Real-time Reconstruction Research Articles

Real-time plasma boundary shape reconstruction using visible camera on EAST Tokamak

Abstract Accurate plasma shape reconstruction is crucial for the stable operation of tokamak devices. In this study, a plasma optical boundary reconstruction system is constructed on the Experimental Advanced Superconducting Tokamak (EAST), and real-time shape reconstruction based on an optical method is realized for the first time on EAST.
First, a boundary extraction algorithm based on gray features is designed to extract the optical boundary from plasma optical images. Then, to reconstruct the optical boundary in the tokamak coordinate system, a camera calibration algorithm is developed based on feature point matching, and a coordinate mapping algorithm is designed based on plasma geometric features. Then, the system reconstructs the plasma boundary shape based on images acquired by cameras. Finally, the system is deployed in real-time on EAST, and its reconstruction rate meets the requirement of the EAST plasma shape control system. This study validates the feasibility of using an optical boundary shape reconstruction method on a tokamak device for real-time plasma shape reconstruction, providing a new shape reconstruction approach during steady-state discharge in future fusion devices.

In-Situ visual reconstruction of strut profiles in pulsed wire arc additive manufacturing of lattice structures

ABSTRACT The wire arc additive manufacturing (WAAM) process often results in geometric inaccuracies in the produced struts, highlighting the need for in-situ monitoring. Industrial cameras struggle to capture accurate images due to interference from arc light and metal radiation. This study introduces a real-time visual reconstruction method that leverages regions of interest (ROI) to enhance profile accuracy. Initially, the melt pool is analyzed and segmented from a series of frames to establish an initial strut profile. This profile then serves as the ROI for segmenting the solidified weld bead regions, yielding a more precise strut profile. Comparative analysis shows that the proposed method achieves a high Intersection Over Union (IOU) score of 0.911 and an Average Symmetric Surface Distance (ASD) error of 0.355 mm, demonstrating both accuracy and robustness. Additionally, the inclination angle and diameter are extracted from the reconstructed profiles.

Efficient and Accurate Semi-Automatic Neuron Tracing with Extended Reality.

Neuron tracing, alternately referred to as neuron reconstruction, is the procedure for extracting the digital representation of the three-dimensional neuronal morphology from stacks of microscopic images. Achieving accurate neuron tracing is critical for profiling the neuroanatomical structure at single-cell level and analyzing the neuronal circuits and projections at whole-brain scale. However, the process often demands substantial human involvement and represents a nontrivial task. Conventional solutions towards neuron tracing often contend with challenges such as non-intuitive user interactions, suboptimal data generation throughput, and ambiguous visualization. In this paper, we introduce a novel method that leverages the power of extended reality (XR) for intuitive and progressive semi-automatic neuron tracing in real time. In our method, we have defined a set of interactors for controllable and efficient interactions for neuron tracing in an immersive environment. We have also developed a GPU-accelerated automatic tracing algorithm that can generate updated neuron reconstruction in real time. In addition, we have built a visualizer for fast and improved visual experience, particularly when working with both volumetric images and 3D objects. Our method has been successfully implemented with one virtual reality (VR) headset and one augmented reality (AR) headset with satisfying results achieved. We also conducted two user studies and proved the effectiveness of the interactors and the efficiency of our method in comparison with other approaches for neuron tracing.

Physics-guided deep learning-based real-time image reconstruction of Fourier-domain optical coherence tomography

In this paper, we introduce a physics-guided deep learning approach for high-quality, real-time Fourier-domain optical coherence tomography (FD-OCT) image reconstruction. Unlike traditional supervised deep learning methods, the proposed method employs unsupervised learning. It leverages the underlying OCT imaging physics to guide the neural networks, which could thus generate high-quality images and provide a physically sound solution to the original problem. Evaluations on synthetic and experimental datasets demonstrate the superior performance of our proposed physics-guided deep learning approach. The method achieves the highest image quality metrics compared to the inverse discrete Fourier transform (IDFT), the optimization-based methods, and several state-of-the-art methods based on deep learning. Our method enables real-time frame rates of 232 fps for synthetic images and 87 fps for experimental images, which represents significant improvements over existing techniques. Our physics-guided deep learning-based approach could offer a promising solution for FD-OCT image reconstruction, which potentially paves the way for leveraging the power of deep learning in real-world OCT imaging applications.

