Three-dimensional Reconstruction Research Articles

Construction of a nomogram model to predict technical difficulty in performing laparoscopic sphincter-preserving radical resection for rectal cancer

BACKGROUND Colorectal surgeons are well aware that performing surgery for rectal cancer becomes more challenging in obese patients with narrow and deep pelvic cavities. Therefore, it is essential for colorectal surgeons to have a comprehensive understanding of pelvic structure prior to surgery and anticipate potential surgical difficulties. AIM To evaluate predictive parameters for technical challenges encountered during laparoscopic radical sphincter-preserving surgery for rectal cancer. METHODS We retrospectively gathered data from 162 consecutive patients who underwent laparoscopic radical sphincter-preserving surgery for rectal cancer. Three-dimensional reconstruction of pelvic bone and soft tissue parameters was conducted using computed tomography (CT) scans. Operative difficulty was categorized as either high or low, and multivariate logistic regression analysis was employed to identify predictors of operative difficulty, ultimately creating a nomogram. RESULTS Out of 162 patients, 21 (13.0%) were classified in the high surgical difficulty group, while 141 (87.0%) were in the low surgical difficulty group. Multivariate logistic regression analysis showed that the surgical approach using laparoscopic intersphincteric dissection, intraoperative preventive ostomy, and the sacrococcygeal distance were independent risk factors for highly difficult laparoscopic radical sphincter-sparing surgery for rectal cancer (P < 0.05). Conversely, the anterior-posterior diameter of pelvic inlet/sacrococcygeal distance was identified as a protective factor (P < 0.05). A nomogram was subsequently constructed, demonstrating good predictive accuracy (C-index = 0.834). CONCLUSION The surgical approach, intraoperative preventive ostomy, the sacrococcygeal distance, and the anterior-posterior diameter of pelvic inlet/sacrococcygeal distance could help to predict the difficulty of laparoscopic radical sphincter-preserving surgery.

Three-dimensional surface reconstruction from reflectance direction fields with orthogonal multicolor filters

Three-dimensional surface reconstruction from reflectance direction fields with orthogonal multicolor filters

Evaluation of Three-Dimensional Reconstruction Technology in Precision Hepatectomy for Primary Liver Cancer

Abstract Background Primary Liver Cancer has become a potent threat to the world due to its high morbidity and mortality rate. Up till now, Liver transplantation is the most suggested treatment but it is not feasible owing to the unavailability of donors and high cost. Hepatectomy provides an alternative treatment to this deadliest disease. Precision hepatectomy is performed with the aid of traditional 2 dimensional technology and image processing such as CT scan and Magnetic Resonance Imaging. However, it requires extensive expertise and pose challenges to the young doctors in decision making. Modern imaging and computer technology has opened the new avenues in medical field with the advent of 3 dimensional Reconstruction and visualization methods. Material and Methods We conducted a cohort retrospective study. In this study, we tried to evaluate the efficacy an impacts of 3 dimensional reconstruction on the preoperative planning of hepatectomy, intraoperative conditions and postoperative complications. We took 95 patients and divided them in two groups A and B. Group A has 67 patients who underwent hepatectomy before the application of 3 dimensional reconstruction and 28 patients on whom hepatectomy was performed according to the planning and methods of 3dimensional reconstruction and results were evaluated. Results Our study found that 3 dimensional reconstruction can help in better diagnosis, resection planning and reduce the postoperative complication. Results were not significant difference p > 0.05 on the incidence of postoperative complication between group A and B. Results were significant p < 0.05 for the intraoperative blood loss, optimal surgery time and postoperative hospitalization. Conclusion Hence, 3 dimensional reconstruction is a landmark discovery in medical sciences for the accurate evaluation and resection of complex liver cancers.

Three-dimensional reconstruction of transverse hole defect in plate based on TOFD inspection

ABSTRACT In this paper, aluminium plate specimens with circular transverse hole defect was prepared, and the specimen was subjected to ultrasonic non-destructive testing using the TOFD (Time-of-Flight Diffraction) inspection method. Simultaneously, addressing the issue of three-dimensional reconstruction of defect within the field of ultrasonic non-destructive testing, a method combining the least squares approach and volumetric rendering was proposed to process the B-scan images obtained from TOFD inspection. This method was used to reconstruct the three-dimensional shape of transverse hole defect. The result shows that processing defect information acquired through TOFD inspection using the integrated approach of least squares and volumetric rendering leads to clear three-dimensional reconstruction images. This research offers an efficient method for the three-dimensional visualisation of transverse hole defect in plate.

