Automatic Registration Research Articles

Improving the registration stability of cone-beam computed tomography with the Sphere-Mask Optical Positioning System: a feasibility study.

Cone-beam computed tomography (CBCT) is an important tool for patient positioning in radiotherapy due to its outstanding advantages. However, the CBCT registration shows errors due to the limitations of the automatic registration algorithm and the nonuniqueness of manual verification results. The purpose of this study was to verify the feasibility of using the Sphere-Mask Optical Positioning System (S-M_OPS) to improve the registration stability of CBCT through clinical trials. From November 2021 to February 2022, 28 patients who received intensity-modulated radiotherapy and site verification with CBCT were included in this study. S-M_OPS was used as an independent third-party system to supervise the CBCT registration result in real time. The supervision error was calculated based on the CBCT registration result and using the S-M_OPS registration result as the standard. For the head and neck, patients with a supervision error ≥3 or ≤-3 mm in 1 direction were selected. For the thorax, abdomen, pelvis, or other body parts, patients with a supervision error ≥5 or ≤-5 mm in 1 direction were selected. Then, re-registration was performed for all patients (selected and unselected). The registration errors of CBCT and S-M_OPS were calculated based on the re-registration results as the standard. For selected patients with large supervision errors, CBCT registration errors (mean ± standard deviation) in the latitudinal (LAT; left/right), vertical (VRT; superior/inferior), and longitudinal (LNG; anterior/posterior) directions were 0.90±3.20, -1.70±0.98, and 7.30±2.14 mm, respectively. The S-M_OPS registration errors were 0.40±0.14, 0.32±0.66, and 0.24±1.12 mm in the LAT, VRT, and LNG directions, respectively. For all patients, CBCT registration errors in the LAT, VRT, and LNG directions were 0.39±2.69, -0.82±1.47, and 2.39±2.93 mm, respectively. The S-M_OPS registration errors were -0.25±1.33, 0.55±1.27, and 0.36±1.34 mm for all patients in the LAT, VRT, and LNG directions, respectively. This study shows that S-M_OPS registration offers comparable accuracy to CBCT for daily registration. S-M_OPS, as an independent third-party tool, can prevent large errors in CBCT registration, thereby improving the accuracy and stability of CBCT registration.

In situ guidance for MRI interventions using projected feedback.

To develop and evaluate an augmented reality instrument guidance system for MRI-guided needle placement procedures such as musculoskeletal biopsy and arthrography. Our system guides the physician to insert a needle toward a target while looking at the insertion site without requiring special headgear. The system is comprised of a pair of stereo cameras, a projector, and a computational unit with a touch screen. All components are designed to be used within the MRI suite (Zone 4). Multi-modality fiducial markers called VisiMARKERs, detectable in both MRI and camera images, facilitate automatic registration after the initial scan. The navigation feedback is projected directly onto the intervention site allowing the interventionalist to keep their focus on the insertion site instead of a secondary monitor which is often not in front of them. We evaluated the feasibility and accuracy of this system on custom-built shoulder phantoms. Two radiologists used the system to select targets and entry points on initial MRIs of these phantoms over three sessions. They performed 80 needle insertions following the projected guidance. The system targeting error was 1.09mm, and the overall error was 2.29mm. We demonstrated both feasibility and accuracy of this MRI navigation system. The system operated without any problems inside the MRI suite close to the MRI bore. The two radiologists were able to easily follow the guidance and place the needle close to the target without any intermediate imaging.

Validation of a surgical navigation system for hypertensive intracerebral hemorrhage based on mixed reality using an automatic registration method

Validation of a surgical navigation system for hypertensive intracerebral hemorrhage based on mixed reality using an automatic registration method

A robust and automatic CT-3D ultrasound registration method based on segmentation, context, and edge hybrid metric.