NeRF-based Localization and Meshing with Wearable Laser Scanning System: A Case Study in Underground Environment

Abstract. Due to the subterranean scene’s poor lighting conditions and variability of the environment, real-time localizing and meshing in complex underground scenes present a challenging task, with high-potential applications in mining and tunnel protection. In this work, we propose a method that combines SLAM and NeRF for mesh reconstruction in the underground environment with a wearable device. First, a LiDAR-Inertial odometry is used for pose estimation. The resulting poses and sequential laser frames are synchronized to generate a novel data structure, scan-block, which is crucial for improving efficiency and ensuring local precision. This structure is designed to enhance efficiency and ensure local precision. Finally, the generated scan-blocks are passed to the backend NeRF for real-time mesh reconstruction. The experiments are carried out in a complex underground space. The experimental results proved that this method achieved good results. The demo video can be found at https://youtu.be/_y1vbaW06EM?si= hFnAl12u-ffU933h.

Real-time equilibrium reconstruction by multi-task learning neural network based on HL-3 tokamak

Abstract A neural network model, EFITNN, has been developed capable of real-time magnetic equilibrium reconstruction based on HL-3 tokamak magnetic measurement signals. The model processes inputs from 68 channels of magnetic measurement data gathered from 1159 HL-3 experimental discharges, including plasmas current, loop voltage, and the poloidal magnetic fields measured by probes. The outputs of the model feature eight key plasmas parameters, alongside high-resolution ( 129 × 129 ) reconstructions of the toroidal current density J P and poloidal magnetic flux distributions Ψ rz . Moreover, the network’s architecture employs a multi-task learning structure, which enables the sharing of weights and mutual correction among different outputs, and leads to increase the model’s accuracy by up to 32%. The performance of EFITNN demonstrates remarkable consistency with the offline EFIT, achieving average R 2 = 0.941, 0.997 and 0.959 for eight plasmas parameters, Ψ rz and J P , respectively. The model’s robust generalization capabilities are particularly evident in its successful predictions of quasi-snowflake (QSF) divertor configurations and its adept handling of data from shot numbers or plasmas current intervals not previously encountered during training. Compared to numerical methods, EFITNN significantly enhances computational efficiency with average computation time ranging from 0.08 ms to 0.45 ms, indicating its potential utility in real-time isoflux control and plasmas profile management.

Improved Real-time 3D Reconstruction Method for Mixed Reality Telepresence

Improved Real-time 3D Reconstruction Method for Mixed Reality Telepresence

Real-time delivered dose assessment in carbon ion therapy of moving targets

Abstract Purpose:
Real-time adaptive particle therapy is being investigated as a means to maximize the treatment delivery accuracy. To react to dosimetric errors, a system for fast and reliable verification of the agreement between planned and delivered doses is essential. This study presents a clinically feasible, real-time 4D-dose reconstruction system, synchronized with the treatment delivery and motion of the patient, which can provide the necessary feedback on the quality of the delivery.
Methods:
A GPU-based analytical dose engine capable of millisecond dose calculation for carbon ion therapy has been developed and interfaced with the next generation of the Dose Delivery System (DDS) in use at Centro Nazionale di Adroterapia Oncologica (CNAO). The system receives the spot parameters and the motion information of the patient during the treatment and performs the reconstruction of the planned and delivered 4Ddoses. After each iso-energy layer, the results are displayed on a graphical user interface by the end of the spill pause of the synchrotron, permitting verification against the reference dose.
The framework has been verified experimentally at CNAO for a lung cancer case based on a virtual phantom 4DCT. The patient’s motion was mimicked by a moving Ionization Chambers (ICs) 2D-array.
Results:
For the investigated static and 4D-optimized treatment delivery cases, real time dose reconstruction was-achieved with an average pencil beam dose calculation speed up to more than one order of magnitude smaller than the spot delivery. The reconstructed doses have been benchmarked against offline log-file based dose reconstruction with the TRiP98 treatment planning system, as well as QA measurements with the ICs 2D-array, where an average gamma-index passing rate (3%/3mm) of 99.8% and 98.3%, respectively, were achieved.
Conclusion:
This work provides the first real-time 4D-dose reconstruction engine for carbon ion therapy. The framework integration with the CNAO DDS paves the way for a swift transition to the clinics.

