Super-resolution Research Articles

G-Protein Signaling in Alzheimer's Disease: Spatial Expression Validation of Semi-Supervised Deep Learning Based Computational Framework.

Systemic study of pathogenic pathways and interrelationships underlying genes associated with Alzheimer's disease (AD) facilitates the identification of new targets for effective treatments. Recently available large-scale multi-omics datasets provide opportunities to use computational approaches for such studies. Here, we devised a novel disease gene identification (digID) computational framework that consists of a semi-supervised deep learning classifier to predict AD-associated genes and a protein-protein interaction (PPI) network-based analysis to prioritize the importance of these predicted genes in AD. digID predicted 1,529 AD-associated genes and revealed potentially new AD molecular mechanisms and therapeutic targets including GNAI1 and GNB1, two G-protein subunits that regulate cell signaling, and KNG1, an upstream modulator of CDC42 small G-protein signaling and mediator of inflammation and candidate coregulator of amyloid precursor protein (APP). Analysis of mRNA expression validated their dysregulation in AD brains but further revealed the significant spatial patterns in different brain regions as well as among different sub-regions of frontal cortex and hippocampi. Super-resolution STochastic Optical Reconstruction Microscopy (STORM) further demonstrated their subcellular co-localization and molecular interactions with APP in a transgenic mouse model of both sexes with AD-like mutations. These studies support the predictions made by digID while highlighting the importance of concurrent biological validation of computationally identified gene clusters as potential new AD therapeutic targets.Significance Statement Powerful computational approaches such as machine learning (ML) can interrogate large-scale multi-omics datasets to predict disease-associated genes unbiasedly via systemic study. This study presents a new disease gene identification (digID) computational framework using semi-supervised deep learning classifier. Empowered by the super-resolution imaging and the spatial biology paradigm, we further revealed that the ML model predicted AD-related G-protein signaling is subject to spatial expression dysregulation. Therefore, computational discoveries require independent biological validation to yield medical insights and our data highlight three novel G-protein genes and their signaling networks to be potential new AD therapeutic targets.

Optimization of Sparse Camera Array Arrangement using Grid-based Method

—This study explores the application of multi-camera array technology in super-resolution (SR) imaging system. We propose an innovative method based on grid representation to optimize camera arrangements using sparse Gaussian processes and variational inference. This approach significantly enhances the image reconstruction quality of sparse camera arrays. Unlike conventional techniques that provide only qualitative conclusions, our grid-based method precisely optimizes camera positions and effectively simulates the impact of assembly errors. The optimized camera arrangement substantially improves the SR reconstruction quality of sparse array imaging systems, reducing contour jaggedness and high-frequency aliasing. Extensive simulations and experimental validations confirm the robustness and practical applicability of our method. The results demonstrate that the optimized camera arrangements can achieve high-resolution imaging with enhanced robustness against assembly errors, indicating their potential for various applications such as biological microscopy, remote sensing, and smartphone photography. This work presents a new and effective strategy for designing sparse camera array imaging systems, offering significant improvements in both image quality and system reliability.

Four-frame pixel super-resolution method for lensless imaging systems

Lensless imaging systems have gained significant attention recently due to their advantages in terms of reduced size and weight compared to traditional lens-based systems. However, like other imaging methods, lensless imaging encounters challenges in resolving scenes with more details. In this article, we propose a novel four-frame super-resolution method specifically tailored for lensless imaging systems. Our approach shares similarities with previous lensless imaging systems, involving a sensor and a modulation device placed in front of the image sensor. We develop an explicit degradation downsampling model with sub-pixel shifts and provide the solution to corresponding inverse problem, may offering valuable guidance for other super-resolution imaging algorithms based on spatial displacements. By applying random lateral sub-pixel shifts, acquiring four low-resolution (LR) images, and fusing their spatial information, we achieve high-resolution (HR) sensor recordings, enabling super-resolution reconstruction of the imaging scene. Numerical simulations demonstrate approximately an improvement in spatial resolution compared to single-measurement methods. Furthermore, we evaluate the performance of our method across various lensless imaging systems utilizing different masks, validating its versatility and effectiveness in achieving higher resolution outcomes. Experimental results also support our proposed scheme's ability to achieve higher spatial resolution reconstruction in a real system.