The fusion of computed tomography (CT) and ultrasound (US) image can enhance lesion detection ability and improve the success rate of liver interventional radiology. The image-based fusion methods encounter the challenge of registration initialization due to the random scanning pose and limited field of view of US. Existing automatic methods those used vessel geometric information and intensity-based metric are sensitive to parameters and have low success rate. The learning-based methods require a large number of registered datasets for training. The aim of this study is to provide a fully automatic and robust US-3D CT registration method without registered training data and user-specified parameters assisted by the revolutionary deep learning-based segmentation, which can further be used for preparing training samples for the study of learning-basedmethods. We propose a fully automatic CT-3D US registration method by two improved registration metrics. We propose to use 3D U-Net-based multi-organ segmentation of US and CT to assist the conventional registration. The rigid transform is searched in the space of any paired vessel bifurcation planes where the best transform is decided by a segmentation overlap metric, which is more related to the segmentation precision than Dice coefficient. In nonrigid registration phase, we propose a hybrid context and edge based image similarity metric with a simple mask that can remove most noisy US voxels to guide the B-spline transform registration. We evaluate our method on 42 paired CT-3D US datasets scanned with two different US devices from two hospitals. We compared our methods with other exsiting methods with both quantitative measures of target registration error (TRE) and the Jacobian determinent with paired t-test and qualitative registration imagingresults. The results show that our method achieves fully automatic rigid registration TRE of 4.895 mm, deformable registration TRE of 2.995 mm in average, which outperforms state-of-the-art automatic linear methods and nonlinear registration metrics with paired t-test's p value less than 0.05. The proposed overlap metric achieves better results than self similarity description (SSD), edge matching (EM), and block matching (BM) with p values of 1.624E-10, 4.235E-9, and 0.002, respectively. The proposed hybrid edge and context-based metric outperforms context-only, edge-only, and intensity statistics-only-based metrics with p values of 0.023, 3.81E-5, and 1.38E-15, respectively. The 3D US segmentation has achieved mean Dice similarity coefficient (DSC) of 0.799, 0.724, 0.788, and precision of 0.871, 0.769, 0.862 for gallbladder, vessel, and branch vessel,respectively. The deep learning-based US segmentation can achieve satisfied result to assist robust conventional rigid registration. The Dice similarity coefficient-based metrics, hybrid context, and edge image similarity metric contribute to robust and accurateregistration.

360 Assessment of Pedicle Screw Placement Accuracy Utilizing a Novel Augmented Reality and Artificial Intelligence Surgical Guidance System

INTRODUCTION: The integration of artificial intelligence (AI) and augmented reality (AR) technologies in spine navigation has the potential to minimize pedicle screw misplacement, decrease radiation exposure, and improve procedural efficiency, addressing some of the challenges associated with spinal instrumentation. METHODS: Sixty lumbosacral pedicle screws were placed by 4 Orthopedics surgeons in 6 cadavers using the AR/AI surgical navigation system. Two CT intraoperative scans (before and after screw placement) of the cadaveric specimens were obtained for the study to measure the 3D positional and angular discrepancies between virtual and real screws. The validation procedure consisted of 3 steps: (1) automatic registration and 3D coordinate transformation, where the preop CT scan was aligned with the postop scan to determine the virtual screw 3D positions and orientations in postop scan; (2) analysis of the postop scan to determine the real screw 3D positions and orientations as they appeared in the scan volume; (3) automatic comparison between the 3D positions and orientations of the virtual and real screws. RESULTS: A one-sample t-test statistical analysis yielded a mean positional error of 2.16 mm ± 1.00 mm (99% CI: 1.81-2.49 mm), and a mean angular error of 1.49± 0.73° (99% CI: 1.25-1.74°). These results were independent of anatomical level, side, and surgeon. CONCLUSIONS: This study indicates that this AR/AI surgical guidance system provides mean positional and angular errors lower than 3.0 mm and 3.0° respectively, thus complying with FDA-required regulatory acceptance criteria. The system was FDA-cleared as a US 510k Orthopedic Stereotaxic Instrument.

P‐2.21: Research on multi‐lidar detection technology for autonomous driving

Nowadays autonomous driving has become a hot topic, many people pay attention to the field. Target detection through sensors is the basis of autonomous driving and plays an important role in high-level autonomous driving. The effective environmental information obtained by using a single sensor is less, and the visual sensor is easily affected by the weather and the algorithm is complex, so there are problems in real-time detection and accuracy. Multi-lidar detection is also a popular research in this field and has important research value and application prospect.This paper mainly describes the key steps of multi-lidar detection and proposes a fully automatic point cloud registration scheme. The fully automatic calibration method does not require manual initialization and does not rely on additional sensors at all, which can play a good role in multi-lidar detection. After that, the fused point cloud data is filtered to remove interference points and reduce the number of point clouds. In view of the under-segmentation of ground point cloud, the point cloud is mapped to the raster graph, and the ground point and non-ground point are separated by Random sample consensus algorithm and least square method. Then, distance-based clustering is used for obstacle detection on non-ground points.

