Search Results (15,665)

Reliable acupoint localization is essential for developing artificial intelligence (AI) and extended reality (XR) tools in traditional Korean medicine; however, conventional annotation of 2D images often suffers from inter- and intra-annotator variability. This study presents a low-cost dual-camera imaging system that fuses infrared (IR) and RGB views on a Raspberry Pi 5 platform, incorporating an IR ink pen in conjunction with a 780 nm emitter array to standardize point visibility. Among the tested marking materials, the IR ink showed the highest contrast and visibility under IR illumination, making it the most suitable for acupoint detection. Five feature detectors (SIFT, ORB, KAZE, AKAZE, and BRISK) were evaluated with two matchers (FLANN and BF) to construct representative homography pipelines. Comparative evaluations across multiple camera-to-surface distances revealed that KAZE + FLANN achieved the lowest mean 2D Error (1.17 ± 0.70 px) and the lowest mean aspect-aware error (0.08 ± 0.05%) while remaining computationally feasible on the Raspberry Pi 5. In hand-image experiments across multiple postures, the dual-camera registration maintained a mean 2D error below ~3 px and a mean aspect-aware error below ~0.25%, confirming stable and reproducible performance. The proposed framework provides a practical foundation for generating high-quality acupoint datasets, supporting future AI-based localization, XR integration, and automated acupuncture-education systems. Full article

Decoding visual content from neural activity remains a central challenge at the intersections of engineering, neuroscience, and computational modeling. Prior work has primarily leveraged electroencephalography (EEG) with generative models to recover static images. In this study, we advance EEG-based decoding by introducing a temporal encoding framework that approximates dynamic object transformations across time. EEG recordings from healthy participants (n = 20) were used to model neural representations of objects presented in “initial” and “later” states. Individualized classifiers trained on time-specific EEG signatures achieved high discriminability, with Random Forest models reaching a mean accuracy and standard deviation of 92 ± 2% and a mean AUC-ROC and standard deviation of 0.87 ± 0.10, driven largely by gamma- and beta-band activity at the frontal electrodes. These results confirm and extend evidence of strong interindividual variability, showing that subject-specific models outperform intersubject approaches in decoding temporally varying object representations. Beyond classification, we demonstrate that pairwise temporal encodings can be integrated into a generative pipeline to produce approximated reconstructions of short video sequences and 3D object renderings. Our findings establish that temporal EEG features, captured using low-cost open-source hardware, are sufficient to support the decoding of visual content across discrete time points, providing a versatile platform for potential applications in neural decoding, immersive media, and human–computer interaction. Full article

Background: Midpalatal suture expansion is effective in both growing and adult patients, and Miniscrew-Assisted Rapid Palatal Expansion (MARPE) provides greater skeletal effects and fewer dentoalveolar side effects than traditional expanders. However, asymmetric expansion remains a challenge, often influenced by pre-existing craniofacial asymmetries, appliance design, and suture morphology. In this case report, we describe asymmetric expansion with 3D-guided piezocorticotomy-assisted MARPE and its management with directly printed aligners (DPAs). Methods: A patient with facial asymmetry, a narrow maxillary arch, and multiple dentoalveolar deformities underwent pre-treatment evaluation, including root inclination analysis and CBCT imaging. A MARPE appliance with 3D-guided piezocorticotomy assistance was applied; post-expansion orthodontic treatment was digitally planned and performed with directly printed aligners. Results: During MARPE activation, asymmetric midpalatal suture disarticulation was observed, with greater displacement on the left side due to jackscrew orientation and root proximity. Post-expansion orthodontic correction with DPAs allowed precise root positioning, spatial redistribution, and improved occlusal symmetry. Over 20 months, significant improvements were achieved in midline orientation, axial root inclination, and transverse arch coordination. Conclusions: The reported case underscores the importance of pre-treatment evaluation for asymmetries and careful appliance design in MARPE protocols; in addition, it demonstrates that directly printed aligners, supported by digital planning, can provide accurate and efficient dentoalveolar correction following asymmetric expansion. Full article

