Advances In Hardware Research Articles

MRI signatures of cortical microstructure in human development align with oligodendrocyte cell-type expression.

Neuroanatomical changes to the cortex during adolescence have been well documented using MRI, revealing ongoing cortical thinning and volume loss with age. However, the underlying cellular mechanisms remain elusive with conventional neuroimaging. Recent advances in MRI hardware and new biophysical models of tissue informed by diffusion MRI data hold promise for identifying the cellular changes driving these morphological observations. This study used ultra-strong gradient MRI to obtain high-resolution, in vivo estimates of cortical neurite and soma microstructure in sample of typically developing children and adolescents. Cortical neurite signal fraction, attributed to neuronal and glial processes, increased with age (mean R2 fneurite=.53, p<3.3e-11, 11.91% increase over age), while apparent soma radius decreased (mean R2 Rsoma=.48, p<4.4e-10, 1% decrease over age) across domain-specific networks. To complement these findings, developmental patterns of cortical gene expression in two independent post-mortem databases were analysed. This revealed increased expression of genes expressed in oligodendrocytes, and excitatory neurons, alongside a relative decrease in expression of genes expressed in astrocyte, microglia and endothelial cell-types. Age-related genes were significantly enriched in cortical oligodendrocytes, oligodendrocyte progenitors and Layer 5-6 neurons (pFDR<.001) and prominently expressed in adolescence and young adulthood. The spatial and temporal alignment of oligodendrocyte cell-type gene expression with neurite and soma microstructural changes suggest that ongoing cortical myelination processes contribute to adolescent cortical development. These findings highlight the role of intra-cortical myelination in cortical maturation during adolescence and into adulthood.

Automated mobile robots routing and job assignment in automated factory

In the era of Industry 4.0, smart manufacturing and automated factories require advanced software and hardware resources. The decisions on AMR routing and job assignment are two of the key issues in automated factories. In this paper, we investigate the key issues by establishing a mixed integer linear programming model to minimize the makespan for a batch of products. As the problem considers the joint optimization of AMR routing, job-to-AMR assignments, job-to-machine assignments, and job sequencing on machines, the proposed model is comprehensive but complex, with million integer variables and constraints. To tackle this complexity, we introduce a hybrid heuristic approach based on variable neighborhood search and adaptive large neighborhood search algorithms. Three accelerating tactics, two specific neighborhood structures, and six tailored operators are devised to handle large-scale instances efficiently. Remarkably, our metaheuristic can handle 280 jobs within 800 s, resulting in twice the efficiency achieved by traditional factories. Some managerial implications are also obtained based on sensitivity analysis, which may be potentially useful to increase the operational efficiency in automated factory management.

Quantum-attack-resilience OTP-based multi-factor mutual authentication and session key agreement scheme for mobile users

Due to rapid advancements in hardware and mobile communication technologies, the usage of various mobile-based online applications is increasing tremendously. However, security and privacy are two of the most essential features of wireless communication. Using a Mutual Authentication and Session Key Agreement (MASK) scheme, an authorized mobile user can login to a remote server over the Internet. In quantum contexts, many of the MASK schemes are not secure. This paper proposes a One-Time Password (OTP) and biometric-based Multi-Factor MASK (OTP-MF-MASK) scheme for mobile users. We used Peikert’s authentication and reconciliation mechanism, defined for the post-quantum environments. The OTP-MF-MASK scheme used a password, mobile device, biometric, and OTP as login credentials. To avoid the biometric acquisition problem, we used the fuzzy extractor in the OTP-MF-MASK scheme. We proved that the OTP-MF-MASK scheme is semantically secure in the Random Oracle Model (ROM) based on the hardness assumption of the Ring Learning With Errors (RLWE) problem. The OTP-MF-MASK scheme is compared with state-of-the-art schemes to justify the attack-resilience and computation efficiencies in quantum environments.

A Review of Recent Hardware and Software Advances in GPU-Accelerated Edge-Computing Single-Board Computers (SBCs) for Computer Vision.

