D point cloud registration is a crucial task in computer vision, robotics, and safeguarding cultural artifacts in the digital realm. However, maintaining a balance between efficiency and accuracy during the 3D point cloud registration process continues to be a challenge. To solve this issue, a Reliable Correspondences Evaluation and Feature Interaction Network called RCFI-Net has been proposed for fast and precise registration. Our model use a two-stage approach to improve registration efficiency. In the first stage, a Transformer with position encoding network is employed to reinforce point features. Overlapping masks are learned based on the attention mechanism to identify overlapping areas, followed by the sampling of interest points that have high scores in these areas to accelerate registration. In the second stage, non-distinguishing points are eliminated, and a triangulated descriptor is introduced to further differentiate inliers and outliers and find reliable correspondences. Our proposed method has been evaluated on both public datasets and real Terracotta Warriors data, with results showing that it outperforms traditional and feature-learning methods in terms of accuracy, efficiency, and robustness.

3D-visualization of segmented contacts of directional deep brain stimulation electrodes via registration and fusion of CT and FDCT

Objectives3D-visualization of the segmented contacts of directional deep brain stimulation (DBS) electrodes is desirable since knowledge about the position of every segmented contact could shorten the timespan for electrode programming. CT cannot yield images fitting that purpose whereas highly resolved flat detector computed tomography (FDCT) can accurately image the inner structure of the electrode. This study aims to demonstrate the applicability of image fusion of highly resolved FDCT and CT to produce highly resolved images that preserve anatomical context for subsequent fusion to preoperative MRI for eventually displaying segmented contactswithin anatomical context in future studies.Material and methodsRetrospectively collected datasets from 15 patients who underwent bilateral directional DBS electrode implantation were used. Subsequently, after image analysis, a semi-automated 3D-registration of CT and highly resolved FDCT followed by image fusion was performed. The registration accuracy was assessed by computing the target registration error.ResultsOur work demonstrated the feasibility of highly resolved FDCT to visualize segmented electrode contacts in 3D. Semiautomatic image registration to CT was successfully implemented in all cases. Qualitative evaluation by two experts revealed good alignment regarding intracranial osseous structures. Additionally, the average for the mean of the target registration error over all patients, based on the assessments of two raters, was computed to be 4.16 mm.ConclusionOur work demonstrated the applicability of image fusion of highly resolved FDCT to CT for a potential workflow regarding subsequent fusion to MRI in the future to put the electrodes in an anatomical context.

RDLR: A Robust Deep Learning-Based Image Registration Method for Pediatric Retinal Images.

Retinal diseases stand as a primary cause of childhood blindness. Analyzing the progression of these diseases requires close attention to lesion morphology and spatial information. Standard image registration methods fail to accurately reconstruct pediatric fundus images containing significant distortion and blurring. To address this challenge, we proposed a robust deep learning-based image registration method (RDLR). The method consisted of two modules: registration module (RM) and panoramic view module (PVM). RM effectively integrated global and local feature information and learned prior information related to the orientation of images. PVM was capable of reconstructing spatial information in panoramic images. Furthermore, as the registration model was trained on over 280,000 pediatric fundus images, we introduced a registration annotation automatic generation process coupled with a quality control module to ensure the reliability of training data. We compared the performance of RDLR to the other methods, including conventional registration pipeline (CRP), voxel morph (WM), generalizable image matcher (GIM), and self-supervised techniques (SS). RDLR achieved significantly higher registration accuracy (average Dice score of 0.948) than the other methods (ranging from 0.491 to 0.802). The resulting panoramic retinal maps reconstructed by RDLR also demonstrated substantially higher fidelity (average Dice score of 0.960) compared to the other methods (ranging from 0.720 to 0.783). Overall, the proposed method addressed key challenges in pediatric retinal imaging, providing an effective solution to enhance disease diagnosis. Our source code is available at https://github.com/wuwusky/RobustDeepLeraningRegistration .