Generalizing the Enhanced-Deep-Super-Resolution neural network to brain MR images: a retrospective study on the Cam-CAN dataset.

The Enhanced-Deep-Super-Resolution (EDSR) model is a state-of-art convolutional neural network suitable for improving image spatial resolution. It was previously trained with general-purpose pictures and then, in this work, tested on biomedical Magnetic Resonance (MR) images, comparing the network outcomes with traditional up-sampling techniques. We explored possible changes in the model response when different MR sequences were analyzed. T1w and T2w MR brain images of 70 human healthy subjects (F:M 40:30) from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) repository were down-sampled and then up-sampled using EDSR model and BiCubic (BC) interpolation. Several reference metrics were used to quantitatively assess the performance of up-sampling operations (RMSE, pSNR, SSIM and HFEN). Two-dimensional and three-dimensional reconstructions were evaluated. Different brain tissues were analyzed individually. The EDSR model was superior to BC interpolation on the selected metrics, both for two- and three- dimensional reconstructions. The reference metrics showed higher quality of EDSR over BC reconstructions for all the analyzed images, with a significant difference of all the criteria in T1w images and of the perception-based SSIM and HFEN in T2w images. The analysis per tissue highlights differences in EDSR performance related to the gray-level values, showing a relative lack of out-performance in reconstructing hyper-intense areas. The EDSR model, trained on general-purpose images, better reconstructs MR T1w and T2w images than BC, without any re-training or fine-tuning. These results highlight the excellent generalization ability of the network and lead to possible applications on other MR measurements.Significance Statement Super resolution applications in biomedical images may help in reducing acquisition scan time and concurrently improving the quality of the exam. Neural networks have been shown to work better than traditional up-sampling techniques, even though ad hoc training experiments need to be performed for specific kind of data. In this work, we used a model previously trained with general-purpose images and we directly applied to magnetic resonance human brain ones; we verified its ability of reconstructing new kind of images, comparing the results with traditional up-sampling techniques. Our analysis highlights the excellent generalization capabilities of the model over the images tested, without need of specific re-training, suggesting that such results might be reproduced on images from other acquisition systems.

Whole-body magnetic resonance imaging at 0.05 Tesla

Despite a half-century of advancements, global magnetic resonance imaging (MRI) accessibility remains limited and uneven, hindering its full potential in health care. Initially, MRI development focused on low fields around 0.05 Tesla, but progress halted after the introduction of the 1.5 Tesla whole-body superconducting scanner in 1983. Using a permanent 0.05 Tesla magnet and deep learning for electromagnetic interference elimination, we developed a whole-body scanner that operates using a standard wall power outlet and without radiofrequency and magnetic shielding. We demonstrated its wide-ranging applicability for imaging various anatomical structures. Furthermore, we developed three-dimensional deep learning reconstruction to boost image quality by harnessing extensive high-field MRI data. These advances pave the way for affordable deep learning–powered ultra-low-field MRI scanners, addressing unmet clinical needs in diverse health care settings worldwide.

Program VUE: analysing distributions of cryo-EM projections using uniform spherical grids

Three-dimensional cryo electron microscopy reconstructions are obtained by extracting information from a large number of projections of the object. These projections correspond to different `views' or `orientations', i.e. directions in which these projections show the reconstructed object. Uneven distribution of these views and the presence of dominating preferred orientations may distort the reconstructed spatial images. This work describes the program VUE (views on uniform grids for cryo electron microscopy), designed to study such distributions. Its algorithms, based on uniform virtual grids on a sphere, allow an easy calculation and accurate quantitative analysis of the frequency distribution of the views. The key computational element is the Lambert azimuthal equal-area projection of a spherical uniform grid onto a disc. This projection keeps the surface area constant and represents the frequency distribution with no visual bias. Since it has multiple tunable parameters, the program is easily adaptable to individual needs, and to the features of a particular project or of the figure to be produced. It can help identify problems related to an uneven distribution of views. Optionally, it can modify the list of projections, distributing the views more uniformly. The program can also be used as a teaching tool.

