Virtual Scanning Research Articles

HLA-DR4Pred2: An improved method for predicting HLA-DRB1*04:01 binders

HLA-DRB1*04:01 is associated with numerous diseases, including sclerosis, arthritis, diabetes, and COVID-19, emphasizing the need to scan for binders in the antigens to develop immunotherapies and vaccines. Current prediction methods are often limited by their reliance on the small datasets. This study presents HLA-DR4Pred2, developed on a large dataset containing 12,676 binders and an equal number of non-binders. It’s an improved version of HLA-DR4Pred, which was trained on a small dataset, containing 576 binders and an equal number of non-binders. All models were trained, optimized, and tested on 80 % of the data using five-fold cross-validation and evaluated on the remaining 20 %. A range of machine learning techniques was employed, achieving maximum AUROC of 0.90 and 0.87, using composition and binary profile features, respectively. The performance of the composition-based model increased to 0.93, when combined with BLAST search. Additionally, models developed on the realistic dataset containing 12,676 binders and 86,300 non-binders, achieved a maximum AUROC of 0.99. Our proposed method outperformed existing methods when we compared the performance of our best model to that of existing methods on the independent dataset. Finally, we developed a standalone tool and a webserver for HLADR4Pred2, enabling the prediction, design, and virtual scanning of HLA-DRB1*04:01 binding peptides, and we also released a Python package available on the Python Package Index (https://webs.iiitd.edu.in/raghava/hladr4pred2/; https://github.com/raghavagps/hladr4pred2; https://pypi.org/project/hladr4pred2/).

CNN-based transfer learning for forest aboveground biomass prediction from ALS point cloud tomography

ABSTRACT This study presents a new approach for predicting forest aboveground biomass (AGB) from airborne laser scanning (ALS) data: AGB is predicted from sequences of images depicting vertical cross-sections through the ALS point clouds. A 3D version of the VGG16 convolutional neural network (CNN) with initial weights transferred from pre-training on the ImageNet dataset was used. The approach was tested on datasets from Canada, Poland, and the Czech Republic. To analyse the effect of training sample size on model performance, different-sized samples ranging from 10 to 375 ground plots were used. The CNNs were compared with random forest models (RFs) trained on point cloud metrics. At the maximum number of training samples, the difference in RMSE between observed and predicted AGB of CNNs and RFs ranged from −2 t/ha to 5 t/ha, and the difference in squared Pearson correlation coefficient ranged from −0.05 to 0.06. Additional pre-training on synthetic data derived from virtual laser scanning of simulated forest stands could only improve the prediction performance of the CNNs when only a few real training samples (10–40) were available. While 3D CNNs trained on cross-section images derived from real data showed promising results, RFs remain a competitive alternative.

Influence of coarse aggregates’ morphological characteristics on the pore structures of skeleton in porous asphalt mixture

Coarse aggregates play a significant role in configuring the pore structures in the porous asphalt mixture (PAM). This study aims to reveal the influence of coarse aggregates’ morphological characteristics on the pore features in the coarse aggregate skeleton (CAS) of PAM. To achieve this goal, X-ray CT and three-dimensional (3D) visualization reconstruction technology were utilized to acquire the 3D morphology of different kinds of coarse aggregates. Based on the morphology of real aggregate particles, a 3D simulation model of CAS was developed, and virtual scanning imaging technology was used to obtain the pore features in the CAS. The sensitive influence of coarse aggregate morphologies on the pore features was evaluated by GA-BP neural network. Results show that air void in the skeleton is most sensitive to the composite flat-elongated index and composite sphericity of 13.2mm aggregates, and composite sphericity of 9.5mm aggregates. The composite sphericity of 13.2mm aggregates, composite flat-elongated index and composite texture index of 9.5mm aggregates, composite flat-elongated index, composite angularity index, and composite texture index of 4.75mm aggregates are the high-sensitivity influencing factors to the fractal characteristic of pore structures.