Dynamic near-field and far-field radiation manipulation using a reprogrammable guided-wave-excited metasurface

The dynamic and integrated control of near- and far-field electromagnetic waves is essential for advancing emerging intelligent information technology. Metasurfaces, distinguished by their low-profile design, cost-effectiveness, and ease of fabrication, have successfully revolutionized various electromagnetic functions. However, current research on the dynamic integrated manipulation of near-field and far-field electromagnetic waves using a single metasurface remains relatively constrained, due to the complexity of element-level control, restricted dynamic tuning range, and tuning speed. Herein, we propose an element-level controlled, versatile, compact, and broadband platform allowing for the real-time electronic reconstruction of desired near/far-field electromagnetic wavefronts. This concept is achieved by precisely regulating the 1-bit amplitude coding pattern across a guided-wave-excited metasurface aperture loaded with PIN diodes, following our binary-amplitude holographic theory and modified Gerchberg–Saxton (G–S) algorithm. Consistent findings across calculations, simulations, and experiments highlight the metasurface’s robust performance in 2D beam scanning, frequency scanning, dynamic focusing lens, dynamic holography display, and 3D multiplexing holography, even under 1-bit control. This simplified and innovative metasurface architecture holds the promise of substantially propelling forthcoming investigations and applications of highly integrated, multifunctional, and intelligent platforms.

Digital-Twin virtual model real-time construction via spatio-temporal cascade reconstruction for full-field plastic deformation monitoring in metal tube bending manufacturing

Digital Twin (DT) technology, which integrates multi-source information, is extensively applied for comprehensive monitoring, predicting, and optimizing manufacturing processes. The core of this technology is the Digital Twin Virtual Model (DTVM), which acts as a virtual mirror reflecting the real-world physical processes within a digital environment. In processes like tube bending, constructing a real-time DTVM capable of capturing full-field plastic deformation is essential for monitoring and analyzing plastic behavior. However, existing DTVMs often simplify spatial resolution and suffer from temporal delays, impeding the accurate real-time depiction of the complete state of the real physical processes. To address this issue, a real-time DTVM construction method based on spatio-temporal cascade reconstruction was proposed for full-field plastic deformation monitoring in metal tube bending. Initially, a joint-section driven predefined bending tube coordinate representation method was introduced to comprehensively capture the entire plastic deformation area in bending tubes. Subsequently, through a physics-derived model integrating limited real-time data and plastic forming theory, a low-fidelity model with complete but low accuracy was obtained. This model was subsequently refined into a high-fidelity model with both completeness and high accuracy using the proposed FPDR-Net. To eliminate temporal lags, the concept of compensation for time-delay through prediction was introduced. The newly developed TSCR-Net was applied to leverage past data to predict the present state, thereby achieving real-time synchronization mapping between the physical process and the DTVM. Finally, the proposed real-time reconstruction method for monitoring was validated through a case study on the bending of a 6061-T6 tube. The accuracy of full-field plastic deformation reconstruction was compared to traditional algorithms and finite element methods. The experimental results demonstrated that the proposed approach is highly efficient for real-time and full-field plastic deformation monitoring.

Accelerating imaging research at large-scale scientific facilities through scientific computing.

To date, computed tomography experiments, carried-out at synchrotron radiation facilities worldwide, pose a tremendous challenge in terms of the breadth and complexity of the experimental datasets produced. Furthermore, near real-time three-dimensional reconstruction capabilities are becoming a crucial requirement in order to perform high-quality and result-informed synchrotron imaging experiments, where a large amount of data is collected and processed within a short time window. To address these challenges, we have developed and deployed a synchrotron computed tomography framework designed to automatically process online the experimental data from the synchrotron imaging beamlines, while leveraging the high-performance computing cluster capabilities to accelerate the real-time feedback to the users on their experimental results. We have, further, integrated it within a modern unified national authentication and data management framework, which we have developed and deployed, spanning the entire data lifecycle of a large-scale scientific facility. In this study, the overall architecture, functional modules and workflow design of our synchrotron computed tomography framework are presented in detail. Moreover, the successful integration of the imaging beamlines at the Shanghai Synchrotron Radiation Facility into our scientific computing framework is also detailed, which, ultimately, resulted in accelerating and fully automating their entire data processing pipelines. In fact, when compared with the original three-dimensional tomography reconstruction approaches, the implementation of our synchrotron computed tomography framework led to an acceleration in the experimental data processing capabilities, while maintaining a high level of integration with all the beamline processing software and systems.