Over the past decade, recurring influxes of pelagic Sargassum have posed significant environmental and economic challenges in the Caribbean Sea. Effective monitoring is crucial for understanding bloom dynamics and mitigating their impacts. This study presents a comprehensive machine learning (ML) and deep learning (DL) framework for detecting Sargassum and estimating its fractional cover using imagery from key satellite sensors: the Operational Land Imager (OLI) on Landsat-8 and the Multispectral Instrument (MSI) on Sentinel-2. A spectral library was constructed from five core spectral bands (Blue, Green, Red, Near-Infrared, and Short-Wave Infrared). It was used to train an ensemble of five diverse classifiers: Random Forest (RF), K-Nearest Neighbors (KNN), XGBoost (XGB), a Multi-Layer Perceptron (MLP), and a 1D Convolutional Neural Network (1D-CNN). All models achieved high classification performance on a held-out test set, with weighted F1-scores exceeding 0.976. The probabilistic outputs from these classifiers were then leveraged as a direct proxy for the sub-pixel fractional cover of Sargassum. Critically, an inter-algorithm agreement analysis revealed that detections on real-world imagery are typically either of very high (unanimous) or very low (contentious) confidence, highlighting the diagnostic power of the ensemble approach. The resulting framework provides a robust and quantitative pathway for generating confidence-aware estimates of Sargassum distribution. This work supports efforts to manage these harmful algal blooms by providing vital information on detection certainty, while underscoring the critical need to empirically validate fractional cover proxies against in situ or UAV measurements. Full article

Background: Cardiac-respiratory dual gating in SPECT (DG-SPECT) is an emergent technique for alleviating motion blurring artifacts in myocardial perfusion imaging (MPI) due to both cardiac and respiratory motions. Moreover, the attenuation artifact may arise from the spatial mismatch between the sequential SPECT and CT attenuation scans due to the dual gating of SPECT data and non-gating CT images. Objectives: This study adapts a four-dimensional (4D) cardiac SPECT reconstruction with post-reconstruction respiratory motion correction (4D-RMC) for dual-gated SPECT. In theory, a respiratory motion-matched attenuation correction (MAC) method is expected to yield more accurate reconstruction results than the conventional motion-averaged attenuation correction (AAC) method. However, its potential benefit is not clear in the presence of practical imaging artifacts in DG-SPECT. In this study, we aim to quantitatively investigate these two attenuation methods for SPECT MPI: 4D-RMC (MAC) and 4D-RMC (AAC). Methods: DG-SPECT imaging (eight cardiac gates and eight respiratory gates) of the NCAT phantom was simulated using SIMIND Monte Carlo simulation, with a lesion (20% reduction in uptake) introduced at four different locations of the left ventricular wall: anterior, lateral, septal, and inferior. For each respiratory gate, a joint cardiac motion-compensated 4D reconstruction was used. Then, the respiratory motion was estimated for post-reconstruction respiratory motion-compensated smoothing for all respiratory gates. The attenuation map averaged over eight respiratory gates was used for each respiratory gate in 4D-RMC (AAC) and the matched attenuation map was used for each respiratory gate in 4D-RMC (MAC). The relative root mean squared error (RMSE), structural similarity index measurement (SSIM), and a Channelized Hotelling Observer (CHO) study were employed to quantitatively evaluate different reconstruction and attenuation correction strategies. Results: Our results show that the 4D-RMC (MAC) method improves the average relative RMSE by as high as 5.42% and the average SSIM value by as high as 1.28% compared to the 4D-RMC (AAC) method. Compared to traditional 4D reconstruction without RMC (“4D (MAC)”), these metrics were improved by as high as 11.23% and 27.96%, respectively. The 4D-RMC methods outperformed 4D (without RMC) on the CHO study with the largest improvement for the anterior lesion. However, the image intensity profiles, the CHO assessment, and reconstruction images are very similar between 4D-RMC (MAC) and 4D-RMC (AAC). Conclusions: Our results indicate that the improvement of 4D-RMC (MAC) over 4D-RMC (AAC) is marginal in terms of lesion detectability and visual quality, which may be attributed to the simple NCAT phantom simulation, but otherwise suggest that AAC may be sufficient for clinical use. However, further evaluation of the MAC technique using more physiologically realistic digital phantoms that incorporate diverse patient anatomies and irregular respiratory motion is warranted to determine its potential clinical advantages for specific patient populations undergoing dual-gated SPECT myocardial perfusion imaging. Full article