Comparing triple and single Doppler lidar wind measurements with sonic anemometer data based on a new filter strategy for virtual tower measurements

Abstract. In this study, we compare the wind measurements of a virtual tower triple Doppler lidar setup to those of a sonic anemometer located at a height of 90 m above ground on an instrumented tower and with those of two single Doppler lidars to evaluate the effect of the horizontal homogeneity assumption used for single Doppler lidar applications on the measurement accuracy. The triple lidar setup was operated in a 90 m stare and a step–stare mode at six heights between 90 and 500 m above ground, while the single lidars were operated in a continuous scan velocity–azimuth display (VAD) mode where one of them had a zenith angle of 54.7° and the other one of 28.0°. The instruments were set up at the boundary-layer field site of the German Meteorological Service (DWD) in July and August of 2020 during the FESST@MOL (Field Experiment on sub-mesoscale spatiotemporal variability at the Meteorological Observatory Lindenberg) 2020 campaign. Overall, we found good agreement of the lidar methods for the whole study period for different averaging times and scan modes compared to the sonic anemometer. For the step–stare mode wind speed measurements, the comparability between the triple lidar and the sonic anemometer was 0.47 m s−1 at an averaging time of 30 min with a bias value of −0.34 m s−1. For wind speed measured by one single lidar setup for the same period with an averaging time of 30 min, we found a comparability of 0.32 m s−1 at an averaging time of 30 min and a bias value of −0.07 m s−1 as well as values of 0.47 and −0.34 m s−1 for the other one, respectively. We also compared the wind velocity measurements of the single and triple lidars at different heights and found decreasing agreement between them with increasing measurement height up to 495 m above ground for the single lidar systems. We found that the single Doppler lidar with the increased zenith angle produced poorer agreement with the triple Doppler lidar setup than the one with the lower zenith angle, especially at higher altitudes. At a height of 495 m above ground and with an averaging time of 30 min the comparability and bias for the larger zenith angle were 0.71 and −0.50 m s−1, respectively, compared to values of 0.57 and −0.28 m s−1 for the smaller zenith angle. Our results confirm that a single Doppler lidar provides reliable wind speed and direction data over heterogeneous but basically flat terrain in different scan configurations. For the virtual tower scanning strategies, we developed a new filtering approach based on a median absolute deviation (MAD) filter combined with a relatively relaxed filtering criterion for the signal-to-noise ratio output by the instrument.

Estimation of canopy photon recollision probability from airborne laser scanning

The past two decades have witnessed the widespread application of the spectral invariant theory (p-theory) in modeling the shortwave radiation absorbed or scattered by vegetation. The basic principle of this theory is that the canopy reflectance is solely determined by the optical properties of leaves and the photon recollision probability p. As one of the spectral invariants, p serves as a critical bond between the spectral characteristics of the canopy at any wavelength and the reflectance, transmittance, or absorptance of the vegetation canopy, and is intimately associated with the solution of the radiative transfer equation. Currently, estimation of p-value is predominantly accomplished through canopy structural parameters, such as the spherically averaged silhouette to total area ratio (STAR¯) or Leaf Area Index (LAI). In this work, we provide an approach to estimate canopy photon recollision probability directly from Airborne Laser Scanning (ALS) data. We showed that the recollision probability can be interpreted as the interceptions of virtual rays emitted from sampling points within tree crowns described with turbid media, which avoided detailed reconstruction of leaf structures. The approach was evaluated with both virtual experiments as well as field measurements. The virtual experiments employed the Large-scalE remote Sensing data and image Simulation model (LESS) to simulate virtual ALS scanning data based on three RAdiation transfer Model Intercomparison (RAMI) actual canopies, with each divided into 25 segments, for which the p-values could be obtained through LESS. Our findings showed that p-values can be accurately estimated from ALS point clouds. Specifically, it exhibited great consistency with RMSE% less than 5% for broadleaved forest scenes, 25% for mixed forest scenes, and less than 10% for coniferous forest scenes in virtual experiments, respectively, and less than 25% compared to field measurements. This study displays the potential of ALS as a promising tool for forest structure characterization and short-wave radiation modeling in forest ecosystems.