Kidney Stone Detection based on Improved YOLOv7 with Attention Module and Super Resolution Techniques Under Limited Training Samples

Kidney Stone Detection based on Improved YOLOv7 with Attention Module and Super Resolution Techniques Under Limited Training Samples

HiExM: high-throughput expansion microscopy enables scalable super-resolution imaging.

Expansion microscopy (ExM) enables nanoscale imaging using a standard confocal microscope through the physical, isotropic expansion of fixed immunolabeled specimens. ExM is widely employed to image proteins, nucleic acids, and lipid membranes in single cells; however, current methods limit the number of samples that can be processed simultaneously. We developed High-throughput Expansion Microscopy (HiExM), a robust platform that enables expansion microscopy of cells cultured in a standard 96-well plate. Our method enables ~4.2x expansion of cells within individual wells, across multiple wells, and between plates. We also demonstrate that HiExM can be combined with high-throughput confocal imaging platforms to greatly improve the ease and scalability of image acquisition. As an example, we analyzed the effects of doxorubicin, a known cardiotoxic agent, on human cardiomyocytes (CMs) as measured by Hoechst signal across the nucleus. We show a dose dependent effect on nuclear DNA that is not observed in unexpanded CMs, suggesting that HiExM improves the detection of cellular phenotypes in response to drug treatment. Our method broadens the application of ExM as a tool for scalable super-resolution imaging in biological research applications.

Achieving Single Cell Acoustic Localisation with Deactivation Super Resolution.

Super-resolution optical microscopy enables optical imaging of cells, molecules and other biological structures beyond the diffraction limit. However, no similar method exists to super-resolve specific cells with ultrasound. Here we introduce Deactivation Super Resolution (DSR), an ultrasound imaging method that uses the acoustic deactivation of genetically encodable contrast agents to super-resolve individual cells with ultrasound as they navigate through structures that cannot be resolved by conventional imaging methods. DSR takes advantage of gas vesicles, which are air-filled sub-micron protein particles that can be expressed in genetically engineered cells to produce ultrasound contrast. Our experimental results show that DSR can distinguish sub-wavelength microstructures that standard B-mode ultrasound images fail to resolve by super- localizing individual mammalian cells. This study provides a proof of concept for the potential of DSR to serve as a super- resolution ultrasound technique for individual cell localization, opening new horizons in the field.

Dual-Path Large Kernel Learning and Its Applications in Single-Image Super-Resolution.

To enhance the performance of super-resolution models, neural networks frequently employ module stacking. However, this approach inevitably results in an excessive proliferation of parameter counts and information redundancy, ultimately constraining the deployment of these models on mobile devices. To surmount this limitation, this study introduces the application of Dual-path Large Kernel Learning (DLKL) to the task of image super-resolution. Within the DLKL framework, we harness a multiscale large kernel decomposition technique to efficiently establish long-range dependencies among pixels. This network not only maintains excellent performance but also significantly mitigates the parameter burden, achieving an optimal balance between network performance and efficiency. When compared with other prevalent algorithms, DLKL exhibits remarkable proficiency in generating images with sharper textures and structures that are more akin to natural ones. It is particularly noteworthy that on the challenging texture dataset Urban100, the network proposed in this study achieved a significant improvement in Peak Signal-to-Noise Ratio (PSNR) for the ×4 upscaling task, with an increase of 0.32 dB and 0.19 dB compared with the state-of-the-art HAFRN and MICU networks, respectively. This remarkable result not only validates the effectiveness of the present model in complex image super-resolution tasks but also highlights its superior performance and unique advantages in the field.

Overview of the super-resolution and advanced microscopy imaging session at the 21st IUPAB and the 62nd Biophysics Society of Japan joint congress

Overview of the super-resolution and advanced microscopy imaging session at the 21st IUPAB and the 62nd Biophysics Society of Japan joint congress

Discovery of Limb Brightening in the Parsec-scale Jet of NGC 315 through Global Very Long Baseline Interferometry Observations and Its Implications for Jet Models