Triplet Epipolar Images for Spaceborne Three Linear Cameras

Abstract. Epipolar images can reduce conjugate points searching from a two-dimensional to a one-dimensional space, which significantly improves the robustness and efficiency of dense matching. However, two images matched the lack of redundancy and suffered from occlusions. The third image could introduce two more stereos and improve the accuracy and completeness of the three-dimension reconstruction, which were adopted by spaceborne three linear cameras (TLCs), the ALOS PRSIM and ZY-3. In this study, we propose a new triplet epipolar images generation method for spaceborne TLCs. Triplet epipolar images were defined as any two of the three epipolar image pairs. The triplet epipolar geometry requires the imaging rays of any conjugate point to be coplanar. For high-resolution satellite images, parallel projection can be used to approximate the imaging geometry of satellite images. Therefore, a coplanar principal optical axis is a fundamental requirement for spaceborne TLCs. We propose a general workflow to generate triplet epipolar images (TEIs), which includes free-net bundle adjustment of TLCs, building a triplet epipolar geometry, correcting the y-parallaxes, and generating a rational function model (RFM) for TEIs. The ZY3-02 satellite images were used to validate the proposed method. The root means square error (RMSEs) of the free-net bundle adjustment in the image space was 0.185 pixels, which proved the fine intrinsic accuracy. After compensation, the RMSEs of the y parallaxes of the three epipolar image pairs were 0.295, 0.310, and 0.370 pixels. Owing to the simple geometry of the TEIs, the RMSEs of the RFM replacements were within 0.001 pixels.

Bicontinuous RuO2 nanoreactors for acidic water oxidation

Improving activity and stability of Ruthenium (Ru)-based catalysts in acidic environments is eager to replace more expensive Iridium (Ir)-based materials as practical anode catalyst for proton-exchange membrane water electrolyzers (PEMWEs). Here, a bicontinuous nanoreactor composed of multiscale defective RuO2 nanomonomers (MD-RuO2-BN) is conceived and confirmed by three-dimensional tomograph reconstruction technology. The unique bicontinuous nanoreactor structure provides abundant active sites and rapid mass transfer capability through a cavity confinement effect. Besides, existing vacancies and grain boundaries endow MD-RuO2-BN with generous low-coordination Ru atoms and weakened Ru-O interaction, inhibiting the oxidation of lattice oxygen and dissolution of high-valence Ru. Consequently, in acidic media, the electron- and micro-structure synchronously optimized MD-RuO2-BN achieves hyper water oxidation activity (196 mV @ 10 mA cm−2) and an ultralow degradation rate of 1.2 mV h−1. A homemade PEMWE using MD-RuO2-BN as anode also conveys high water splitting performance (1.64 V @ 1 A cm−2). Theoretical calculations and in-situ Raman spectra further unveil the electronic structure of MD-RuO2-BN and the mechanism of water oxidation processes, rationalizing the enhanced performance by the synergistic effect of multiscale defects and protected active Ru sites.

STORM Super-Resolution Visualization of Self-Assembled γPFD Chaperone Ultrastructures in Methanocaldococcus jannaschii.

Gamma-prefoldin (γPFD), a unique chaperone found in the extremely thermophilic methanogen Methanocaldococcus jannaschii, self-assembles into filaments in vitro, which so far have been observed using transmission electron microscopy and cryo-electron microscopy. Utilizing three-dimensional stochastic optical reconstruction microscopy (3D-STORM), here we achieve ∼20 nm resolution by precisely locating individual fluorescent molecules, hence resolving γPFD ultrastructure both in vitro and in vivo. Through CF647 NHS ester labeling, we first demonstrate the accurate visualization of filaments and bundles with purified γPFD. Next, by implementing immunofluorescence labeling after creating a 3xFLAG-tagged γPFD strain, we successfully visualize γPFD in M. jannaschii cells. Through 3D-STORM and two-color STORM imaging with DNA, we show the widespread distribution of filamentous γPFD structures within the cell. These findings provide valuable insights into the structure and localization of γPFD, opening up possibilities for studying intriguing nanoscale components not only in archaea but also in other microorganisms.