An improved multiple discrete time system for operational modal analysis of a slanted rotational blade under natural excitation via a long-range tracking continuously scanning laser Doppler vibrometer system

A long-range tracking continuously scanning laser Doppler vibrometer (LTCSLDV) system is able to continuously track the speed and simultaneously sweep the surface of a distanced rotational blade with predicted paths. During the long-range continuous scanning, laser beams including raw responses with modal parameter information are transmitted from the measured distanced rotational blade to the laser Doppler vibrometer (LDV). However, classical signal processing methods for raw responses obtained from a LTCSLDV measurement, which are the polynomial and demodulation method, cannot implement standard modal estimation. Its reason is that continuous scanning responses includes density virtual measuring points and one of its results is that some significant modal parameter, especially damping ratio, cannot be estimated directly. This work provides an improved multiple discrete time system (MDTS) for LTCSLDV measurements that is capable of extracting the responses of multiple virtual measuring points on the virtual scanning path with equally intervals as if these responses are measured at fixed pseudo-measurement points. Therefore, extensively complex signal processing can be implemented on the processed responses through program or commercial software only if the amount of the data of them is sufficient for modal analysis. The measurements were performed on a slanted rotational blade (SRB) in real operational condition with the considerations of the pitch angle of the SRB and the tilt angle of the direction of laser beam emitted from a LDV. The predicted tracking and scanning path of the laser spot in long-range measurements is realized through visual identification with a high-speed color camera.

A step towards 6D WAXD tensor tomography.

X-ray scattering/diffraction tensor tomography techniques are promising methods to acquire the 3D texture information of heterogeneous biological tissues at micrometre resolution. However, the methods suffer from a long overall acquisition time due to multi-dimensional scanning across real and reciprocal space. Here, a new approach is introduced to obtain 3D reciprocal information of each illuminated scanning volume using mathematic modeling, which is equivalent to a physical scanning procedure for collecting the full reciprocal information required for voxel reconstruction. The virtual reciprocal scanning scheme was validated by a simulated 6D wide-angle X-ray diffraction tomography experiment. The theoretical validation of the method represents an important technological advancement for 6D diffraction tensor tomography and a crucial step towards pervasive applications in the characterization of heterogeneous materials.

Implementation of remote MRI scanning

The present shortage of MRI technologists continues to interfere with the delivery of care of patients. In addition, there have been limited solutions to cover disability, sickness, vacation, and personal days of that limited workforce. Our practice decided that the best way to address these coverage problems was to implement a virtual remote scanning solution. We explain the IT infrastructure, training and policies needed to implement this innovative solution safely and successfully to the MRI technologist shortage.

Using convolutional neural networks for stereological characterization of 3D hetero-aggregates based on synthetic STEM data

The 3D nano/microstructure of materials can significantly influence their macroscopic properties. In order to enable a better understanding of such structure-property relationships, 3D microscopy techniques can be deployed, which are however often expensive in both time and costs. Often 2D imaging techniques are more accessible, yet they have the disadvantage that the 3D nano/microstructure of materials cannot be directly retrieved from such measurements. The motivation of this work is to overcome the issues of characterizing 3D structures from 2D measurements for hetero-aggregate materials. For this purpose, a method is presented that relies on machine learning combined with methods of spatial stochastic modeling for characterizing the 3D nano/microstructure of materials from 2D data. More precisely, a stochastic model is utilized for the generation of synthetic training data. This kind of training data has the advantage that time-consuming experiments for the synthesis of differently structured materials followed by their 3D imaging can be avoided. More precisely, a parametric stochastic 3D model is presented, from which a wide spectrum of virtual hetero-aggregates can be generated. Additionally, the virtual structures are passed to a physics-based simulation tool in order to generate virtual scanning transmission electron microscopy (STEM) images. The preset parameters of the 3D model together with the simulated STEM images serve as a database for the training of convolutional neural networks, which can be used to determine the parameters of the underlying 3D model and, consequently, to predict 3D structures of hetero-aggregates from 2D STEM images. Furthermore, an error analysis is performed with respect to structural descriptors, e.g. the hetero-coordination number. The proposed method is applied to image data of TiO2-WO3 hetero-aggregates, which are highly relevant in photocatalysis processes. However, the proposed method can be transferred to other types of aggregates and to different 2D microscopy techniques. Consequently, the method is relevant for industrial or laboratory setups in which product quality is to be quantified by means of inexpensive 2D image acquisition.