Political Communication: Uncovering Knowledge, Attitudes and Young Voters’ Readiness for PRU-15 in Batang Padang District, Perak

Malaysia made history when the Dewan Rakyat approved an amendment to the Federal Constitution that lowered the voting age from 21 to 18 years old. The country’s democratic system was colored by the automatic registration of those who turned 18 as voters for the 15th Malaysian General Election (GE-15). This amendment aims to democratize the political process in this nation and promote mature, fair, and equitable elections. This ongoing study aims to discover young voters' knowledge, attitudes, and readiness toward the 15th general election (PRU-15) in Batang Padang, Perak district. Methodologically, a quantitative approach was used where 462 youth participants completed questionnaires. The findings discovered that although attitudes and readiness among young voters in the research population are at a moderate level, they have a high level of knowledge. The result also uncovered five key factors that influence young voters’ readiness towards making their decisions for PRU-15 namely voting is my responsibility, the good reputation of elected representatives, peer influence, the implementation of the Undi-18 policy by the government and family support. The study thus contributed to a new landscape of political communication through young voters’ contribution not only to casting the ballot during the election but also to participating in the country’s leadership as members of parliament. Keywords: Political communication, Undi-18, PRU-15, knowledge, young voters.

IDCF: information distribution composite feature for multi-modal image registration

ABSTRACT Automatic registration of multi-modal remote sensing data is a challenging task. Due to the significant nonlinear radiation difference and noise between multi-mode images, the register points extracted by traditional gradient algorithms (such as SIFT) have low repetition rate and poor feature similarity, which makes it difficult to register multi-mode images. To solve these problems, this paper proposes a method which is called Multi-modal Image Matching Based on Information Distribution Composite Feature (IDCF). Firstly, an adaptive information entropy map (AIEM) is proposed. AIEM not only describes the information distribution characteristics of the image, but also the distribution of the contour features of the image. Compared with traditional contour feature extraction operators, AIEM extraction results are clearer, more comprehensive and more detailed. In addition, AIEM is more robust to NRD compared to gradient, which is greatly affected by NRD. Then, IDCF extracts corner points on AIEM as feature points because corner points have better repeatability. After that, a composite feature description model based on maximum information index map (MIIM) and information trend graph (ITM) is defined. MIIM describes the main change direction of image information and ITM describes the overall change trend of image information. Finally, the similarity criterion SAD is used to match the feature points. The proposed IDCF aims to capture the structural similarity between images and has been tested with a variety of optical, Lidar, SAR, and map data. The results show that IDCF is robust against complex NRD outperforms the advanced algorithms (i.e. RIFT, PSO-SIFT and OS-SIFT) in matching performance.

Automatic registration of dental CT and 3D scanned model using deep split jaw and surface curvature

Background and objectives: In the medical field, various image registration applications have been studied. In dentistry, the registration of computed tomography (CT) volume data and 3D optically scanned models is essential for various clinical applications, including orthognathic surgery, implant surgical planning, and augmented reality. Our purpose was to present a fully automatic registration method of dental CT data and 3D scanned models.Methods: We use a 2D convolutional neural network to regress a curve splitting the maxilla (i.e., upper jaw) and mandible (i.e., lower jaw) and the points specifying the front and back ends of the crown from the CT data. Using this regressed information, we extract the point cloud and vertices corresponding to the tooth crown from the CT and scanned data, respectively. We introduce a novel metric, called curvature variance of neighbor (CVN), to discriminate between highly fluctuating and smoothly varying regions of the tooth crown. The registration based on CVN enables more accurate fine registration while reducing the effects of metal artifacts. Moreover, the proposed method does not require any preprocessing such as extracting the iso-surface for the tooth crown from the CT data, thereby significantly reducing the computation time.Results: We evaluated the proposed method with the comparison to several promising registration techniques. Our experimental results using three datasets demonstrated that the proposed method exhibited higher registration accuracy (i.e., 2.85, 1.92, and 7.73 times smaller distance errors for individual datasets) and smaller computation time (i.e., 4.12 times faster registration) than one of the state-of-the-art methods. Moreover, the proposed method worked considerably well for partially scanned data, whereas other methods suffered from the unbalancing of information between the CT and scanned data.Conclusions: The proposed method was able to perform fully automatic and highly accurate registration of dental CT data and 3D scanned models, even with severe metal artifacts. In addition, it could achieve fast registration because it did not require any preprocessing for iso-surface reconstruction from the CT data.