Lightweight Single-Image Super-Resolution (SISR) faces the core challenge of balancing computational efficiency with reconstruction quality, particularly in preserving both high-frequency details and global structures under constrained resources. To address this, we propose the Periodically Enhanced Cascade Network (PECNet). Our main contributions are as follows: 1. Its core component, a novel Multi-scale Adaptive Feature Aggregation (MAFA) module, which employs three functionally complementary branches that work synergistically: one dedicated to extracting local high-frequency details, another to efficiently modeling long-range dependencies and a third to capturing structured contextual information within windows. 2. To seamlessly integrate these branches and enable cross-window information interaction, we introduce the Periodic Boundary Padding Shift (PBPS) mechanism. This mechanism serves as a symmetric preprocessing step that achieves implicit window shifting without introducing any additional computational overhead. Extensive benchmarking shows PECNet achieves better reconstruction quality without a complexity increase. Taking the representative shift-window-based lightweight model, NGswin, as an example, for ×4 SR on the Manga109 dataset, PECNet achieves an average PSNR 0.25 dB higher, while its computational cost (in FLOPs) constitutes merely 40% of NGswin’s. Full article

Cement bond evaluation helps check wellbore integrity and zonal isolation in carbon capture, utilisation, and storage (CCUS) projects. This overview describes various cement bond evaluation methods, focusing on acoustic logging and ultrasonic imaging tools supplemented by emerging data-driven interpretation techniques. Their advantages, limitations, and recent advancements are described with illustrative example on ultrasonic-image-based machine learning classifier that detect microannulus. Key research gaps remain in field-scale validation of long-term cement behaviour and in establishing comprehensive 3-D bond-strength benchmarks. To address these gaps, this review recommends (i) creating an open, standardised ML dataset for CCUS well logs, (ii) adopting best-practice pressure-monitoring protocols during and after injection, and (iii) integrating ML analytics with advanced modelling while exploring alternative binder systems. The next step is to test these ML models on real CO₂-storage well data, paving the way toward more reliable cement-bond integrity assessments in future CCUS projects. Full article

Background/Objectives: Lipedema is a chronic disorder characterized by disproportionate fat accumulation in the extremities, causing pain, bruising, and reduced mobility. When conservative therapy fails, liposuction is considered an effective treatment option. Prior studies often relied on subjective or non-standardized measures, limiting precision. This study aimed to objectively assess volumetric changes after liposuction in stage III lipedema using high-resolution 3D imaging to quantify postoperative changes in circumference and volume, providing individualized yet standardized outcome measures aligned with precision medicine. Methods: We retrospectively analyzed 66 patients who underwent 161 water-assisted liposuctions (WALs). Pre- and postoperative measurements were performed with the VECTRA© WB360 system, allowing reproducible, anatomically specific quantification of limb volumes and circumferences. Secondary endpoints included in-hospital complications. Results: Liposuction achieved significant reductions in all treated regions, most pronounced in the proximal thigh and upper arm. Thigh volume decreased by 4.10–9.25% (q < 0.001), while upper arm volume decreased by 15.63% (left) and 20.15% (right) (q = 0.001). Circumference decreased by up to 5.2% in the thigh (q < 0.001) and 12.27% (q = 0.001) in the upper arm. All changes were calculated relative to baseline values, allowing personalized interpretation of treatment effects. Conclusions: This is the first study to objectively quantify postoperative lipedema changes using whole-body 3D surface imaging. By capturing each patient’s contours pre- and postoperatively, this approach enables individualized evaluation while permitting standardized comparison across patients. It offers a precise understanding of surgical outcomes and supports integration of precision medicine principles in lipedema surgery. Full article

Urbanization poses significant challenges for fault investigation, as it can obscure or even hide surface fault expressions and limit access to potential study sites. This paper reports the preliminary results of Electrical Resistivity Tomography combined with geological field surveys in the urbanized area of Villa d’Agri (Basilicata Region, Southern Italy), which has undergone significant expansion in recent decades. This area is located at the northeastern border of the High Agri Valley, characterized by the Eastern Agri Fault System, one of the fault systems believed to have caused the M 7.0 earthquake in 1857 in Southern Italy. The combined use of Electrical Resistivity Tomography and geological field investigations in previously inadequately explored areas, along with the reprocessing of data provided by the municipal technical office of Marsicovetere, allowed imaging of a previously unknown fault and reconstruction of sedimentary cover and substratum geometries, particularly in the urban and peri-urban sectors of Villa d’Agri. These preliminary findings provide valuable insights for geological and structural studies and have prompted the attention of the local Municipality, supporting further research aimed at enhancing urban management and seismic risk assessment. Full article