IN SILICO APPROACHES ON PHENYLALANINE HYDROXYLASE INHIBITOR-RELATED COMPOUNDS USED IN PARKINSON’S DISEASE TREATMENT

Objective: In Parkinson’s disease, Levodopa with Carbidopa addresses dopamine deficiency. Phenylalanine hydroxylase catalyzes phenylalanine to tyrosine conversion crucial for dopamine synthesis. Inhibiting phenylalanine hydroxylase may enhance Carbidopa's effects, preventing peripheral dopamine synthesis. The study used virtual scanning, molecular docking, and dynamics simulation to explore phenylalanine hydroxylase interactions with Carbidopa and similar ligands. ADME/T assessments and drug similarity tests were conducted to evaluate therapeutic potential in biological systems. Material and Method: A molecular docking study was performed on the structures obtained from the PubChem database and human PAH (PDB ID: 6PAH) using Autodock Vina within Chimera 1.16. Furthermore, the ligands underwent ADME/T assays, which are crucial aspects in drug development. Result and Discussion: The study suggests that 2-(2-Aminohydrazinyl)-3-(3,4-dihydroxyphenyl)-2-methylpropanoic acid shows promise as a phenylalanine hydroxylase inhibitor for Parkinson's disease treatment, but further research is needed to assess its safety, efficacy, and specificity, particularly in extracerebral regions, while also exploring its potential to improve the effectiveness of Levadopa/Carbidopa combination therapy.

3D Specimen Scanning and Mapping in Musculoskeletal Oncology: A Feasibility Study.

Surgical resection is the primary treatment for bone and soft tissue tumors. Negative margin status is a key factor in prognosis. Given the three-dimensional (3D) anatomic complexity of musculoskeletal tumor specimens, communication of margin results between surgeons and pathologists is challenging. We sought to perform ex vivo 3D scanning of musculoskeletal oncology specimens to enhance communication between surgeons and pathologists. Immediately after surgical resection, 3D scanning of the fresh specimen is performed prior to frozen section analysis. During pathologic grossing, whether frozen or permanent, margin sampling sites are annotated on the virtual 3D model using computer-aided design (CAD) software. 3D scanning was performed in seven cases (six soft tissue, one bone), with specimen mapping on six cases. Intraoperative 3D scanning and mapping was performed in one case in which the location of margin sampling was shown virtually in real-time to the operating surgeon to help achieve a negative margin. In six cases, the 3D model was used to communicate final permanent section analysis. Soft tissue, cartilage, and bone (including lytic lesions within bone) showed acceptable resolution. Virtual 3D scanning and specimen mapping is feasible and may allow for enhanced documentation and communication. This protocol provides useful information for anatomically complex musculoskeletal tumor specimens. Future studies will evaluate the effect of the protocol on positive margin rates, likelihood that a re-resection contains additional malignancy, and exploration of targeted adjuvant radiation protocols using a patient-specific 3D specimen map.

Retracted: Application of 3D Virtual Scanning Technology in Landscape Planning of Complex Landscape Gardens

Retracted: Application of 3D Virtual Scanning Technology in Landscape Planning of Complex Landscape Gardens

Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data

Automatic damage assessment by analysing UAV-derived 3D point clouds provides fast information on the damage situation after an earthquake. However, the assessment of different damage grades is challenging given the variety in damage characteristics and limited transferability of methods to other geographic regions or data sources. We present a novel change-based approach to automatically assess multi-class building damage from real-world point clouds using a machine learning model trained on virtual laser scanning (VLS) data. Therein, we (1) identify object-specific point cloud-based change features, (2) extract changed building parts using k-means clustering, (3) train a random forest machine learning model with VLS data based on object-specific change features, and (4) use the classifier to assess building damage in real-world photogrammetric point clouds. We evaluate the classifier with respect to its capacity to classify three damage grades (heavy, extreme, destruction) in pre-event and post-event point clouds of an earthquake in L’Aquila (Italy). Using object-specific change features derived from bi-temporal point clouds, our approach is transferable with respect to multi-source input point clouds used for model training (VLS) and application (real-world photogrammetry). We further achieve geographic transferability by using simulated training data which characterises damage grades across different geographic regions. The model yields high multi-target classification accuracies (overall accuracy: 92.0%–95.1%). Classification performance improves only slightly when using real-world region-specific training data (< 3% higher overall accuracies). We consider our approach especially relevant for applications where timely information on the damage situation is required and sufficient real-world training data is not available.