Clinical impact of artificial intelligence-based solutions on imaging of the pancreas and liver.

Artificial intelligence (AI) has experienced substantial progress over the last ten years in many fields of application, including healthcare. In hepatology and pancreatology, major attention to date has been paid to its application to the assisted or even automated interpretation of radiological images, where AI can generate accurate and reproducible imaging diagnosis, reducing the physicians' workload. AI can provide automatic or semi-automatic segmentation and registration of the liver and pancreatic glands and lesions. Furthermore, using radiomics, AI can introduce new quantitative information which is not visible to the human eye to radiological reports. AI has been applied in the detection and characterization of focal lesions and diffuse diseases of the liver and pancreas, such as neoplasms, chronic hepatic disease, or acute or chronic pancreatitis, among others. These solutions have been applied to different imaging techniques commonly used to diagnose liver and pancreatic diseases, such as ultrasound, endoscopic ultrasonography, computerized tomography (CT), magnetic resonance imaging, and positron emission tomography/CT. However, AI is also applied in this context to many other relevant steps involved in a comprehensive clinical scenario to manage a gastroenterological patient. AI can also be applied to choose the most convenient test prescription, to improve image quality or accelerate its acquisition, and to predict patient prognosis and treatment response. In this review, we summarize the current evidence on the application of AI to hepatic and pancreatic radiology, not only in regard to the interpretation of images, but also to all the steps involved in the radiological workflow in a broader sense. Lastly, we discuss the challenges and future directions of the clinical application of AI methods.

Happy birthday: you get to vote!

AbstractThis paper estimates the effect of automatic voter registration (AVR) on voter turnout in California and Oregon. AVR systems register to vote all eligible individuals who transact with proscribed government agencies, most commonly the Department of Motor Vehicles (DMVs). The article isolates one part of the causal impact of AVR on turnout by taking advantage of a temporal feature of license renewals. Many individuals interact with the DMV periodically due to the need to renew drivers' licenses. Because licenses in both California and Oregon expire on birthdays, an individual's birth date can be treated as an exogenous variable discriminating between some individuals who are registered to vote in time for the election, while others are not. Our instrumental variable analysis compares registration and voting rates for individuals with birth dates prior and subsequent to the voter registration deadline. After calculating a causal effect of AVR on turnout at the individual level, we extrapolate this AVR “birthday” effect to overall voter turnout for these states.

Influence of surgical position and registration methods on clinical accuracy of navigation systems in brain tumor surgery

The aim of this study was to evaluate the influence of skin distortion due to surgical positioning on the clinical accuracy of the navigation system. The distance errors were measured in four fiducial markers (anterior, posterior, right, and left of the head) after the registration of the navigation system. The distance errors were compared between the surface-merge registration (SMR) method using preoperative imaging and the automatic intraoperative registration (AIR) method using intraoperative imaging. The comparison of the distance errors were performed in various surgical positions. The AIR method had the significant accuracy in the lateral markers than the SMR method (lateral position, 3.8 mm vs. 8.95 mm; p < 0.0001; prone position, 4.5 mm vs. 13.9 mm; p = 0.0001; 5.2 mm vs. 11.5 mm; p = 0.0070). The smallest distance errors were obtained close to the surgical field in the AIR method (3.25–3.85 mm) and in the forehead in the SMR method (3.3–8.1 mm). The AIR method was accurate and recommended for all the surgical positions if intraoperative imaging was available. The SMR method was only recommended for the supine position, because skin distortion was frequently observed in the lateral region.

Accuracy of automatic and manual dynamic navigation registration techniques for dental implant surgery in posterior sites missing a single tooth: A retrospective clinical analysis.