Real-Time Dense Visual SLAM with Neural Factor Representation

Developing a high-quality, real-time, dense visual SLAM system poses a significant challenge in the field of computer vision. NeRF introduces neural implicit representation, marking a notable advancement in visual SLAM research. However, existing neural implicit SLAM methods suffer from long runtimes and face challenges when modeling complex structures in scenes. In this paper, we propose a neural implicit dense visual SLAM method that enables high-quality real-time reconstruction even on a desktop PC. Firstly, we propose a novel neural scene representation, encoding the geometry and appearance information of the scene as a combination of the basis and coefficient factors. This representation allows for efficient memory usage and the accurate modeling of high-frequency detail regions. Secondly, we introduce feature integration rendering to significantly improve rendering speed while maintaining the quality of color rendering. Extensive experiments on synthetic and real-world datasets demonstrate that our method achieves an average improvement of more than 60% for Depth L1 and ATE RMSE compared to existing state-of-the-art methods when running at 9.8 Hz on a desktop PC with a 3.20 GHz Intel Core i9-12900K CPU and a single NVIDIA RTX 3090 GPU. This remarkable advancement highlights the crucial importance of our approach in the field of dense visual SLAM.

Seeing is believing: An Augmented Reality application for Palaeolithic rock art

By developing new recording methodologies, current rock art studies generate a large amount of graphic information about sites (tracings, photographs, three-dimensional reproductions) providing visibility of this fragile and little-known heritage, whose accessibility is often difficult or impossible for the general public. In addition, many rock art depictions are challenging to observe, due to the very nature of the artistic entities (fine engravings or faded paintings in karst environments or open-air sites with poor or changing light conditions), or to conservation problems derived from natural factors such as erosion and geological and biological processes, as well as from anthropic factors. These conditions make rock art depictions nearly indistinguishable in many places and on many objects today, except for experts. This difficulty of accessing and visualising rock art heritage, located in fragile environments and often challenging places such as caves or difficult-to-reach open-air sites, makes the information and knowledge generated by investigation of this heritage asset difficult to transfer to society in general, which is frequently unaware of the priceless value of this heritage. The present study proposes generating several mechanisms to transfer the results of research, restitution and documentation of rock art to society in general. An AR (Augmented Reality) application has been developed using LiDAR (Light Detection and Ranging) technology to address current challenges in implementing AR technologies in low-light environments. So far, this app has been developed in a Proof-of-Concept project at Spanish archaeological sites such as Hornos de la Peña (Cantabria), Domingo García (Segovia) and La Salud (Salamanca). This application will be particularly interesting for sites currently visited with or without a guide, allowing user interactivity and real-time reconstruction, for example, of the visibility of graphic motifs.

Computationally Efficient IMplicit Training Strategy for UNrolled NEtworks (IMUNNE): A preliminary analysis using accelerated real-time cardiac cine MRI.

Highly-undersampled, dynamic MRI reconstruction, particularly in multi-coil scenarios, is a challenging inverse problem. Unrolled networks achieve state-of-the-art performance in MRI reconstruction but suffer from long training times and extensive GPU memory cost. In this work, we propose a novel training strategy for IMplicit UNrolled NEtworks (IMUNNE) for highly-undersampled, multi-coil dynamic MRI reconstruction. It formulates the MRI reconstruction problem as an implicit fixed-point equation and leverages gradient approximation for backpropagation, enabling training of deep architectures with fixed memory cost. This study represents the first application of implicit network theory in the context of real-time cine MRI. The proposed method is evaluated using a prospectively undersampled, real-time cine dataset using radial k-space sampling, comprising balanced steady-state free precession (b-SSFP) readouts. Experiments include a hyperparameter search, head-to-head comparisons with a complex U-Net (CU-Net) and an alternating unrolled network (Alt-UN), and an analysis of robustness under noise perturbations; peak signal-to-noise ratio, structural similarity index, normalized root mean-square error, spatio-temporal entropic difference, and a blur metric were used. IMUNNE produced significantly and slightly better image quality compared to CU-Net and Alt-UN, respectively. Compared with Alt-UN, IMUNNE significantly reduced training and inference times, making it a promising approach for highly-accelerated, multi-coil real-time cine MRI reconstruction. IMUNNE strategy successfully applies unrolled networks to image reconstruction of highly-accelerated, real-time radial cine MRI. Implicit training enables rapid, high-quality, and cost-effective CMR exams by reducing training and inference times and lowering memory cost associated with advanced reconstruction methods.