3D Reconstruction and Virtual Reality Is an Acceptable and Feasible Method for Addressing Body Image in Bariatric Metabolic Surgery

Abstract Background Patients living with obesity continue to experience body image dissatisfaction following bariatric metabolic surgery. The underlying reasons are poorly understood but may be due to unmet expectations. Negative body image perception following metabolic surgery leads to poorer psychological and clinical outcomes. This study aims to establish the acceptability and feasibility of three-dimensional (3D) reconstruction and virtual reality (VR) as a method of providing psychological support to bariatric patients to improve body image satisfaction and interventional outcomes. Methods Seven participants were recruited from the Imperial Weight Centre. 3D photographs were captured and processed to produce two 3D reconstructed images with 15% and 25% total weight loss. Participants were shown their images using VR and participated in peer group workshops. Results Six participants were retained until the end of the study. Five out of six participants agreed the images provided them with a more accurate representation of their body changes and overall appearance following bariatric metabolic surgery. All participants strongly agreed with the group setting and felt VR facilitated discussions on body image. Overall, all participants felt that the use of VR and 3D reconstruction is beneficial in supporting patients to adjust to changes in their body image after bariatric metabolic surgery. Conclusions This is the first study to explore and demonstrate that 3D reconstruction and VR is an acceptable and feasible method providing patients with a realistic expectation of how their body will change following significant weight loss, potentially improving body image satisfaction after surgery, as well as psychological and interventional outcomes. Graphical Abstract

Influence of the Road Model on the Optimal Maneuver of a Racing Motorcycle

Motorcycle motion is largely influenced by the road geometry, which alters the allowable accelerations in longitudinal and lateral directions and influences the vertical wheel loads. Recently, a method for three-dimensional road reconstruction and its incorporation into transient and quasi-steady-state (QSS) minimum lap time simulations (MLTSs) has been proposed. The main purpose of this work is to demonstrate how significantly different results from a minimum lap time optimal control problem can be obtained when using inappropriate elevation data sources in the track reconstruction problem, and how the road model reconstructed using poor input data can lead to misleading conclusions when analyzing real vehicle and driver performances. Two road models derived from high- and low-resolution digital elevation models (DEMs) are compared and their impact on the optimal maneuver of a racing motorcycle is examined. The essentials of track identification are presented, as well as vehicle positioning on the 3D road and the generalized QSS motorcycle model. Obtained 3D and 2D road models are analyzed in detail, on a case example of the Road Atlanta racetrack, and used in minimum lap time simulations, which are validated by the experimental data recorded on the Supersport motorcycle. The comparative analysis showed that great care should be taken when selecting the elevation dataset in the track reconstruction process, and that the 1 m resolution local DEMs seem to be sufficient to obtain MLTS results close to the measured ones. The example of using the 3D free-trajectory QSS minimum lap time problem to localize the track segments where real driver actions can be improved is also presented. The differences between simulation results on different road models of the same racetrack can be large and influence the interpretation of optimal maneuver.

Utilizing Synchrotron-Based X-ray Micro-Computed Tomography to Visualize the Microscopic Structure of Starch Hydrogels In Situ.

This study aimed to visualize the microstructures of starch hydrogels using synchrotron-based X-ray micro-computed tomography (μCT). Waxy maize starch (WMS, 3.3% amylose, db), pea starch (PS, 40.3% amylose), and high-amylose maize starch (HMS, 63.6% amylose) were cooked at 95 and 140 °C to prepare starch hydrogels. WMS and HMS failed to form a gel after 95 °C cooking and storage, while PS developed a firm gel. At 140 °C cooking, HMS of a high amylose nature was fully gelatinized and generated a rigid gel with the highest strength. Both scanning electron microscopy (SEM) and μCT revealed the unique structural features of various starch hydrogels/pastes prepared at different temperatures, which were greatly affected by the degree of swelling and dispersity of the starches. As a nondestructive method, μCT showed certain advantages over SEM, including minimal shrinkage of the hydrogels, relatively simple sample preparation, and allowing for three-dimensional reconstruction of the hydrogel microstructure. This study indicated that synchrotron-based μCT could be a useful technique in visualizing biopolymer-based hydrogels.

A randomized controlled clinical trial of concentrated growth factor combined with sodium hyaluronate in the treatment of temporomandibular joint osteoarthritis