Computer Vision (CV) has become increasingly important for Single-Board Computers (SBCs) due to their widespread deployment in addressing real-world problems. Specifically, in the context of smart cities, there is an emerging trend of developing end-to-end video analytics solutions designed to address urban challenges such as traffic management, disaster response, and waste management. However, deploying CV solutions on SBCs presents several pressing challenges (e.g., limited computation power, inefficient energy management, and real-time processing needs) hindering their use at scale. Graphical Processing Units (GPUs) and software-level developments have emerged recently in addressing these challenges to enable the elevated performance of SBCs; however, it is still an active area of research. There is a gap in the literature for a comprehensive review of such recent and rapidly evolving advancements on both software and hardware fronts. The presented review provides a detailed overview of the existing GPU-accelerated edge-computing SBCs and software advancements including algorithm optimization techniques, packages, development frameworks, and hardware deployment specific packages. This review provides a subjective comparative analysis based on critical factors to help applied Artificial Intelligence (AI) researchers in demonstrating the existing state of the art and selecting the best suited combinations for their specific use-case. At the end, the paper also discusses potential limitations of the existing SBCs and highlights the future research directions in this domain.

Ultra-low-field magnetic resonance angiography at 0.05 T: A preliminary study.

We aim to explore the feasibility of head and neck time-of-flight (TOF) magnetic resonance angiography (MRA) at ultra-low-field (ULF). TOF MRA was conducted on a highly simplified 0.05 T MRI scanner with no radiofrequency (RF) and magnetic shielding. A flow-compensated three-dimensional (3D)gradient echo (GRE) sequence with a tilt-optimized nonsaturated excitation RF pulse, and a flow-compensated multislice two-dimensional (2D) GRE sequence, were implemented for cerebral artery and vein imaging, respectively. For carotid artery and jugular vein imaging, flow-compensated 2D GRE sequences were utilized with venous and arterial blood presaturation, respectively. MRA was performed on young healthy subjects. Vessel-to-background contrast was experimentally observed with strong blood inflow effect and background tissue suppression. The large primary cerebral arteries and veins, carotid arteries, jugular veins, and artery bifurcations could be identified in both raw GRE images and maximum intensity projections. The primary brain and neck arteries were found to be reproducible among multiple examination sessions. These preliminary experimental results demonstrated the possibility of artery TOF MRA on low-cost 0.05 T scanners for the first time, despite the extremely low MR signal. We expect to improve the quality of ULF TOF MRA in the near future through sequence development and optimization, ongoing advances in ULF hardware and image formation, and the use of vascular T1 contrast agents.

The application of Verilog in the development of casual games

Verilog is a hardware description language (HDL) that is widely used in digital circuit design and simulation. Its development is closely related to computer science and electrical engineering. Verilog gained popularity in the early 1980s as digital circuit designs became increasingly complex, requiring more efficient circuit design and verification tools. At the same time, rapid advances in computer hardware also stimulated the demand for digital circuit design languages. Furthermore, the popularity and adoption of Verilog highlight the growing necessity for digitisation, automation, and intelligence in modern society. As digital technology continues to advance across various industries, the need for effective and dependable digital circuit design languages is also increasing. This paper delves into the complex process of recreating the timeless arcade classic Pac-Man on the Spartan 3E FPGA platform using hardware description and digital circuit techniques and the Verilog programming language. Through a comprehensive review of existing literature and research, this study investigates the fusion of traditional game design principles with state-of-the-art hardware programming methods, demonstrating the seamless integration of software-driven game mechanics with hardware-based implementation. Through careful design and coding strategies, Pac-Man's basic functionality, such as maze traversal, ghost AI, and pellet consumption, is faithfully replicated using Verilog modules customized for the Spartan 3E FPGA board. By bridging the realms of game development and hardware engineering, this paper not only showcases the versatility of Field Programmable Gate Array (FPGA) technology in entertainment applications but also underscores the interdisciplinary nature of modern computing endeavours.

HUB3D: Intelligent Manufacturing HUB System

HUB3D represents a cutting-edge solution for managing and operating a 3D printer farm through the integration of advanced hardware and software. It features intuitive, responsive interfaces that support seamless interaction across various devices. Leveraging cloud services ensures the system’s stability, security, and scalability, enabling users from diverse locations to effortlessly upload and manage their 3D printing projects. The hardware component includes a purpose-built rack capable of housing up to four 3D printers, each synchronized and managed by a manipulator arm controlled via Raspberry Pi technology. This setup facilitates continuous operation and high automation, optimizing production efficiency and reducing downtime significantly. This integrated approach positions HUB3D at the forefront of additive manufacturing management. By combining robust hardware capabilities with sophisticated software functionalities and cloud integration, the system offers unparalleled advantages. It supports continuous manufacturing processes, enhances workflow efficiency, and enables remote monitoring and management of printing operations. Overall, HUB3D’s innovative design and comprehensive features cater to both individual users and businesses seeking to streamline 3D printing workflows. With scalability, automation, and remote accessibility at its core, HUB3D represents a pivotal advancement in modern manufacturing technology, promising increased productivity and operational flexibility in the realm of additive manufacturing.