We report the first observation of the nearby giant radio galaxy NGC 315 using a global very long baseline interferometry (VLBI) array consisting of 22 radio antennas located across five continents, including high-sensitivity stations, at 22 GHz. Utilizing the extensive u v-coverage provided by the array, coupled with the application of a recently developed superresolution imaging technique based on the regularized maximum-likelihood method, we were able to transversely resolve the NGC 315 jet at parsec scales for the first time. Previously known for its central ridge-brightened morphology at similar scales in former VLBI studies, the jet now clearly exhibits a limb-brightened structure. This finding suggests an inherent limb brightening that was not observable before due to limited angular resolution. Considering that the jet is viewed at an angle of ∼50°, the observed limb brightening is challenging to reconcile with the magnetohydrodynamic models and simulations, which predict that the Doppler-boosted jet edges should dominate over the nonboosted central layer. The conventional jet model that proposes a fast spine and a slow sheath with uniform transverse emissivity may pertain to our observations. However, in this model, the relativistic spine would need to travel at speeds of Γ ≳ 6.0–12.9 along the deprojected jet distance of (2.3–10.8) × 103 gravitational radii from the black hole. We propose an alternative scenario that suggests higher emissivity at the jet boundary layer, resulting from more efficient particle acceleration or mass loading onto the jet edges, and consider prospects for future observations with even higher angular resolution.

Image restoration in frequency space using complex-valued CNNs.

Real-valued convolutional neural networks (RV-CNNs) in the spatial domain have outperformed classical approaches in many image restoration tasks such as image denoising and super-resolution. Fourier analysis of the results produced by these spatial domain models reveals the limitations of these models in properly processing the full frequency spectrum. This lack of complete spectral information can result in missing textural and structural elements. To address this limitation, we explore the potential of complex-valued convolutional neural networks (CV-CNNs) for image restoration tasks. CV-CNNs have shown remarkable performance in tasks such as image classification and segmentation. However, CV-CNNs for image restoration problems in the frequency domain have not been fully investigated to address the aforementioned issues. Here, we propose several novel CV-CNN-based models equipped with complex-valued attention gates for image denoising and super-resolution in the frequency domains. We also show that our CV-CNN-based models outperform their real-valued counterparts for denoising super-resolution structured illumination microscopy (SR-SIM) and conventional image datasets. Furthermore, the experimental results show that our proposed CV-CNN-based models preserve the frequency spectrum better than their real-valued counterparts in the denoising task. Based on these findings, we conclude that CV-CNN-based methods provide a plausible and beneficial deep learning approach for image restoration in the frequency domain.

A one-step protocol to generate impermeable fluorescent HaloTag substrates for in situ live cell application and super-resolution imaging.

Communication between cells is largely orchestrated by proteins on the cell surface, which allow information transfer across the cell membrane. Super-resolution and single-molecule visualization of these proteins can be achieved by genetically grafting HTP (HaloTag Protein) into the protein of interest followed by brief incubation of cells with a dye-HTL (dye-linked HaloTag Ligand). This approach allows for use of cutting-edge fluorophores optimized for specific optical techniques or a cell-impermeable dye-HTL to selectively label surface proteins without labeling intracellular copies. However, these two goals often conflict, as many high-performing dyes exhibit membrane permeability. Traditional methods to eliminate cell permeability face synthetic bottlenecks and risk altering photophysical properties. Here we report that dye-HTL reagents can be made cell-impermeable by inserting a charged sulfonate directly into the HTL, leaving the dye moiety unperturbed. This simple, one-step method requires no purification and is compatible with both the original HTL and second-generation HTL.2, the latter offering accelerated labeling. We validate such compounds, termed dye-SHTL ('dye shuttle') conjugates, in live cells via widefield microscopy, demonstrating exclusive membrane staining of extracellular HTP fusion proteins. In transduced primary hippocampal neurons, we label mGluR2, a neuromodulatory G protein-coupled receptor (GPCR), with dyes optimized for stimulated emission by depletion (STED) super-resolution microscopy, allowing unprecedented accuracy in distinguishing surface and receptors from those in internal compartments of the presynaptic terminal, important in neural communication. This approach offers broad utility for surface-specific protein labelling.

