Search Results (60)

This review analyses and logically structures modern intelligent sensor technologies in the context of animal husbandry, feed production, and veterinary medicine. The main research discussed in the article focuses on machine learning based on modern neural network models, computer vision, and sensor systems that are transforming the methods for assessing the health, behavior, and nutrition of farm animals. The first part examines modern approaches to quality control and optimization of mineral and vitamin premixes, including visual inspection using visual sensors and neural networks. Key roles are played by precise dosing, component stability (minerals, vitamins), and the transition to more bioefficient organic forms of micronutrients to reduce environmental impact. Improvements in feed and premix production are analyzed, including automation, energy management, and the use of machine learning for non-destructive quality control, defect detection, mixing homogeneity assessment, and vitamin stability prediction. The second part analyzes methods for animal location and behavior detection. This article presents computer vision-based systems, including modifications of YOLO, for automatically tracking and classifying key behavioral patterns (lying down, standing, feeding, and aggression) in cattle and pigs, even in crowded conditions. It also discusses the use of ultra-wideband (UWB) systems and accelerometers combined with machine learning for high-precision positioning and detection of specific behavioral anomalies, such as lameness and playfulness. The third section focuses on the application of machine learning in veterinary diagnostics, including the automated interpretation of medical images (X-ray, ultrasound, and MRI) as sensor data streams for the diagnosis of cardiovascular, oncological, and orthopedic diseases in farm and small animals. Furthermore, the article examines the use of machine learning models for proactive disease diagnosis in farm animals and poultry based on multimodal data and image analysis. Considerable attention is given to methods and tools for radiometric diagnosis of animal diseases at an early stage using microwave sensors, as well as laser therapy and surgery in veterinary medicine. The review concludes that the integration of intelligent systems enables a transition to data-driven livestock management, significantly improving animal welfare and, consequently, the efficiency and sustainability of agricultural production. Full article

Imaging-based spatial transcriptomics has advanced from low-plex single-molecule fluorescence in situ hybridization to a diverse set of highly multiplexed platforms, with recent multimodal and pathology-compatible capabilities. Despite major differences in chemistry, coding, and imaging strategies across different platforms, their biological interpretation often converges on a few notable computational biology problems. This review examines imaging-based spatial transcriptomics through the lens of data interpretation and applications, focusing on the analytical framework that converts raw fluorescence signals or accompanying in situ sequencing data into molecule-, cell-, and tissue-level representations. We discuss the key challenges in preprocessing, registration, restoration, feature detection, barcode decoding, molecule calling, cell segmentation, transcript assignment, probabilistic cell typing, spatial-domain inference, and atlas integration. We also highlight how optical crowding, tissue thickness, panel bias, and multimodal complexity increase computational difficulty. Finally, we summarize applications of imaging-based spatial transcriptomics techniques, ranging from subcellular RNA localization to atlas-scale and pathology-aware spatial analysis. Full article

The transient protoplast transformation system is a vital tool for studying protein subcellular localization and phase separation in wheat. However, current protocols remain underdeveloped, and the lack of systematic vector design analysis frequently leads to localization artifacts. Here, we established a simplified wheat mesophyll protoplast transformation method featuring a shortened cycle, streamlined handling, and no variety limitations, enabling stable acquisition of high-quality confocal imaging data. Using this method, we systematically examined the effects of the fluorescent tag position (N- vs. C-terminal) and promoter type (native, single CaMV35S and double CaMV35S) on protein localization and phase separation. Tag position proved decisive: improper fusion can affect the recognition of localization signals, leading to inaccurate patterns. Regarding promoters, the native promoter represents the optimal choice for physiological accuracy. Constitutive strong promoters such as CaMV35S boost gene expression and thereby enhance fluorescent signals for easier imaging, but overexpression may compromise localization fidelity and exacerbate molecular crowding effects, resulting in false-positive phase-separated aggregates. Conversely, insufficient expression will lead to false-negative outcomes. This standardized transformation system and the defined vector design principles offer a robust framework for minimizing artifacts in wheat protein localization and phase separation research. Full article