EchoSee: An Assistive Mobile Application for Real-Time 3D Environment Reconstruction and Sonification Supporting Enhanced Navigation for People with Vision Impairments.

Improving the quality of life for people with vision impairments has been an important goal in the research and design of assistive devices for several decades. This paper seeks to further that goal by introducing a novel assistive technology platform that leverages real-time 3D spatial audio to promote safe and efficient navigation for people who are blind or visually impaired (PVI). The presented platform, EchoSee, uses modern 3D scanning technology on a mobile device to construct a live, digital 3D map of a user's environment as they move about their surroundings. Spatialized, virtual audio sources (i.e., virtual speakers) are dynamically placed within the digital 3D scan of the world, providing the navigator with a real-time 3D stereo audio "soundscape." The digital 3D map, and its resultant soundscape, are continuously updated as the user moves about their environment. The generated soundscape is played back through headphones connected to the navigator's device. This paper details (1) the underlying technical components and how they were integrated to produce the mobile application that generates a dynamic soundscape on a consumer mobile device, (2) a methodology for analyzing navigation performance with the application, (3) the design and execution of a user study investigating the effectiveness of the presented system, and (4) a discussion of the results of that study along with a proposed future study and possible improvements. Altogether, this paper presents a novel software platform aimed at assisting individuals with vision impairments to navigate and understand spaces safely, efficiently, and independently and the results of a feasibility study analyzing the viability of the approach.

Navigation and Robotic Single-Position Prone LLIF: First Cases in Brazil

has been rapid technological advancement in navigation-guided minimally invasive surgery over the past two decades, making these advancements an invaluable aid for surgeons by essentially providing real-time virtual reconstruction of patient anatomy. The objectives of these navigation- and robot-guided procedures are to reduce the likelihood of neural and vascular injury, minimize hospitalization time, decrease bleeding and postoperative pain, shorten healing time, and lower infection rates. A unicentric, retrospective cohort study was conducted to evaluate the preoperative and postoperative clinical and radiographic outcomes of the first Latin American patients diagnosed with lumbar degenerative disease who underwent lumbar interbody fusion at the L4-L5 level via prone-position lateral lumbar interbody fusion-single position prone access. A total of 80 patients (40 assisted by fluoroscopy, 40 assisted by robotics) with 320 percutaneous pedicle screws were evaluated. The primary outcomes analyzed and compared were radiation exposure per screw (seconds), skin-to-skin operative time (minutes), and recovery time (days). Secondary outcomes included lumbar pain intensity (visual analog scale), reported functional disability (Oswestry Disability Index), and any potential complications. All secondary outcomes were collected at the postoperative time. Comparing minimally invasive spine interventions with free-hand instrumentation and robotic instrumentation, a statistically significant difference was identified in radiation exposure per screw and surgical time. The literature on Cirq Robotic is limited; however, minimally invasive spine surgery with robotic assistance appears advantageous in terms of radiation exposure and surgical time.

Spatiotemporal correlation enhanced real-time 4D-CBCT imaging using convolutional LSTM networks.

To enhance the accuracy of real-time four-dimensional cone beam CT (4D-CBCT) imaging by incorporating spatiotemporal correlation from the sequential projection image into the single projection-based 4D-CBCT estimation process. We first derived 4D deformation vector fields (DVFs) from patient 4D-CT. Principal component analysis (PCA) was then employed to extract distinctive feature labels for each DVF, focusing on the first three PCA coefficients. To simulate a wide range of respiratory motion, we expanded the motion amplitude and used random sampling to generate approximately 900 sets of PCA labels. These labels were used to produce 900 simulated 4D-DVFs, which in turn deformed the 0% phase 4D-CT to obtain 900 CBCT volumes with continuous motion amplitudes. Following this, the forward projection was performed at one angle to get all of the digital reconstructed radiographs (DRRs). These DRRs and the PCA labels were used as the training data set. To capture the spatiotemporal correlation in the projections, we propose to use the convolutional LSTM (ConvLSTM) network for PCA coefficient estimation. For network testing, when several online CBCT projections (with different motion amplitudes that cover the full respiration range) are acquired and sent into the network, the corresponding 4D-PCA coefficients will be obtained and finally lead to a full online 4D-CBCT prediction. A phantom experiment is first performed with the XCAT phantom; then, a pilot clinical evaluation is further conducted. Results on the XCAT phantom and the patient data show that the proposed approach outperformed other networks in terms of visual inspection and quantitative metrics. For the XCAT phantom experiment, ConvLSTM achieves the highest quantification accuracy with MAPE(Mean Absolute Percentage Error), PSNR (Peak Signal-to-Noise Ratio), and RMSE(Root Mean Squared Error) of 0.0459, 64.6742, and 0.0011, respectively. For the patient pilot clinical experiment, ConvLSTM also achieves the best quantification accuracy with that of 0.0934, 63.7294, and 0.0019, respectively. The quantification evaluation labels that we used are 1) the Mean Absolute Error (MAE), 2) the Normalized Cross Correlation (NCC), 3)the Structural Similarity Index Measurement(SSIM), 4)the Peak Signal-to-Noise Ratio (PSNR), 5)the Root Mean Squared Error(RMSE), and 6) the Absolute Percentage Error (MAPE). The spatiotemporal correlation-based respiration motion modeling supplied a potential solution for accurate real-time 4D-CBCT reconstruction.