Rapid multispectral image identification of coal and gangue based on super-resolution reconstruction

Accurate coal and gangue separation is crucial for efficient coal utilization. Multispectral imaging (MSI) offers a promising approach but often suffers from limited resolution, hindering accurate identification. This study proposes, a novel method, to our knowledge, combining super-resolution (SR) reconstruction and machine learning to enhance coal and gangue identification in MSI. A spectral attention mechanism and an enhanced multi-scale residual network with GAN (SAM-EMSR-GAN) were developed and evaluated alongside four established SR methods: SRCNN, VDSR, ESRGAN, and DRMSFFN. MSI images of 300 coal and 300 gangue samples were reconstructed, using each method to compare their performance. SAM-EMSR-GAN achieved superior reconstruction, attaining the highest structural similarity index (SSIM) of 0.906 and peak signal-to-noise ratio (PSNR) of 32.97 at 4× magnification. The study further investigated the combination of the SR method with seven widely used classification models: CatBoost, random forest (RF), support vector machine (SVM), least squares support vector machines (LSSVMs), eXtreme gradient boosting (XGBoost), ResNet50, and ResNet101. CatBoost consistently delivered the highest classification accuracy across all SR methods, reaching 97.32% accuracy at 959.37 nm when paired with SAM-EMSR-GAN. Independent validation using a separate dataset confirmed the robustness of this approach, achieving a 92.49% accuracy. These findings demonstrate the potential of combining SAM-EMSR-GAN and CatBoost for accurate and efficient coal and gangue identification, paving the way for intelligent and automated coal sorting technologies.

DLKN: enhanced lightweight image super-resolution with dynamic large kernel network

DLKN: enhanced lightweight image super-resolution with dynamic large kernel network

TDRD3 functions as a selective autophagy receptor with dual roles in autophagy and modulation of stress granule stability.

Tudor Domain Containing 3 (TDRD3) is a methylarginine-reader protein that functions as a scaffold in the nucleus facilitating transcription, however TDRD3 is also recruited to stress granules (SGs) during the Integrated Stress Response (ISR) although its function therein remains largely unknown. We previously showed that TDRD3 is a novel antiviral restriction factor that is cleaved by virus 2A protease, and plays complex modulatory roles in both interferon and inflammatory signaling during stress and enterovirus infections. Here we have found that TDRD3 contains structural motifs similar to known selective autophagy receptors such as p62/SQSTM1, sharing ubiquitin associated domains (UBA) and LC3 interacting regions (LIR) that anchor cargo destined for autophagosomes to activated LC3 protein coating autophagosome membranes. This is of interest since enteroviruses hijack autophagy machinery to facilitate formation of viral replication factories, virus assembly and egress from the infected cell. Here we explored possible roles of TDRD3 in autophagy, hypothesizing that TDRD3 may function as a specialized selective autophagy receptor. We found that KO of TDRD3 in HeLa cells significantly reduces starvation induced autophagy, while its reintroduction restores it in a dose-dependent manner. Autophagy receptors are degraded during autophagy and expression levels decrease during this time. We found that TDRD3 levels decrease to the same extent as the autophagy receptor p62/SQSTM1 during autophagy, indicating autophagy-targeted turnover in that role. Knockout of TDRD3 or G3BP1 did not make significant changes in overall cell localization of LC3B or p62/SQSTM1, but did result in greater concentration of Lamp2 phagosome marker for phagosomes and phagolysosomes. To test the potential roles of TDRD3 in autophagic processes, we created a series of deletion mutants of TDRD3 lacking either UBA domain or the various LIR motifs that are predicted to interact with LC3B. Microscopic examination of starved cells expressing these variants of TDRD3 showed ΔLIR-TDRD3 had defects in colocalization with LC3B or Lamp2. Further, super resolution microscopy revealed ring structures with TDRD3 interfacing with p62/SQSTM1. In examination of arsenite induced stress granules we found recruitment of TDRD3 variants disrupted normally tight SG condensation, altered the decay rate of SGs upon release from stress and the kinetics of SG formation. We found evidence that the LIR3 motif on TDRD3 is involved in TDRD3 interaction with LC3B in coIP experiments, colocalization studies, and that this motif plays a key role in TDRD3 recruitment to SGs and SG resolution. Overall, these data support a functional role of TDRD3 in selective autophagy in a mode similar to p62/SQSTM1, with specific roles in SG stability and turnover. Enterovirus cleavage of TDRD3 likely affects both antiviral and autophagic responses that the virus controls for replication.