Research on Detection Technology of Micro- Components on Circuit Board Based on Digital Image Processing

Aiming at the stability of the circuit board image in the acquisition process, this paper realizes the accurate registration of the image to be registered and the standard image based on the SIFT feature operator and RANSAC algorithm. The device detection model and data set are established based on Faster RCNN. Finally, the number of training was continuously optimized, and when the loss function of Faster RCNN converged, the identification result of the device was obtained.

Coherent point drift with Skewed Distribution for accurate point cloud registration

Point cloud registration methods based on Gaussian Mixture Models (GMMs) exhibit high robustness. However, GMM cannot precisely depict point clouds, because the Gaussian distribution is spatially symmetric and local surfaces of point clouds are typically non-symmetric. In this paper, we propose a novel method for rigid point cloud registration, termed coherent point drift with Skewed Distribution (Skewed CPD). Our method employs an asymmetric distribution constructed from the local surface normals and curvature radii. Compared to the Gaussian distribution, this skewed distribution provides a more accurate spatial description of points on local surfaces. Additionally, we integrate an adaptive multiplier to the covariance, which reallocates the weight of the covariance for different components in the probabilistic mixture model. We employ the EM algorithm to address this maximum likelihood estimation (MLE) issue and leverage GPU acceleration. In the M-step, we adopt an unconstrained optimization technique rooted in a Lie group and Lie algebra to attain the optimal transformation. Experimental results indicate that our method outperforms state-of-the-art methods in both accuracy and robustness. Remarkably, even without loop closure detection, the cumulative error of our approach remains minimal.

Automated Registration of Full Moon Remote Sensing Images Based on Triangulated Network Constraints

Abstract. The registration of full-moon remote sensing images constitutes a pivotal stage in the fusion analysis of multiple lunar remote sensing datasets. Addressing prevailing issues in automatic registration, such as the broad width of full-moon data, significant internal distortion, and texture distortion in high-latitude regions, this paper proposes a method for automatic matching and correction based on triangulation constraints. The approach employs a matching strategy progressing from coarse to fine and from sparse to dense. It optimizes and combines multiple existing matching algorithms, enhances the extraction of initial network points, constructs irregular triangulation networks using these points, conducts dense matching with each triangulation network as a basic unit, and introduces a geometric correction method based on triangulation network + grid (TIN + GRID) for the registration of full-moon data. For the matching of full-moon remote sensing images in high-latitude regions, a novel approach involving memory projection forward transformation-matching-projection inverse transformation is adopted. Through registration experiments with full-moon image data and an analysis of registration accuracy at different latitudes, the average mean square error is found to be less than 2 pixels. These results signify the efficacy of the proposed method in effectively addressing the automatic registration challenges encountered in full-moon remote sensing images.

Rigid point cloud registration based on correspondence cloud for image-to-patient registration in image-guided surgery.