In situ hybridization (ISH) has undergone a rapid evolution from a low-throughput histological staining technique to a diverse family of modern methods for sensitive, specific and multiplexed molecular detection in intact cells and tissues, and to a cornerstone technology for image-based spatial transcriptomics. This transformation has been driven by advances in probe design, signal amplification, cyclic imaging, combinatorial barcoding, automated fluidics and computational decoding, which together allow RNA molecules to be measured within preserved cellular and tissue architecture. In this review, we examine the molecular and engineering principles that underlie modern ISH methods and their extension into ISH-based spatial profiling, with emphasis on hybridization chain reaction, branched-DNA amplification, SABER-FISH, rolling-circle-amplification-based approaches, seqFISH, MERFISH, RAEFISH and selected commercial implementations. We discuss how sensitivity, specificity, tissue compatibility, optical crowding, imaging burden, cost, reproducibility and computational uncertainty shape the practical use of each method. Sequencing-based spatial capture platforms are not reviewed comprehensively, but are considered where comparative benchmarks help clarify trade-offs in spatial resolution, transcriptome breadth, tissue area or analytical interpretation. We also consider how recent benchmarking and standardization efforts are beginning to define quantitative criteria for comparing platforms, and how advances in segmentation, barcode decoding, spatial integration and cell–cell communication analysis convert raw images into biological insight. Finally, we highlight applications in targeted transcript detection, tissue-based validation, neuroscience, cancer, developmental biology, non-model organisms and spatial functional genomics, where modern ISH methods and ISH-based spatial profiling provide information that bulk and dissociated single-cell approaches cannot capture. Together, these developments trace how ISH has expanded from targeted molecular visualization into a broad methodological framework for in situ detection and spatially resolved transcriptomic analysis. Full article

Background/Objectives: Ciliated epithelial change in endometrial lesions is a recognized morphologic finding, but its immunophenotypic correlates and biological significance remain insufficiently defined. We investigated whether endometrial lesions with ciliated epithelial change show reproducible immunohistochemical alterations across benign, premalignant, and malignant diagnostic categories. Methods: We performed a retrospective immunohistochemical study of 315 formalin-fixed paraffin-embedded eutopic uterine endometrial specimens (no endometriotic/ectopic lesions included) collected between 2019 and 2024 and distributed equally across seven diagnostic categories (n = 45 each): normal endometrium, endometrial polyp, hyperplasia with cystic/disordered glands, hyperplasia with crowded glands, atypical hyperplasia/EIN, endometrioid carcinoma, and serous carcinoma. Marker expression was quantified by digital image analysis and compared between lesions with and without ciliated epithelial change, including lesions with ciliated epithelial change showing cytological atypia. Results: Ciliated epithelial change (CEC) was identified in 86/315 cases (27.3%), including 41 cases (13.0%) with atypical CEC. In benign categories, lesions with CEC showed lower E-cadherin expression and higher β-catenin expression, including more frequent nuclear β-catenin localization. In carcinomas, these patterns were not recapitulated and instead showed an opposite or attenuated profile, supporting a context-dependent rather than linear model. Vimentin was consistently reduced in lesions with CEC across diagnostic categories. p53 and CD44 showed heterogeneous findings and were less informative than the adhesion- and phenotype-related markers. Conclusions: Endometrial lesions with CEC show reproducible, context-dependent immunohistochemical alterations, most consistently involving E-cadherin, β-catenin, and vimentin. In particular, nuclear β-catenin reactivity in this setting should not be interpreted as evidence of canonical Wnt-pathway activation in the absence of CTNNB1 sequencing or validated downstream readouts, and the carcinoma findings cannot be assigned to a specific TCGA/ProMisE molecular subgroup using immunohistochemistry alone. The observations should therefore be regarded as exploratory and warrant validation in studies incorporating molecular classification, direct ciliogenesis markers (FOXJ1, acetylated α-tubulin, basal body markers), and outcome data. Full article