MEFSR-GAN: A Multi-Exposure Feedback and Super-Resolution Multitask Network via Generative Adversarial Networks

In applications such as satellite remote sensing and aerial photography, imaging equipment must capture brightness information of different ground scenes within a restricted dynamic range. Due to camera sensor limitations, captured images can represent only a portion of such information, which results in lower resolution and lower dynamic range compared with real scenes. Image super resolution (SR) and multiple-exposure image fusion (MEF) are commonly employed technologies to address these issues. Nonetheless, these two problems are often researched in separate directions. In this paper, we propose MEFSR-GAN: an end-to-end framework based on generative adversarial networks that simultaneously combines super-resolution and multiple-exposure fusion. MEFSR-GAN includes a generator and two discriminators. The generator network consists of two parallel sub-networks for under-exposure and over-exposure, each containing a feature extraction block (FEB), a super-resolution block (SRB), and several multiple-exposure feedback blocks (MEFBs). It processes low-resolution under- and over-exposed images to produce high-resolution high dynamic range (HDR) images. These images are evaluated by two discriminator networks, driving the generator to generate realistic high-resolution HDR outputs through multi-goal training. Extensive qualitative and quantitative experiments were conducted on the SICE dataset, yielding a PSNR of 24.821 and an SSIM of 0.896 for 2× upscaling. These results demonstrate that MEFSR-GAN outperforms existing methods in terms of both visual effects and objective evaluation metrics, thereby establishing itself as a state-of-the-art technology.

Light at the end of the tunnel: FRAP assays combined with super resolution microscopy confirm the presence of a tubular vacuole network in meristematic plant cells

Abstract Plant vacuoles play key roles in cellular homeostasis, performing catabolic and storage functions, and regulating pH and ion balance. Despite their essential role, there is still no consensus on how vacuoles are established. A model proposing that the endoplasmic reticulum is the main contributor of membrane for growing vacuoles in meristematic cells has been challenged by a study proposing that plant vacuoles are formed de novo by homotypic fusion of multivesicular bodies (MVBs). Here, we use the Arabidopsis thaliana root as a model system to provide a systematic overview of successive vacuole biogenesis stages, starting from the youngest cells proximate to the quiescent center. We combine in vivo high- and super-resolution (STED) microscopy to demonstrate the presence of tubular and connected vacuolar structures in all meristematic cells. Using customized fluorescence recovery after photobleaching (FRAP) assays, we establish different modes of connectivity and demonstrate that thin, tubular vacuoles, as observed in cells near the quiescent center, form an interconnected network. Finally, we argue that a growing body of evidence indicates that vacuolar structures cannot originate from MVBs alone but receive membrane material from different sources simultaneously.

Super-resolution deep learning image reconstruction: image quality and myocardial homogeneity in coronary computed tomography angiography

BackgroundThe recently introduced super-resolution (SR) deep learning image reconstruction (DLR) is potentially effective in reducing noise level and enhancing the spatial resolution. We aimed to investigate whether SR-DLR has advantages in the overall image quality and intensity homogeneity on coronary computed tomography (CT) angiography with four different approaches: filtered-back projection (FBP), hybrid iterative reconstruction (IR), DLR, and SR-DLR.MethodsSixty-three patients (mean age, 61 ± 11 years; range, 18–81 years; 40 men) who had undergone coronary CT angiography between June and October 2022 were retrospectively included. Image noise, signal to noise ratio, and contrast to noise ratio were quantified in both proximal and distal segments of the major coronary arteries. The left ventricle myocardium contrast homogeneity was analyzed. Two independent reviewers scored overall image quality, image noise, image sharpness, and myocardial homogeneity.ResultsImage noise in Hounsfield units (HU) was significantly lower (P < 0.001) for the SR-DLR (11.2 ± 2.0 HU) compared to those associated with other image reconstruction methods including FBP (30.5 ± 10.5 HU), hybrid IR (20.0 ± 5.4 HU), and DLR (14.2 ± 2.5 HU) in both proximal and distal segments. SR-DLR significantly improved signal to noise ratio and contrast to noise ratio in both the proximal and distal segments of the major coronary arteries. No significant difference was observed in the myocardial CT attenuation with SR-DLR among different segments of the left ventricle myocardium (P = 0.345). Conversely, FBP and hybrid IR resulted in inhomogeneous myocardial CT attenuation (P < 0.001). Two reviewers graded subjective image quality with SR-DLR higher than other image reconstruction techniques (P < 0.001).ConclusionsSR-DLR improved image quality, demonstrated clearer delineation of distal segments of coronary arteries, and was seemingly accurate for quantifying CT attenuation in the myocardium.

Capillary-scale Microvessel Imaging with High-frequency Ultrasound Localization Microscopy in Mouse Brain.