Implementation of a real-time MSE system.

Motional Stark effect polarimetry is a key diagnostic for plasma fusion research since its usage on PBX-M. The MSE diagnostic measures the radial magnetic pitch angle profile in a plasma from a neutral beam by observation of Stark split D-alpha emission from atoms excited by collision with ions and electrons in the plasma. The pitch angle measurement is used with equilibrium reconstruction codes to determine the q-profile for studies of plasma stability, confinement, and transport. Historically, the algorithm was used in a post-processing fashion. The goal of our work was to apply this method in real time and pass the results to the plasma control system computer for real-time equilibrium reconstruction and control.

Applicability and potential of monitored reconstruction in computed tomography.

Monitored tomographic reconstruction (MTR) is a potentially powerful tool for dose and time reduction in computed tomography scanning. We are the first to study the issue of practical implementation of MTR protocols in current-generation real-life instruments. We propose an empirical quantitative model for calculating acquisition and reconstruction times. It is demonstrated that projection acquisition order has a significant impact on the time and dose of tomographic experiments. The new alternative acquisition most suitable for MTR protocols is proposed. To estimate the restrictions and scope of applicability for MTR four typical commercial setups are studied within a proposed model. We construct an experimental stand for achieving a real-time reconstruction, together with validation of the proposed acquisition time model. We demonstrate that real-time reconstruction may be implemented without slowing down an acquisition process. An optimization of reconstruction from partial data is proposed, which allowed the production of 385 and 440 reconstructions for standard and proposed acquisition orders correspondingly during a single acquisition of 512 projections. The results of the study demonstrate that with proposed optimizations MTR can be effectively utilized for practical applications using the current generation of existing setups in industrial and nano tomography fields.

A greedy regularized block Kaczmarz method for accelerating reconstruction in magnetic particle imaging

Objective. Magnetic particle imaging (MPI) is an emerging medical tomographic imaging modality that enables real-time imaging with high sensitivity and high spatial and temporal resolution. For the system matrix reconstruction method, the MPI reconstruction problem is an ill-posed inverse problem that is commonly solved using the Kaczmarz algorithm. However, the high computation time of the Kaczmarz algorithm, which restricts MPI reconstruction speed, has limited the development of potential clinical applications for real-time MPI. In order to achieve fast reconstruction in real-time MPI, we propose a greedy regularized block Kaczmarz method (GRBK) which accelerates MPI reconstruction. Approach. GRBK is composed of a greedy partition strategy for the system matrix, which enables preprocessing of the system matrix into well-conditioned blocks to facilitate the convergence of the block Kaczmarz algorithm, and a regularized block Kaczmarz algorithm, which enables fast and accurate MPI image reconstruction at the same time. Main results. We quantitatively evaluated our GRBK using simulation data from three phantoms at 20 dB, 30 dB, and 40 dB noise levels. The results showed that GRBK can improve reconstruction speed by single orders of magnitude compared to the prevalent regularized Kaczmarz algorithm including Tikhonov regularization, the non-negative Fused Lasso, and wavelet-based sparse model. We also evaluated our method on OpenMPIData, which is real MPI data. The results showed that our GRBK is better suited for real-time MPI reconstruction than current state-of-the-art reconstruction algorithms in terms of reconstruction speed as well as image quality. Significance. Our proposed method is expected to be the preferred choice for potential applications of real-time MPI.