Large imaging and spectroscopic surveys now produce heterogeneous data at a scale that challenges supervised approaches which depend on scarce labels and task-specific retraining. In this paper, we conduct a systematic evaluation and analysis of AstroCLIP, a cross-modal self-supervised model that aligns galaxy images and optical spectra within a shared embedding space. Our overarching aim is to extend the released benchmark with a more fine-grained assessment of robustness and embedding behaviour. Using the released DESI and DESI Legacy Imaging Survey evaluation suite, we first reproduce the main downstream galaxy-property regression results and then extend the evaluation in two novel ways: (i) by stratifying predictive performance across a neighbour-count proxy for local environment density, and (ii) by comparing the suite’s observational categories labelled Low-z (Bright) and High-z (Faint). We further inspect the embedding space using UMAP and unsupervised clustering, and quantify cluster–property agreement using the adjusted mutual information (AMI). Across tasks, spectral embeddings consistently outperform image embeddings; for example, zero-shot prediction reaches $R^2=0.87$ for $log\left(M_{*}\right)$ and $R^2=0.63$ for $log\left(\mathrm{sSFR}\right)$. Under our environment proxy, moderate-density bins often yield the strongest predictive performance, while very sparse or crowded bins tend to underperform. Image-based predictions benefit substantially from the Low-z (Bright) subset, whereas spectral embeddings are more stable across the observational split. At the same time, UMAP and clustering reveal only weak discrete separation by individual physical properties, so the results are most consistent with useful information being encoded in a largely continuous rather than sharply clustered form. Full article

Detection, tracking, and re-identification (ReID) of children wearing similar uniforms in a kindergarten environment is a very complex challenge for computer vision. Traditional surveillance systems or simple convolutional neural network (CNN) models often fail to distinguish children in crowds and occlusions. To address this challenge, this study proposes a novel hybrid framework combining YOLOv8 and Vision Transformer (ViT). Using YOLOv8 for detection and ViT for global feature extraction, we trained the model on a custom dataset of 31,521 images, achieving an overall accuracy of 93.75%, and the public benchmark MOT20 dataset of 28,630 images, achieving an overall accuracy of 96.02%. Our system showed remarkable success in tracking performance, where it achieved 86.7% MOTA and 99.7% IDF1 scores. This high IDF1 score proves that the model is highly effective in preventing identity switch. The main novelty of this study is the behavioral analysis of children beyond the boundaries of surveillance, where we measure walking distance and trajectory, and screen time. Finally, through cross-dataset comparison with the MOT20 public benchmark, we demonstrated that our proposed customized model is much more effective than current state-of-the-art methods in overcoming the domain gap in specific environments such as kindergarten. Full article

The proliferation of air travel demand necessitates innovative solutions to enhance passenger experience while optimizing airport operational efficiency. This paper presents the pilot-scale implementation and evaluation of an AI-powered service robot ecosystem integrated with thermal cameras and 5G wireless connectivity at Athens International Airport. The system addresses critical challenges in passenger flow management through real-time crowd analytics, congestion detection, and personalized robotic assistance. Eight strategically deployed thermal cameras monitor passenger movements across check-in areas, security zones, and departure entrances while employing privacy-by-design principles through thermal imaging technology that reduces personally identifiable information capture. A humanoid service robot, equipped with Robot Operating System navigation capabilities and natural language processing interfaces, provides real-time passenger assistance including flight information, wayfinding guidance, and congestion avoidance recommendations. The wi.move platform serves as the central intelligence hub, processing video streams through advanced computer vision algorithms to generate actionable insights including passenger count statistics, flow rate analysis, queue length monitoring, and anomaly detection. Formal trial evaluation conducted on 10 April 2025, with extended operational monitoring from April to June 2025, demonstrated strong technical performance with application round-trip latency achieving 42.9 milliseconds, perfect service reliability and availability ratings of one hundred percent, and comprehensive passenger satisfaction scores exceeding 4.3/5 across all evaluated dimensions. Results indicate promising potential for scalable deployment across major international airports, with identified requirements for sixth-generation network capabilities to support enhanced multi-robot coordination and advanced predictive analytics functionalities in future implementations. Full article

Technological advancements have significantly improved cattle farming, particularly in sensor-based activity monitoring for health management, estrus detection, and overall herd supervision. However, such a sensor-based monitoring framework often illustrates several issues, such as high cost, animal discomfort, and susceptibility to false measurement. This study introduces a vision-based cattle activity monitoring approach deployed in a commercial Nestlé dairy farm, specifically one that is estrus-focused, where overhead cameras capture unconstrained herd behavior under variable lighting, occlusions, and crowding. A custom dataset of 2956 Images are collected and then annotated into four fine-grained behaviors—standing, lying, grazing, and estrus—enabling detailed analysis beyond coarse activity categories commonly used in prior livestock monitoring studies. Furthermore, computer vision-based deep learning algorithms are deployed on this dataset to classify the aforementioned classes. A comparative analysis of YOLOv8 and YOLOv9 is provided, which clearly illustrates that YOLOv8-L achieved a mAP of 91.11%, whereas YOLOv9-E achieved a mAP of 90.23%. Full article