Molecular mechanism of HNTX-I activates the intermediate-conductance Ca2+-activated K+ (IK) channels

The IK channel, a potassium ion channel regulated by calcium ions and voltages in a bidirectional manner, has been implicated in a range of diseases. However, there are currently few compounds available that can target the IK channel with high potency and specificity. Hainantoxin-I (HNTX-I) is the first peptide activator of IK channel discovered so far, but its activity is not ideal, and the underlying mechanism interaction between HNTX-I toxin and IK channel remains unclear. Thus, our study aimed to enhance the potency of IK channel activating peptides derived from HNTX-I and elucidate the molecular mechanism underlying the interaction between HNTX-I and the IK channel. By employing virtual alanine scanning mutagenesis, we generated 11 HNTX-I mutants using site-directed mutagenesis to pinpoint specific residues crucial for the HNTX-I and IK channel interaction. Subsequently, we identified key residues on the IK channel that are involved in the interaction with HNTX-I. Additionally, molecular docking was employed to guide the molecular engineering process and clarify the binding interface between HNTX-I and the IK channel. Our results demonstrate that HNTX-I primarily acts on the IK channel via the N-terminal amino acid, and its interaction with the IK channel is mediated by electrostatic and hydrophobic interactions, specifically the amino acid residues at positions 1, 3, 5, and 7 on HNTX-I. This study provides valuable insights into the peptide toxins that may serve as potential templates for the development of activators with enhanced potency and selectivity for the IK channel.

Augmented Reality Surgical Navigation System Integrated with Deep Learning.

Most current surgical navigation methods rely on optical navigators with images displayed on an external screen. However, minimizing distractions during surgery is critical and the spatial information displayed in this arrangement is non-intuitive. Previous studies have proposed combining optical navigation systems with augmented reality (AR) to provide surgeons with intuitive imaging during surgery, through the use of planar and three-dimensional imagery. However, these studies have mainly focused on visual aids and have paid relatively little attention to real surgical guidance aids. Moreover, the use of augmented reality reduces system stability and accuracy, and optical navigation systems are costly. Therefore, this paper proposed an augmented reality surgical navigation system based on image positioning that achieves the desired system advantages with low cost, high stability, and high accuracy. This system also provides intuitive guidance for the surgical target point, entry point, and trajectory. Once the surgeon uses the navigation stick to indicate the position of the surgical entry point, the connection between the surgical target and the surgical entry point is immediately displayed on the AR device (tablet or HoloLens glasses), and a dynamic auxiliary line is shown to assist with incision angle and depth. Clinical trials were conducted for EVD (extra-ventricular drainage) surgery, and surgeons confirmed the system's overall benefit. A "virtual object automatic scanning" method is proposed to achieve a high accuracy of 1 ± 0.1 mm for the AR-based system. Furthermore, a deep learning-based U-Net segmentation network is incorporated to enable automatic identification of the hydrocephalus location by the system. The system achieves improved recognition accuracy, sensitivity, and specificity of 99.93%, 93.85%, and 95.73%, respectively, representing a significant improvement from previous studies.

Research on Defect Detection of The Liquid Bag of Bag Infusion Sets Based on Machine Vision

Intravenous infusion often uses bag infusion devices for clinic treatment, and the liquid bag assembly is an essential component of the bag infusion device. This paper adopts a machine vision system to inspect the assembly quality of the pipeline and dosing interface of liquid bag assembly. We conduct in-depth research on the lighting method, image pre-processing, and defect detection algorithm of a vision system for two defects of pipeline missing and dosing interface missing. Moreover, we do a lighting experiment to detect transparent liquid bag assembly defects. Proposes an adaptive gamma correction library based on power function derivative calculation, and combines the cumulative histogram for adaptive gamma correction, which amplifies the image edge information, combined with the binarization of the OTSU, solves the image segmentation problem in this. Proposes an adaptive ROI region selection method and virtual linear scanning method to achieve the detection of two kinds of defects. The results show that the recognition rate of missing defects of the pipeline on the liquid bag assembly in the machine vision system reaches 100%.