To assess the relative accuracy of manual (U-shaped tube) and automatic (two-in-one) dynamic navigation registration techniques for implant surgery performed in posterior sites missing one tooth. This study included 58 partially edentulous patients with 58 implants, including 31 and 27 in the manual and automatic groups. Deviations between the planned and actual implant placement were assessed. The angular deviation in the overall study cohort was 2.54 ± 1.21°, while the 3D deviations at the implant platform and apex were 0.90 ± 0.46 mm and 1.04 ± 0.47 mm, respectively. The respective angular deviations in the manual and automatic groups were 2.82 ± 1.17° and 2.21 ± 1.19° (p > .05), while platform deviations were 0.89 ± 0.48 mm and 0.91 ± 0.45 mm (p > .05), and apex deviations were 0.99 ± 0.48 mm and 1.11 ± 0.46 mm (p > .05). No significant differences in absolute buccolingual, mesiodistal, or apicocoronal deviations were detected between these groups at either level (p > .05) nor were did deviation distributions differ in the buccolingual, mesiodistal, or apicocoronal directions at the platform or apex levels (p > .05). Manual and automatic dynamic navigation registration techniques can achieve excellent accuracy when placing implants in posterior sites missing a single tooth. The two-in-one automatic registration technique can reduce the amount of time and intraoperative steps necessary to complete the registration process relative to the manual U-shaped tube registration technique. Further follow-up studies are necessary to expand on these results.

The partisan costs of automatic voter registration

The partisan costs of automatic voter registration

The Feasibility of Electromagnetic Navigation Technique to Achieve Preoperative Plan in Mandibular Angle Osteotomy

In contrast to the most commonly used optical navigation system, electromagnetic navigation has huge potential in operations with a narrow field. The purpose of this experiment was to test and confirm whether the electromagnetic navigation method the authors developed for mandibular angle osteotomy (MAO) met clinical requirements. Using a dental splint that could be repeatedly mounted on teeth, registration between surgical plan and actual field was performed automatically. Navigation of MAO was first performed on 10 mandibular models. The position precision measured using a coordinate measuring machine was 1.30±0.61 mm. Then, a navigation experiment was performed on 4 patients. Accuracy in actual operation measured by the NDI pointing sensor was 1.89±0.76 mm. Our noninvasive automatic registration process reduced the surgical exposure time and eliminated the bias of the manual selection of registration points. This preliminary study confirmed the feasibility of the electromagnetic navigation technique in terms of both applicability and accuracy in MAO surgery.

MSIr: Automatic Registration Service for Mass Spectrometry Imaging and Histology.

Mass spectrometry imaging (MSI) is a powerful tool that can be used to simultaneously investigate the spatial distribution of different molecules in samples. However, it is difficult to comprehensively analyze complex biological systems with only a single analytical technique due to different analytical properties and application limitations. Therefore, many analytical methods have been combined to extend data interpretation, evaluate data credibility, and facilitate data mining to explore important temporal and spatial relationships in biological systems. Image registration is an initial and critical step for multimodal imaging data fusion. However, the image registration of multimodal images is not a simple task. The property difference between each data modality may include spatial resolution, image characteristics, or both. The image registrations between MSI and different imaging techniques are often achieved indirectly through histology. Many methods exist for image registration between MSI data and histological images. However, most of them are manual or semiautomatic and have their prerequisites. Here, we built MSI Registrar (MSIr), a web service for automatic registration between MSI and histology. It can help to reduce subjectivity and processing time efficiently. MSIr provides an interface for manually selecting region of interests from histological images; the user selects regions of interest to extract the corresponding spectrum indices in MSI data. In the performance evaluation, MSIr can quickly map MSI data to histological images and help pinpoint molecular components at specific locations in tissues. Most registrations were adequate and were without excessive shifts. MSIr is freely available at https://msir.cmdm.tw and https://github.com/CMDM-Lab/MSIr.

A survey of feature detection methods for localisation of plain sections of axial brain magnetic resonance imaging

Matching MRI brain images between patients or mapping patients’ MRI slices to the simulated atlas of a brain is key to the automatic registration of MRI of a brain. The ability to match MRI images would also enable such applications as indexing and searching MRI images among multiple patients or selecting images from the region of interest. In this work, we have introduced robustness, accuracy and cumulative distance metrics and methodology that allows us to compare different techniques and approaches in matching brain MRI of different patients or matching MRI brain slice to a position in the brain atlas. To that end, we have used feature detection methods AGAST, AKAZE, BRISK, GFTT, HardNet, and ORB, which are established methods in image processing, and compared them on their resistance to image degradation and their ability to match the same brain MRI slice of different patients. We have demonstrated that some of these techniques can correctly match most of the brain MRI slices of different patients. When matching is performed with the atlas of the human brain, their performance is significantly lower. The best performing feature detection method was a combination of SIFT detector and HardNet descriptor that achieved 93% accuracy in matching images with other patients and only 52% accurately matched images when compared to atlas.