Comparative Analysis of Four Different Intraoral Scanners: An In Vitro Study.

(1) Background: Intraoral scanners undergo rapid advancements in hardware and software, prompting frequent updates by manufacturers. (2) Aim: This study aimed to quantitatively assess the precision of full dental arch digital impressions obtained from four different intraoral scanners: Trios 5-3SHAPE, Copenhagen, Denmark, CEREC Primescan- Dentsply Sirona, New York, NY, USA, Planmeca Emerald S-Planmeca Oy, Helsinki, Finland, and Medit i700-Medit Corp, Seoul, Republic of Korea. (3) Methods: A maxillary virtual dental model (digital master model) was created in accordance with ISO standard 20896-1. Subsequently, a 3D-printed model was obtained from the master model's STL file and scanned 15 times consecutively with each scanner. STL files were aligned with the master model's STL using Medit Link-Medit Design software v.3.1.0. The accuracy was evaluated by measuring deviations in micrometers between each scanner's scans and the master model. (4) Results: The study revealed variations in accuracy ranging from 23 to 32 µm across scans of the same dental arch, irrespective of the scanner used and scanning strategy employed. The anterior regions exhibited higher precision (Mean Absolute Deviation of 112 µm) compared to the posterior regions (Mean Absolute Deviation of 127 µm). Trios 5 demonstrated the smallest deviation (average 112 µm), indicating superior accuracy among the scanners tested. Emerald S and Medit i700 exhibited balanced performance (average 117 µm and 114 µm, respectively), while Primescan consistently displayed high deviation (average 127 µm). (5) Conclusions: Based on clinically accepted thresholds for accuracy in intraoral scanning, which are typically 200 µm for full arch scans, Trios 5 surpasses these benchmarks with its average deviation falling within the 200 µm range. Emerald S and Medit i700 also meet these standards, while Primescan, although showing high overall deviation, approaches the upper limit of clinical acceptability. Considering the limitations of an in vitro investigation, the findings demonstrate that each intraoral scanner under evaluation is capable of reliably and consistently capturing a full arch scan for dentate patients.

The marketing on Big 4 websites of Big Data Analytics in the external audit: Evidence and consequences

Leveraging ubiquitous digital data, advanced hardware, and sophisticated software, Big Data Analytics (BDA) enables unprecedented in-depth examination of business processes. This paper investigates how the Big 4 accounting firms promote their use of technology-enabled analytics in auditing practices on their official websites. We find that all the Big 4 market their audit analytics as offering operational insights that add value for clients. Historically, auditors have sought to share valuable perspectives gained during engagements beyond verifying that clients are in compliance with accounting principles. However, providing these value-adding insights is transitioning from a supplementary benefit to an essential selling point of audits. This behavior likely stems from BDA technology’s inherent duality–facilitating regulatory compliance and business intelligence. Incorporating artificial intelligence into audit firms’ technological arsenal will further enhance their ability to deliver client-valued insights. These developments necessitate further research into how the BDA application impacts auditor independence.

Semantic guidance incremental network for efficiency video super-resolution

AbstractIn video streaming, bandwidth constraints significantly affect client-side video quality. Addressing this, deep neural networks offer a promising avenue for implementing video super-resolution (VSR) at the user end, leveraging advancements in modern hardware, including mobile devices. The principal challenge in VSR is the computational intensity involved in processing temporal/spatial video data. Conventional methods, uniformly processing entire scenes, often result in inefficient resource allocation. This is evident in the over-processing of simpler regions and insufficient attention to complex regions, leading to edge artifacts in merged regions. Our innovative approach employs semantic segmentation and spatial frequency-based categorization to divide each video frame into regions of varying complexity: simple, medium, and complex. These are then processed through an efficient incremental model, optimizing computational resources. A key innovation is the sparse temporal/spatial feature transformation layer, which mitigates edge artifacts and ensures seamless integration of regional features, enhancing the naturalness of the super-resolution outcome. Experimental results demonstrate that our method significantly boosts VSR efficiency while maintaining effectiveness. This marks a notable advancement in streaming video technology, optimizing video quality with reduced computational demands. This approach, featuring semantic segmentation, spatial frequency analysis, and an incremental network structure, represents a substantial improvement over traditional VSR methodologies, addressing the core challenges of efficiency and quality in high-resolution video streaming.