Image-to-patient registration aligns preoperative images to intra-operative anatomical structures and it is a critical step in image-guided surgery (IGS). The accuracy and speed of this step significantly influence the performance of IGS systems. Rigid registration based on paired points has been widely used in IGS, but studies have shown its limitations in terms of cost, accuracy, and registration time. Therefore, rigid registration of point clouds representing the human anatomical surfaces has become an alternative way for image-to-patient registration in the IGSsystems. We propose a novel correspondence-based rigid point cloud registration method that can achieve global registration without the need for pose initialization. The proposed method is less sensitive to outliers compared to the widely used RANSAC-based registration methods and it achieves high accuracy at a high speed, which is particularly suitable for the image-to-patient registration inIGS. We use the rotation axis and angle to represent the rigid spatial transformation between two coordinate systems. Given a set of correspondences between two point clouds in two coordinate systems, we first construct a 3D correspondence cloud (CC) from the inlier correspondences and prove that the CC distributes on a plane, whose normal is the rotation axis between the two point clouds. Thus, the rotation axis can be estimated by fitting the CP. Then, we further show that when projecting the normals of a pair of corresponding points onto the CP, the angle between the projected normal pairs is equal to the rotation angle. Therefore, the rotation angle can be estimated from the angle histogram. Besides, this two-stage estimation also produces a high-quality correspondence subset with high inlier rate. With the estimated rotation axis, rotation angle, and the correspondence subset, the spatial transformation can be computed directly, or be estimated using RANSAC in a fast and robust way within only 100iterations. To validate the performance of the proposed registration method, we conducted experiments on the CT-Skull dataset. We first conducted a simulation experiment by controlling the initial inlier rate of the correspondence set, and the results showed that the proposed method can effectively obtain a correspondence subset with much higher inlier rate. We then compared our method with traditional approaches such as ICP, Go-ICP, and RANSAC, as well as recently proposed methods like TEASER, SC2-PCR, and MAC. Our method outperformed all traditional methods in terms of registration accuracy and speed. While achieving a registration accuracy comparable to the recently proposed methods, our method demonstrated superior speed, being almost three times faster thanTEASER. Experiments on the CT-Skull dataset demonstrate that the proposed method can effectively obtain a high-quality correspondence subset with high inlier rate, and a tiny RANSAC with 100 iterations is sufficient to estimate the optimal transformation for point cloud registration. Our method achieves higher registration accuracy and faster speed than existing widely used methods, demonstrating great potential for the image-to-patient registration, where a rigid spatial transformation is needed to align preoperative images to intra-operative patientanatomy.

Accuracy of manual and artificial intelligence-based superimposition of cone-beam computed tomography with digital scan data, utilizing an implant planning software: A randomized clinical study.

To investigate the accuracy of conventional and automatic artificial intelligence (AI)-based registration of cone-beam computed tomography (CBCT) with intraoral scans and to evaluate the impact of user's experience, restoration artifact, number of missing teeth, and free-ended edentulous area. Three initial registrations were performed for each of the 150 randomly selected patients, in an implant planning software: one from an experienced user, one from an inexperienced operator, and one from a randomly selected post-graduate student of implant dentistry. Six more registrations were performed for each dataset by the experienced clinician: implementing a manual or an automatic refinement, selecting 3 small or 3 large in-diameter surface areas and using multiple small or multiple large in-diameter surface areas. Finally, an automatic AI-driven registration was performed, using the AI tools that were integrated into the utilized implant planning software. The accuracy between each type of registration was measured using linear measurements between anatomical landmarks in metrology software. Fully automatic-based AI registration was not significantly different from the conventional methods tested for patients without restorations. In the presence of multiple restoration artifacts, user's experience was important for an accurate registration. Registrations' accuracy was affected by the number of free-ended edentulous areas, but not by the absolute number of missing teeth (p < .0083). In the absence of imaging artifacts, automated AI-based registration of CBCT data and model scan data can be as accurate as conventional superimposition methods. The number and size of selected superimposition areas should be individually chosen depending on each clinical situation.

Accurate Calculation of Tree Stem Traits in Forests Using Localized Multi-View Registration

Abstract. In recent years, there has been a high demand in forestry and forest research for the accurate measurement of tree traits from point clouds captured by terrestrial laser scanners. However, the reliability of the calculated values is not sufficient due to the difficulty of accurate registration of each tree over a large area of forest. To solve this problem, we introduce localized multi-view registration for correcting the registration matrix of each tree stem. In addition, we discuss methods for registering the whole point clouds of a forest by using the registration matrices locally calculated for tree stems. Especially, we discuss a method to align tree stem points that do not have sufficient overlapping points required in registration. The proposed method was applied to actual forest point clouds and diameter at breast height (DBH) was compared to the manually measured DBH. Experimental results showed that the proposed method was effective in reducing registration errors and in calculating tree stem traits with high accuracy.