Ultrasound localization microscopy is a super-resolution vascular imaging technique which has garnered substantial interest as a tool for small animal neuroimaging, neuroscience research, and the characterization of vascular pathologies. In the pursuit of increasingly high-fidelity reconstructions of microvasculature, there remains several outstanding questions concerning this sub-diffraction imaging technology, including the accurate reconstruction of microvessels approaching the capillary scale and the pragmatic challenges associated with long data acquisition times. In the context of small animal neurovascular imaging, we posit that increasing the ultrasound imaging frequency is a straightforward approach to enable higher concentrations of microbubble contrast agents, thus increasing the likelihood of microvascular/capillary mapping and decreasing the imaging duration. We demonstrate that higher frequency imaging results in improved ULM fidelity and more efficient microbubble localization due to a smaller microbubble point-spread function that is easier to localize, and which can achieve a higher localizable concentration within the same unit volume of tissue. A select example of in vivo capillary-level vascular reconstruction is demonstrated for the highest frequency imaging probe, which has substantial implications for neuroscientists investigating microvascular function in disease states, regulation, and brain development. High frequency ULM yielding a spatial resolution of 7.1μm, as measured by Fourier ring correlation, throughout the entire depth of the brain, highlighting this technology as a highly relevant tool for neuroimaging research.

Iterative Immunostaining and NEDD Denoising for Improved Signal-To-Noise Ratio in ExM-LSCM.

Expansion microscopy (ExM) has significantly reformed the field of super-resolution imaging, emerging as a powerful tool for visualizing complex cellular structures with nanoscale precision. Despite its capabilities, the epitope accessibility, labeling density, and precision of individual molecule detection pose challenges. We recently developed an iterative indirect immunofluorescence (IT-IF) method to improve the epitope labeling density, improving the signal and total intensity. In our protocol, we iteratively apply immunostaining steps before the expansion and exploit signal processing through noise estimation, denoising, and deblurring (NEDD) to aid in quantitative image analyses. Herein, we describe the steps of the iterative staining procedure and provide instructions on how to perform NEDD-based signal processing. Overall, IT-IF in ExM-laser scanning confocal microscopy (LSCM) represents a significant advancement in the field of cellular imaging, offering researchers a versatile tool for unraveling the structural complexity of biological systems at the molecular level with an increased signal-to-noise ratio and fluorescence intensity. Key features • Builds upon the method developed by Mäntylä et al. [1] and introduces the IT-IF method and signal-processing platform for several nanoscopy imaging applications. • Retains signal-to-noise ratio and significantly enhances the fluorescence intensity of ExM-LSCM data. • Automatic estimation of noise, signal reconstruction, denoising, and deblurring for increased reliability in image quantifications. • Requires at least seven days to complete.

Generative AI-Enabled Energy-Efficient Mobile Augmented Reality in Multi-Access Edge Computing

This paper proposes a novel offloading and super-resolution (SR) control scheme for energy-efficient mobile augmented reality (MAR) in multi-access edge computing (MEC) using SR as a promising generative artificial intelligence (GAI) technology. Specifically, SR can enhance low-resolution images into high-resolution versions using GAI technologies. This capability is particularly advantageous in MAR by lowering the bitrate required for network transmission. However, this SR process requires considerable computational resources and can introduce latency, potentially overloading the MEC server if there are numerous offload requests for MAR services. In this context, we conduct an empirical study to verify that the computational latency of SR increases with the upscaling level. Therefore, we demonstrate a trade-off between computational latency and improved service satisfaction when upscaling images for object detection, as it enhances the detection accuracy. From this perspective, determining whether to apply SR for MAR, while jointly controlling offloading decisions, is challenging. Consequently, to design energy-efficient MAR, we rigorously formulate analytical models for the energy consumption of a MAR device, the overall latency and the MAR satisfaction of service quality from the enforcement of the service accuracy, taking into account the SR process at the MEC server. Finally, we develop a theoretical framework that optimizes the computation offloading and SR control problem for MAR clients by jointly optimizing the offloading and SR decisions, considering their trade-off in MAR with MEC. Finally, the performance evaluation indicates that our proposed framework effectively supports MAR services by efficiently managing offloading and SR decisions, balancing trade-offs between energy consumption, latency, and service satisfaction compared to benchmarks.