Integrating Artificial Intelligence Into the Visualization and Modeling of Three-Dimensional Anatomy in Pediatric Surgical Patients

BackgroundPediatric surgeons often treat patients with complex anatomical considerations due to congenital anomalies or distortion of normal structures by solid organ tumors. There are multiple applications for three-dimensional visualization of these structures based on cross-sectional imaging. Recently, advances in artificial intelligence (AI) applications and graphics hardware have made rapid 3D modelling of individual structures within the body accessible to surgeons without sophisticated and expensive hardware. In this report, we provide an overview of these applications and their uses in preoperative planning for pediatric surgeons. MethodsDeidentified DICOM files containing cross-sectional imaging of preoperative pediatric surgery patients were loaded from an institutional PACS database onto a secure PC with dedicated graphics and AI hardware (NVIDIA Geforce RTX 4070 laptop GPU). Visualization was obtained using an open-source imaging platform (3D Slicer). AI extensions to the platform were utilized to delineate the anatomy of interest. ResultsSegmentations of skeletal and visceral structures within a scan were obtained using the TotalSegmentator extension with an average processing time under 5 min. Additional AI modules were utilized for providing detailed mapping of the airways (AirwaySegmentation), lungs (Chest Imaging Platform), liver (SlicerLiver), or vasculature (SlicerVMTK). Other extensions were used for delineation of tumors within the hepatic parenchyma (MONAI Auto3DSeg) and hepatic vessels (RVesselX). ConclusionAI algorithms for image interpretation and processors dedicated to AI functions have significantly decreased the technical and financial requirements for obtaining detailed three-dimensional images of patient anatomy. Models obtained using AI algorithms have potential applications in preoperative planning, surgical simulation, patient education, and training. Level of EvidenceV, Case Series, Description of Technique.

EnergAt: Fine-Grained Energy Attribution for Multi-Tenancy

In the post-Moore's Law era, relying solely on hardware advancements for automatic performance gains is no longer feasible without increased energy consumption, due to the end of Dennard scaling. Consequently, computing accounts for an increasing amount of global energy usage, contradicting the objective of sustainable computing. The lack of hardware support and the absence of a standardized, software-centric method for the precise tracing of energy provenance exacerbates the issue. Aiming to overcome this challenge, we argue that fine-grained software energy attribution is attainable, even with limited hardware support. To support our position, we present a thread-level, NUMA-aware energy attribution method for CPU and DRAM in multi-tenant environments. The evaluation of our prototype implementation, EnergAt, demonstrates the validity, effectiveness, and robustness of our theoretical model, even in the presence of the noisy-neighbor effect. We envisage a sustainable cloud environment and emphasize the importance of collective efforts to improve software energy efficiency.

Quantum Machine Learning: The Superhero That Classical Machine Learning Never Knew It Needed

Quantum Machine Learning (QML) is an emerging interdisciplinary field that combines the principles of quantum mechanics and machine learning to develop algorithms that can potentially outperform classical algorithms in certain tasks. QML leverages the unique properties of quantum systems, such as superposition and entanglement, to process information in ways that are not possible with classical computers. This paper provides a comprehensive overview of QML, including its principles, algorithms, and applications. We focus particularly on supervised learning methods, which involve training a quantum model on labeled data to make predictions on new, unseen data. We discuss the potential of QML to revolutionize various domains, such as finance, chemistry, and materials science, and highlight the challenges associated with the development and implementation of QML algorithms, including the need for more advanced quantum hardware and software. This paper aims to provide a clear understanding of the current state of QML research and its potential impact on future computational capabilities.

Experimental methods in chemical engineering: Monte Carlo

AbstractMonte Carlo (MC) methods employ a statistical approach to evaluate complex mathematical models that lack analytical solutions and assess their uncertainties. To this end, techniques such as Markov chain Monte Carlo (MCMC), bootstrap, and sequential MC methods repeat the same operations over a specified range of conditions. Consequently, both the frequentist and Bayesian statistical approaches are computationally intensive, depending on the problem formulation. Improving sampling techniques and identifying sources of error reduce the computational demand but do not guarantee that the solution reaches the global optimum. Moreover, efficient algorithms and advances in hardware continue to decrease computation time. MC methods are applicable to a plethora of problems ranging from medicine to computational chemistry, economics, and industrial safety, making them integral to the ongoing industrial digitalization by evaluating the quality of applied models. In chemical engineering, MC simulations are used in four clusters of research: design, systems, and optimization; molecular simulation, including CO2 and carbon capture; adsorption and molecular dynamics; and thermodynamics. There is limited cross‐referencing between the design cluster and the other three, which presents an interesting area for future research. This mini‐review presents two applications within chemical engineering: emissions and energy forecasting.