ObjectiveTo investigate the effect of concentrated growth factor (CGF) combined with sodium hyaluronate (SH) on temporomandibular joint osteoarthritis (TMJOA).MethodsSixty patients with TMJOA who were diagnosed by cone-beam computed tomography (CBCT) between March 2020 and March 2023 at the Stomatological Hospital of Xi’an Jiaotong University were randomly divided into a control group (n = 30) and an experimental group (n = 30). The patients in the experimental group were treated with CGF + SH, and those in the control group were treated with SH only. The visual analogue scale (VAS) score indicating pain in the temporomandibular joint (TMJ) area; the Helkimo Clinical Dysfunction Index (Di); and changes in condylar CBCT at the first visit and 2 weeks, 3 months and 6 months after treatment were recorded. The CBCT data of the patients in the experimental and control groups were collected, and the three-dimensional CBCT image sequences were imported into Mimics Medical 19.0 software in DICOM format for condylar reconstruction.ResultsThe VAS scores at 2 weeks, 3 months and 6 months after treatment were significantly lower in the experimental group than in the control group (P < 0.05), and the pain in the experimental group was significantly relieved. The Di was significantly lower in the experimental group than in the control group (P < 0.05), and the clinical function of the TMJ improved. After treatment, the CBCT score was significantly lower in the experimental group than in the control group (P < 0.05), and the condylar bone cortex was obviously repaired. Observation of the condylar bone cortex by three-dimensional reconstruction showed the same results as those obtained by CBCT.ConclusionCGF combined with SH is effective in the treatment of TMJOA and can improve muscle pain, TMJ pain, Impaired TMJ function, Impaired range of movement, Pain on movement of the mandible and promote bone repair.The registration number (TRN)ChiCTR2400082712.The date of registrationApril 5, 2024.

Segmentation and quantitative analysis of optical coherence tomography (OCT) images of laser burned skin based on deep learning.

Evaluation of skin recovery is an important step in the treatment of burns. However, conventional methods only observe the surface of the skin and cannot quantify the injury volume. Optical coherence tomography (OCT) is a non-invasive, non-contact, real-time technique. Swept-frequency OCT uses near infrared light and analyzes the intensity of light echo at different depths to generate images from optical interference signals. To quantify the dynamic recovery of skin burns over time, laser induced skin burns in mice were evaluated using deep learning of swept-frequency OCT images.A laser-induced mouse skin thermal injury model was established in thirty Kunming mice, and OCT images of normal and burned areas of mouse skin were acquired at day 0, day 1, day 3, day 7, and day 14 after laser irradiation. This resulted in 7000 normal and 1400 burn B-scan images which were divided into training, validation, and test sets at 8:1.5:0.5 ratio for the normal data and 8:1:1 for the burn data. Normal images were manually annotated, and the deep learning U-Net model (verified with PSPNe and HRNet models) was used to segment the skin into three layers: the dermal epidermal layer, subcutaneous fat layer, and muscle layer. For the burn images, the models were trained to segment just the damaged area. Three-dimensional reconstruction technology was then used to reconstruct the damaged tissue and calculate the damaged tissue volume. The average IoU value and f-score of the normal tissue layer U-Net segmentation model were 0.876 and 0.934 respectively. The IoU value of the burn area segmentation model reached 0.907 and f-score value reached 0.951. Compared with manual labeling, the U-Net model was faster with higher accuracy for skin stratification. OCT and U-Net segmentation can provide rapid and accurate analysis of tissue changes and clinical guidance in the treatment of burns.

Assessment of cerebral venous sinus: Anatomical and functional diagnostic performance of three-dimensional reconstruction models based on venous sinus MRI and CT images

Venous sinus stenosis is commonly observed in patients presenting with pulsatile tinnitus (PT). While magnetic resonance imaging (MRI) and computed tomography (CT) are commonly used for assessing venous sinus geometries, the preferred modality remains unclear. In this study, we reconstructed the three-dimensional (3D) geometries of the venous sinus using MRI and CT imaging data from 20 PT patients. We conducted comparisons of the anatomical features of the venous sinus through case-wise analysis and anatomic geometrical parameter-wise analysis. Our findings indicate that by taking the geometries from CT as a reference, MRI could provide a better illustration of venous structure, primarily due to a stronger flow signal concentrated in the vascular tree. We observed high agreements in anatomic parameters measured from 3D geometries reconstructed based on CT and MRI in 19 out of 20 cases. Notably, the cross-sectional area of the sinus and segment length displayed the highest consistency, with a mean difference of -5.01% and 6.5% between modalities, respectively. In addition, we noticed that 55% of cases exhibited consistency in analyzing the confluence of the sinus, while variants of connectivity and collateral branching were observed between CT and MRI. Importantly, CT-based geometric reconstruction provided better detail of inflow side branches in the straight sinus, whereas MRI preserved more side branches of outflow in the downstream sinus. It is important to note that CT-based evaluation may be affected by the bone structures surrounding the venous sinus, whereas MRI-based evaluation focuses on blood flow to the segments, potentially indicating both anatomical and functional abnormalities.