Background: Amyloid positron emission tomography (PET) has been proposed as a tool to monitor myelination in multiple sclerosis (MS). We present baseline results from an ongoing prospective study, which is the first to include both early and standard phases of amyloid PET in patients with newly diagnosed MS. Methods: The prospective study includes patients with newly diagnosed MS (January 2023–February 2024). Clinical evaluation includes neurological disability (EDSS) and neuropsychological assessment. Brain MRI, early [¹⁸F]florbetaben (FBB) PET (eFBB; 0–5, 0–10 min post-injection), and standard FBB PET (sFBB; 90 min post-injection) were acquired. Normal-appearing white matter (NAWM) and damaged white matter (DWM) in MRI were segmented and co-registered with PET images. Results are presented as standardized uptake values (SUV), with the ratio using cerebellum as the reference region (SUVR) and the percentage of change between the DWM and NAWM. Results: Twenty patients were included (35.05 ± 10.72 years; 75% women). Both eFBB and sFBB acquisitions showed significantly lower SUVRmax and SUVRmean, and higher SUVRmin in the DWM compared to NAWM (p < 0.001) in all patients. SUV parameters in both DWM and NAWM from eFBB and sFBB PET correlated with the number of relapses and EDSS (r = −0.454 and r = −0.446, respectively; p < 0.05). Additionally, SUVR values in the DWM during eFBB correlated with cognitive impairment (SDMT; r = −0.516, p < 0.01), fatigue (MFIS-5; r = −0.450, p < 0.05), and quality of life (EQ-5D; r = −0.490, p < 0.05). Conclusions: Quantitative analysis of dual-phase FBB PET demonstrates differential uptake between DWM and NAWM, which is probably associated with demyelination and neurodegeneration. These preliminary findings suggest that amyloid PET may have predictive value for disease activity and progression, supporting its potential as a biomarker in MS. Follow-up data from this study are needed to support the baseline results. Full article

Complex distortion cancellation methods are often used at the radio frequency (RF) front end of multiantenna full-duplex transceivers to mitigate signal distortion; however, these methods have high computational complexity and limited practicality. To address these problems, the present study explored the complexities associated with such transceivers to develop a practical multistep approach for suppressing distortions arising from in-phase and quadrature (I/Q) imbalance, nonlinear power amplifier (PA) responses, and multipath self-interference caused by simultaneous transmissions on the same frequency. In this approach, the I/Q imbalance is estimated and then compensated for, following which nonlinear PA distortion is estimated and pre-compensated for. Subsequently, an auxiliary RF transmitter is combined with linearly regenerating self-interference signals to achieve full-duplex self-interference cancellation. The proposed method was implemented on a software-defined radio platform, with the distortion factor calibration specifically optimized for multiantenna full-duplex transceivers. The experimental results indicate that the image signal caused by I/Q imbalance can be suppressed by up to 60 dB through iterative computation. By combining IQI and DPD preprocessing, the nonlinear distortion spectrum can be reduced by 25 dB. Furthermore, integrating IQI, DPD, and self-interference preprocessing achieves up to 180 dB suppression of self-interference signals. Experimental results also demonstrate that the proposed method achieves approximately 20 dB suppression of self-interference. Thus, the method has high potential for enhancing the performance of multiantenna RF full-duplex systems. Full article

The transmission of Escherichia coli through contaminated fruits and vegetables poses serious public health risks and has led to several national outbreaks in the USA. To enhance food safety, rapid and reliable detection of E. coli on produce is essential. This study evaluated the performance of the CSI-D+ system combined with deep learning for detecting varying concentrations of E. coli on citrus and spinach leaves. Eight levels of E. coli contamination, ranging from 0 to 10⁸ colony-forming units (CFU)/mL, were inoculated onto the leaf surfaces. For each concentration level, 10 droplets were applied to 8 citrus and 12 spinach leaf samples (2 cm in diameter), and fluorescence images were captured. The images were then subdivided into quadrants, and several post-processing operations were applied to generate the final dataset, ensuring that each sample contained at least 2–3 droplets. Using this dataset, multiple deep learning (DL) models, including EfficientNetB7, ConvNeXtBase, and five YOLO11 variants (n, s, m, l, x), were trained to classify E. coli concentration levels. Additionally, Eigen-CAM heatmaps were used to visualize the spatial responses of the models to bacterial presence. All YOLO11 models outperformed EfficientNetB7 and ConvNeXtBase. In particular, YOLO11s-cls was identified as the best-performing model, achieving average validation accuracies of 88.43% (citrus) and 92.03% (spinach), and average test accuracies of 85.93% (citrus) and 92.00% (spinach) at a 0.5 confidence threshold. This model demonstrated an inference speed of 0.011 s per image with a size of 11 MB. These findings indicate that fluorescence-based imaging combined with deep learning for rapid E. coli detection could support timely interventions to prevent contaminated produce from reaching consumers. Full article