RockDNet: Deep Learning Approach for Lithology Classification

Analyzing rock and underground layers is known as drill core lithology. The extracted core sample helps not only in exploring the core properties but also reveals the lithology of the entire surrounding area. Automating rock identification from drill cuttings is a key element for efficient reservoir characterization, replacing the current subjective and time-consuming manual process. The recent advancements in computer hardware and deep learning technology have enabled the automatic classification of various applications, and lithology is not an exception. This work aims to design an automated method for rock image classification using deep learning technologies. A novel CNN (Convolution Neural Network) is proposed for lithology classification in addition to thorough comparison with benchmark CNN models. The proposed CNN model has the advantageous of having very low complexity while maintaining high accuracy. Experimental results on rock mages taken from the “digitalrocksportal” database demonstrate the ability of the proposed method to classify three classes, carbonate, sandstone and shale rocks, with high accuracy, and comparisons with related work demonstrated the efficiency of the proposed model, with more than 98% saving in parameters.

Radiation Techniques for Tracking the Progress of the Hydrometallurgical Leaching Process: A Case Study of Mn and Zn

With advancements in hardware and software, non-destructive radiometric analytical methods have become popular in a wide range of applications. A typical case is the study of the leaching process of metals from mineral ores and mine tailings. The objective of the current study was to develop a radiometric method based on neutron activation analysis (NAA), in particular, delayed gamma neutron activation analysis (DGNAA), to monitor the process of Mn and Zn leaching from Ti ore, Cu mine tailings, and Zn-Pb mine tailings. The DGNAA method was performed using a neutron source: a deuterium-tritium (D-T) neutron generator for Mn and a MARIA research nuclear reactor for Zn. Laboratory-scale Mn leaching from Ti ores, Cu tailings, and Zn-Pb tailings was investigated using delayed gamma-rays of 56Mn (half-life of 2.6 h). The dissolution efficiencies of Mn were found to increase with interaction time and HCl concentration (1 to 5 M) and to vary with the leaching temperature (22.5 to 110 °C). Such results were found to agree with those obtained by total reflection X-ray fluorescence (TXRF) spectrometry for the same samples. 65Zn (half-life of 244 days) was chosen to investigate real-time/online leaching of Zn in Ti ore, Cu tailings, and Zn-Pb tailings. During online monitoring, Zn recovery was also reported to increase with increased leaching time. After approximately 300 min of leaching, 80%, 79%, and 53% recovery of Zn in Zn-Pb tailings, Ti ore, and Cu tailings, respectively, were reported. Theoretically, developed mathematical prediction models for 65Zn radiotracer analysis showed that the spherical diffusion model requires much less time to attain saturation compared to the linear diffusion model. The results of NAA for Zn were compared with those obtained by handheld X-ray fluorescence (handheld-XRF) and TXRF analysis. The analyzed samples encompassed leached Ti ore, Cu tailings, and Zn-Pb tailings which were subjected to different conditions of leaching time, temperature, and HCl concentrations. The XRF analysis confirmed that the leaching efficiencies of Zn rise with the increase in leaching time and HCl concentration and fluctuate with leaching temperature. The developed approach is important and can be applied in laboratories and industrial setups for online monitoring of the recovery of any element whose isotopes can be activated using neutrons. The efficiency of the metal-recovery process has a direct impact on the normal operation and economic advantages of hydrometallurgy.