Enhancing surgical planning for abdominal tumors in children through advanced 3D visualization techniques: a systematic review of future prospects

IntroductionPreoperative three-dimensional (3D) reconstruction using sectional imaging is increasingly used in challenging pediatric cases to aid in surgical planning. Many case series have described various teams' experiences, discussing feasibility and realism, while emphasizing the technological potential for children. Nonetheless, general knowledge on this topic remains limited compared to the broader research landscape. The aim of this review was to explore the current devices and new opportunities provided by preoperative Computed Tomography (CT) scans or Magnetic Resonance Imaging (MRI).MethodsA systematic review was conducted to screen pediatric cases of abdominal and pelvic tumors with preoperative 3D reconstruction published between 2000 and 2023.DiscussionSurgical planning was facilitated through virtual reconstruction or 3D printing. Virtual reconstruction of complex tumors enables precise delineation of solid masses, formulation of dissection plans, and suggests dedicated vessel ligation, optimizing tissue preservation. Vascular mapping is particularly relevant for liver surgery, large neuroblastoma with imaging-defined risk factors (IDRFs), and tumors encasing major vessels, such as complex median retroperitoneal malignant masses. 3D printing can facilitate specific tissue preservation, now accessible with minimally invasive procedures like partial nephrectomy. The latest advancements enable neural plexus reconstruction to guide surgical nerve sparing, for example, hypogastric nerve modelling, typically adjacent to large pelvic tumors. New insights will soon incorporate nerve plexus images into anatomical segmentation reconstructions, facilitated by non-irradiating imaging modalities like MRI.ConclusionAlthough not yet published in pediatric surgical procedures, the next anticipated advancement is augmented reality, enhancing real-time intraoperative guidance: the surgeon will use a robotic console overlaying functional and anatomical data onto a magnified surgical field, enhancing robotic precision in confined spaces.

Fast millimeter-wave three-dimensional holographic reconstruction based on target accurate distance

Fast millimeter-wave three-dimensional holographic reconstruction based on target accurate distance

Comparative evaluations on the canal-centering ability of novel heat-treated retreatment file system using nano-computed tomography

Abstract Introduction: The main goal of instrumentation during retreatment is to maintain the original curvature of the canal during retrieval of gutta-percha. The present study evaluates the canal-centering ability of two different retreatment file systems. Materials and Methods: Forty extracted single-rooted teeth were decoronated and obturated at the standardized root length of 16 mm. Samples were divided into two groups of each 20 single root teeth and they were instrumented using Solite RS3 Retreatment and ProTaper Retreatment files, respectively. Both pre- and postoperative nano-computed tomography scans were taken, and three-dimensional reconstruction was done for analysis. Sections of both the pre- and postoperative samples were taken at 7 mm, 5 mm, and 3 mm from the apex to calculate the canal-centering ratio. Independent t-test was used for statistical analysis between the two groups. Results: Solite RS3 retreatment files showed a significant difference at the 3 levels (P &lt; 0.000) compared to ProTaper retreatment files. Conclusion: From the above results, we can conclude that Solite RS3 caused minimal canal transportation and produced a relatively centered preparation in comparison to the ProTaper Retreatment system.

CAMEL. II. A 3D Coronal Mass Ejection Catalog Based on Coronal Mass Ejection Automatic Detection with Deep Learning

Coronal mass ejections (CMEs) are major drivers of geomagnetic storms, which may cause severe space weather effects. Automating the detection, tracking, and three-dimensional (3D) reconstruction of CMEs is important for operational predictions of CME arrivals. The COR1 coronagraphs on board the Solar Terrestrial Relations Observatory spacecraft have facilitated extensive polarization observations, which are very suitable for the establishment of a 3D CME system. We have developed such a 3D system comprising four modules: classification, segmentation, tracking, and 3D reconstructions. We generalize our previously pretrained classification model to classify COR1 coronagraph images. Subsequently, as there are no publicly available CME segmentation data sets, we manually annotate the structural regions of CMEs using Large Angle and Spectrometric Coronagraph C2 observations. Leveraging transformer-based models, we achieve state-of-the-art results in CME segmentation. Furthermore, we improve the tracking algorithm to solve the difficult separation task of multiple CMEs. In the final module, tracking results, combined with the polarization ratio technique, are used to develop the first single-view 3D CME catalog without requiring manual mask annotation. Our method provides higher precision in automatic 2D CME catalog and more reliable physical parameters of CMEs, including 3D propagation direction and speed. The aforementioned 3D CME system can be applied to any coronagraph data with the capability of polarization measurements.