Estimating plant area density of individual trees from discrete airborne laser scanning data using intensity information and path length distribution

Plant area density (PAD) of individual trees is an important structural indicator related to tree growth status, stress levels due to pests and diseases, photosynthesis potential, and evapotranspiration. Airborne laser scanning (ALS) provides unprecedented 3D information for mapping forest canopy parameters. Previous studies mainly focused on mapping stand-level and 2D leaf area index. This study proposes a method to estimate PAD from discrete and multiple return ALS data at individual tree scales. The proposed method uses path length distribution to eliminate crown-shape-induced clumping, as well as intensity information to estimate crown transmittance from relative low-density points. The path length distribution is derived from the 3D crown boundary contours created by an alpha shape algorithm, which explicitly considers the non-uniform LiDAR pulse penetration distances. Pulse intensity is calibrated with the nearest pure-ground pulse to mitigate the need for prior leaf and ground reflectance information, which can be used in areas with a heterogeneous background. The proposed method was evaluated both in virtual experiments as well as with terrestrial laser scanning (TLS) data. The virtual experiments used the large-scale remote sensing data and image simulation model (LESS) to simulate virtual ALS scanning data based on abstract and realistic canopies. Results showed that the ALS-derived PAD is highly accurate, with RMSE less than 0.02 and R2 > 0.99 for the abstract sphere and cube crowns, and RMSE = 0.19 and R2 = 0.578 for the realistic crowns. The comparison with TLS of a birch plot shows that the ALS-derived PAD is consistent with those derived from TLS, with RMSE = 0.14 and R2 = 0.46. This study demonstrated that using the full intensity and geometry information of a point cloud is capable of generating high-resolution forest parameters from ALS data.

SEM Measurements of the Dimensions of Relief Structures in the Technological Process of Manufacturing Microcircuits

The problems of measuring the dimensions of relief elements on a scanning electron microscope (SEM) in the technological process of manufacturing microcircuits are considered. The first problem is related to the fact that the increase in the SEM during operation can vary over a wide range depending on the measured dimensions. The second problem is that the probe diameter determined in the SEM calibration process differs from the diameter used in operational measurements. The third problem is related to the fact that it is not known which relief parameter is measured in the SEM probe defocusing method. It is shown that to solve the first problem, it is necessary to calibrate the mark on the image using structures with a trapezoidal profile and large angles of inclination of the side walls. The solution of the second problem is based on the method of defocusing the SEM probe: determining the dependence of the sizes between certain points on the SEM signals on the probe diameter and extrapolating this dependence to the zero value of the diameter. The third problem is solved with the help of a virtual scanning electron microscope.

TPDNet: Texture-Guided Phase-to-DEPTH Networks to Repair Shadow-Induced Errors for Fringe Projection Profilometry

This paper proposes a phase-to-depth deep learning model to repair shadow-induced errors for fringe projection profilometry (FPP). The model comprises two hourglass branches that extract information from texture images and phase maps and fuses the information from the two branches by concatenation and weights. The input of the proposed model contains texture images, masks, and unwrapped phase maps, and the ground truth is the depth map from CAD models. A loss function was chosen to consider image details and structural similarity. The training data contain 1200 samples in the verified virtual FPP system. After training, we conduct experiments on the virtual and real-world scanning data, and the results support the model’s effectiveness. The mean absolute error and the root mean squared error are 1.0279 mm and 1.1898 mm on the validation dataset. In addition, we analyze the influence of ambient light intensity on the model’s performance. Low ambient light limits the model’s performance as the model cannot extract valid information from the completely dark shadow regions in texture images. The contribution of each branch network is also investigated. Features from the texture-dominant branch are leveraged as guidance to remedy shadow-induced errors. Information from the phase-dominant branch network makes accurate predictions for the whole object. Our model provides a good reference for repairing shadow-induced errors in the FPP system.

Development of metaverse for intelligent healthcare.

The metaverse integrates physical and virtual realities, enabling humans and their avatars to interact in an environment supported by technologies such as high-speed internet, virtual reality, augmented reality, mixed and extended reality, blockchain, digital twins and artificial intelligence (AI), all enriched by effectively unlimited data. The metaverse recently emerged as social media and entertainment platforms, but extension to healthcare could have a profound impact on clinical practice and human health. As a group of academic, industrial, clinical and regulatory researchers, we identify unique opportunities for metaverse approaches in the healthcare domain. A metaverse of 'medical technology and AI' (MeTAI) can facilitate the development, prototyping, evaluation, regulation, translation and refinement of AI-based medical practice, especially medical imaging-guided diagnosis and therapy. Here, we present metaverse use cases, including virtual comparative scanning, raw data sharing, augmented regulatory science and metaversed medical intervention. We discuss relevant issues on the ecosystem of the MeTAI metaverse including privacy, security and disparity. We also identify specific action items for coordinated efforts to build the MeTAI metaverse for improved healthcare quality, accessibility, cost-effectiveness and patient satisfaction.