A handheld fluorescent lateral flow immunoassay platform for highly sensitive point-of-care detection of methamphetamine and tramadol

The escalating issue of drug abuse poses a significant threat to public health and societal stability worldwide. An on-site drug detection platform is vital for combating drug abuse and trafficking, as it eliminates the need for additional tools, extensive processes, or specialized training. Therefore, it is imperative to develop a fast, sensitive, non-invasive, and reliable multiplex drug testing platform. In this study, we have presented a silica core@dual quantum dot-shell nanocomposite (SI/DQD)-based fluorescent lateral flow immunoassay (LFIA) platform for the highly sensitive and simultaneous point-of-care (POC) detection of methamphetamine (MET) and tramadol (TR). A 3D-printed attachment was designed to integrate optical and electrical components, facilitating the miniaturization of the instrument and reducing both cost and complexity. The device's advanced hardware and effective fluorescence extraction algorithm with waveform reconstruction enable swift, automatic noise reduction and data analysis. SI/DQD nanocomposites were utilized as fluorescent nanotags in the LFIA strips due to their outstanding luminous efficiency and robustness. This LFIA platform achieves impressive detection limits (LODs) of 0.11 ng mL−1 for MET and 0.017 ng mL−1 for TR. The method has also successfully detected MET and TR in complex biological samples, demonstrating its practical application capabilities. The proposed fluorescent LFIA platform, based on SI/DQD technology, holds significant promise for the swift and accurate POC detection of these substances. Its affordability, compact size, and excellent analytical performance make it suitable for on-site drug testing, including at borders and roadside checks, and open up new possibilities for the design and implementation of drug testing methods.

E-Banking Technology: A Comprehensive Study on Customer Satisfaction and Bank Services

This paper explores the dynamic landscape of e-banking technology, emphasizing advancements in hardware, software, and networks to deliver innovative solutions. It highlights moderate e-banking adoption among surveyed individuals, underscoring the crucial role of customer satisfaction in banking services. Despite this, critical gaps are identified, motivating the study to provide a detailed analysis of responses concerning cloud services, bank system security, service quality, and e-learning initiatives. With meticulous data collection from 125 respondents, primarily students from Tangerang actively using e-banking, the research investigates the frequency and patterns of e-banking usage. Through comprehensive descriptive analysis, the study offers insights into customer satisfaction in the e-banking domain and sets the stage for future causal research. Its ultimate goal is to enhance comprehension of the factors influencing customer satisfaction in e-banking.

Internet street view image fusion method using convolutional neural network

The use of image fusion technology in the area of information processing is continuing to advance in depth thanks to ongoing hardware advancements and related research. An enhanced convolutional neural network approach is developed to fuse visible and infrared images, and image pre-processing is carried out utilising an image alignment method with edge detection in order to gain more accurate and trustworthy image information. The performance of the fast wavelet decomposition, convolutional neural network, and modified convolutional neural network techniques is compared and examined using four objective assessment criteria. The experimental findings demonstrated that the picture alignment was successful with an offset error of fewer than 3 pixels in the horizontal direction and an angle error of less than 0.3∘ in both directions. The revised convolutional neural network method increased the information entropy, mean gradient, standard deviation, and edge detection information by an average of 46.13%, 39.40%, 19.91%, and 3.72%. The runtime of the modified approach was lowered by 19.42% when compared to the convolutional neural network method, which enhanced the algorithm’s performance and boosted the effectiveness of picture fusion. The image fusion accuracy reached 98.61%, indicating that the method has better fusion performance and is of practical value for improving image fusion quality.

Accelerated musculoskeletal magnetic resonance imaging with deep learning-based image reconstruction at 0.55 T-3 T

Magnetic resonance imaging (MRI) is acentral component of musculoskeletal imaging. However, long image acquisition times can pose practical barriers in clinical practice. MRI is the established modality of choice in the diagnostic workup of injuries and diseases of the musculoskeletal system due to its high spatial resolution, excellent signal-to-noise ratio (SNR), and unparalleled soft tissue contrast. Continuous advances in hardware and software technology over the last few decades have enabled four-fold acceleration of 2D turbo-spin-echo (TSE) without compromising image quality or diagnostic performance. The recent clinical introduction of deep learning (DL)-based image reconstruction algorithms helps to minimize further the interdependency between SNR, spatial resolution and image acquisition time and allows the use of higher acceleration factors. The combined use of advanced acceleration techniques and DL-based image reconstruction holds enormous potential to maximize efficiency, patient comfort, access, and value of musculoskeletal MRI while maintaining excellent diagnostic accuracy. Accelerated MRI with DL-based image reconstruction has rapidly found its way into clinical practice and proven to be of added value. Furthermore, recent investigations suggest that the potential of this technology does not yet appear to be fully harvested. Deep learning-reconstructed fast musculoskeletal MRI examinations can be reliably used for diagnostic work-up and follow-up of musculoskeletal pathologies in clinical practice.