Automatic Registration of Homogeneous and Cross-Source TomoSAR Point Clouds in Urban Areas.

Building reconstruction using high-resolution satellite-based synthetic SAR tomography (TomoSAR) is of great importance in urban planning and city modeling applications. However, since the imaging mode of SAR is side-by-side, the TomoSAR point cloud of a single orbit cannot achieve a complete observation of buildings. It is difficult for existing methods to extract the same features, as well as to use the overlap rate to achieve the alignment of the homologous TomoSAR point cloud and the cross-source TomoSAR point cloud. Therefore, this paper proposes a robust alignment method for TomoSAR point clouds in urban areas. First, noise points and outlier points are filtered by statistical filtering, and density of projection point (DoPP)-based projection is used to extract TomoSAR building point clouds and obtain the facade points for subsequent calculations based on density clustering. Subsequently, coarse alignment of source and target point clouds was performed using principal component analysis (PCA). Lastly, the rotation and translation coefficients were calculated using the angle of the normal vector of the opposite facade of the building and the distance of the outer end of the facade projection. The experimental results verify the feasibility and robustness of the proposed method. For the homologous TomoSAR point cloud, the experimental results show that the average rotation error of the proposed method was less than 0.1°, and the average translation error was less than 0.25 m. The alignment accuracy of the cross-source TomoSAR point cloud was evaluated for the defined angle and distance, whose values were less than 0.2° and 0.25 m.

Assessment of thoracic spinal curvatures in static postures using spatially tracked 3D ultrasound volumes: a proof-of-concept study

The assessment of spinal posture is a difficult endeavour given the lack of identifiable bony landmarks for placement of skin markers. Moreover, potentially significant soft tissue artefacts along the spine further affect the accuracy of marker-based approaches. The objective of this proof-of-concept study was to develop an experimental framework to assess spinal postures by using three-dimensional (3D) ultrasound (US) imaging. A phantom spine model immersed in water was scanned using 3D US in a neutral and two curved postures mimicking a forward flexion in the sagittal plane while the US probe was localised by three electromagnetic tracking sensors attached to the probe head. The obtained anatomical ‘coarse’ registrations were further refined using an automatic registration algorithm and validated by an experienced sonographer. Spinal landmarks were selected in the US images and validated against magnetic resonance imaging data of the same phantom through image registration. Their position was then related to the location of the tracking sensors identified in the acquired US volumes, enabling the localisation of landmarks in the global coordinate system of the tracking device. Results of this study show that localised 3D US enables US-based anatomical reconstructions comparable to clinical standards and the identification of spinal landmarks in different postures of the spine. The accuracy in sensor identification was 0.49 mm on average while the intra- and inter-observer reliability in sensor identification was strongly correlated with a maximum deviation of 0.8 mm. Mapping of landmarks had a small relative distance error of 0.21 mm (SD = ± 0.16) on average. This study implies that localised 3D US holds the potential for the assessment of full spinal posture by accurately and non-invasively localising vertebrae in space.

Reliability of automatic finish line detection for tooth preparation in dental computer-aided software.

This study aimed to investigate the accuracy of automatic tooth finish line registration compared to manual registration with regard to various finish line configurations and dental computer-aided design (CAD) software. Finish line registrations were performed on 15 digital tooth models with different finish line configurations (edge roundness radius = 0 mm, 0.2 mm, and 0.4 mm; edge angle = 30°, 60°, 90°, 120°, and 150°) using automatic and manual methods for designing virtual copings (N = 150). The discrepancies between the registered finish line extracted from the copings and the actual finish line segmented from the digitized tooth model were measured. Three-way analysis of variance (ANOVA) and post-hoc analyses with Bonferroni correction (α = 0.05) were used to analyze the results. The finish line configurations, registration methods, and CAD software interacted with the accuracy of the registered finish line (p = 0.001). The automatic finish line registration method exhibited larger error values than the manual method, especially at high finish line edge roundness and obtuse edge angles for both EXOCAD and R2CAD software (p < 0.001). The difference in dental CAD software affected the registration accuracy in the automatic method (p < 0.001), but not in the manual method (p = 0.676). Finish line registration errors may occur when the automatic registration method is applied to the indistinct edge of tooth preparation. The accuracy of the automatic finish line registration could differ according to the CAD software program.