While recent industrial automation trends emphasize the importance of non-destructive inspection by material-identifying millimeter-wave, terahertz-wave, and infrared (MMW, THz, IR) monitoring, fundamental tools in these wavelength bands (such as sensors) are still immature. Although inorganic semiconductors serve as diverse sensors with well-established large-scale fine-processing fabrication, the use of those devices is insufficient for non-destructive monitoring due to the lack of photo-absorbent properties for such major materials in partial regions across MMW–IR wavelengths. To satisfy the inherent advantageous non-destructive MMW–IR material identification, ultrabroadband operation is indispensable for photo-sensors under compact structure, flexible designability, and sensitive performances. This review then introduces the recent advances of carbon nanotube film-based photo-thermoelectric imagers regarding usable and high-yield device fabrication techniques and scientific synergy among computer vision to collectively satisfy material identification with three-dimensional (3D) structure reconstruction. This review synergizes material science, printable electronics, high-yield fabrication, sensor devices, optical measurements, and imaging into guidelines as functional non-destructive inspection platforms. The motivation of this review is to introduce the recent scientific fusion of MMW–IR sensors with visible-light computer vision, and emphasize its significance (non-invasive material-identifying sub-millimeter-resolution 3D-reconstruction with 660 nm–1.15 mm-wavelength imagers at noise equivalent power within 100 pWHz^−1/2) among the existing testing methods. Full article

Synthetic Aperture Radar (SAR) three-dimensional (3D) imaging has considerable potential in disaster monitoring and topographic mapping. Conventional 3D SAR imaging techniques for unmanned aerial vehicle (UAV) formations require rigorously regulated vertical or linear flight trajectories to maintain signal coherence. In practice, however, restricted collaboration precision among UAVs frequently prevents adherence to these trajectories, resulting in blurred scattering characteristics and degraded 3D localization accuracy. To address this, a 3D reconstruction technique based on horizontal-cross configurations is proposed, which establishes a new theoretical framework. This approach reduces stringent flight restrictions by transforming the requirement for vertical baselines into geometric flexibility in the horizontal plane. For dual-UAV subsystems, a geometric inversion algorithm is developed for initial scattering center localization. For multi-UAV systems, a multi-aspect fusion algorithm is proposed; it extends the dual-UAV inversion method and incorporates basis transformation theory to achieve coherent integration of multi-platform radar observations. Numerical simulations demonstrate an 80% reduction in implementation costs compared to tomographic SAR (TomoSAR), along with a 1.7-fold improvement in elevation resolution over conventional beamforming (CBF), confirming the framework’s effectiveness. This work presents a systematic horizontal-cross framework for SAR 3D reconstruction, offering a practical solution for UAV-based imaging in complex environments. Full article

Low-light image enhancement in architectural scenes presents a considerable challenge for computer vision applications in construction engineering. Images captured in architectural settings during nighttime or under inadequate illumination often suffer from noise interference, low-light blurring, and obscured structural features. Although low-light image enhancement and deblurring are intrinsically linked when emphasizing architectural defects, conventional image restoration methods generally treat these tasks as separate entities. This paper introduces an efficient and robust Frequency-Space Recovery Network (FSRNet), specifically designed for low-light image enhancement in architectural contexts, tailored to the unique characteristics of such scenes. The encoder utilizes a Feature Refinement Feedforward Network (FRFN) to achieve precise enhancement of defect features while dynamically mitigating background redundancy. Coupled with a Frequency Response Module, it modifies the amplitude spectrum to amplify high-frequency components of defects and ensure balanced global illumination. The decoder utilizes InceptionDWConv2d modules to capture multi-directional and multi-scale features of cracks. When combined with a gating mechanism, it dynamically suppresses noise, restores the spatial continuity of defects, and eliminates blurring. This method also reduces computational costs in terms of parameters and MAC operations. To assess the effectiveness of the proposed approach in architectural contexts, this paper conducts a comprehensive study using low-light defect images from indoor concrete walls as a representative case. Experimental results indicate that FSRNet not only achieves state-of-the-art PSNR performance of 27.58 dB but also enhances the mAP of the downstream YOLOv8 detection model by 7.1%, while utilizing only 3.75 M parameters and 8.8 GMACs. These findings fully validate the superiority and practicality of the proposed method for low-light image enhancement tasks in architectural settings. Full article