Multi-object tracking and segmentation (MOTS) is a critical task in video analysis with applications spanning autonomous driving, robot navigation, and scene understanding. MOTS has made significant progress but still faces persistent challenges, such as crowded scenes, abnormal illumination, and small objects. Several trackers have implemented attention mechanisms to overcome these difficulties. However, many attention mechanisms have quadratic computational complexity and use little spatio-temporal information. This paper proposes a Dual-Linear Attention Network (DLAN), a novel approach that effectively integrates both appearance and spatio-temporal information while maintaining linear attention complexity. DLAN employs recursive linear self-attention to strengthen the appearance representation and prototypical linear cross-attention to condense rich spatio-temporal information, which can compensate for missing pixel information. DLAN optimizes both image features and segmentation, with the refined segmentation guiding frame-level memory updates to improve instance consistency. Extensive experiments on BDD100K MOT, BDD100K MOTS, and KITTI MOTS datasets demonstrate the following: (1) The three main challenges of object occlusion, illumination variation, and distant objects have been successfully mitigated by integrating DLAN. (2) DLAN has achieved an overall competitive performance when compared to state-of-the-art trackers, with a 26% reduction in identity switches (IDS) when compared to QDTrack-mots-fix. Full article

Background/Objectives: The endoscopic transorbital approach (ETOA) is a minimally invasive surgical route that provides access to the lateral skull base through the superior eyelid. Originally developed as an endoscopic procedure, ETOA has recently been explored using alternative visualization tools such as the exoscope. This study evaluates the effectiveness of exoscopic visualization across the different steps of transorbital surgery. Methods: Eight formalin-fixed cadaveric specimens (16 sides) were dissected by four teams of neurosurgeons trained in ETOA. The dissection protocol consisted of three stages: skin, orbital, and intracranial. The teams were assigned to four groups: the first performed a pure endoscopic ETOA (group A) and the second and third performed a combined exoscopic/endoscopic ETOA, using exoscopic visualization, respectively, for the skin phase only (group B) or for the skin and orbital phases (group C), while the fourth group performed a pure exoscopic ETOA All surgeons rotated across groups. Operative time was recorded. After each procedure, surgeons rated operative comfort, maneuverability, and image quality on a 0–5 scale. Pre- and postoperative CT scans were used for volumetric analysis, comparing surgical cavity size with and without the endoscope in place. In addition, an illustrative exoscopic case was included. Results: Exoscopic visualization proved to be more effective during the skin phase. In the orbital phase, it improved access and reduced crowding during lateral wall drilling. However, endoscopic visualization provided superior image clarity and magnification for deep and medial orbital structures. CT-based analysis confirmed that the exoscope significantly improves the working space during orbital dissection. Moreover, the combined approaches (Groups B and C) achieved shorter operative times and higher subjective ratings. Conclusions: The exoscope could be a valuable visualizing tool for transorbital surgery. While the skin phase benefits most from exoscopic visualization, the endoscope remains essential for the intracranial phase. The orbital phase can be effectively performed with either technique, each offering specific advantages and limitations. Full article

Background and Objectives: Optic disc drusen (ODD) can mimic papilledema and are linked to structural crowding, microvascular change, and visual-field loss. We synthesized structural/microvascular differences, functional status and change, diagnostic performance, and ODD–NAION co-occurrence. Methods: This study used PRISMA-aligned searches of PubMed, Embase, and Web of Science (inception–15 July 2025). Eligible designs included cross-sectional, cohort, and diagnostic accuracy studies with numeric outcomes (OCT/OCTA, visual fields, test accuracy, NAION prevalence). Two reviewers independently screened, extracted, and appraised bias. Heterogeneity precluded meta-analysis; narrative synthesis was used. Bias risk was moderate. Results: From 359 records, 6 studies met the criteria. ODD eyes showed thicker RNFL than controls (117.54 ± 18.75 vs. 105.81 ± 14.45 µm; 101 ± 12 vs. 97 ± 10 µm) and worse baseline mean deviation (−1.78 ± 3.87 dB). OCTA demonstrated sectoral peripapillary vessel-area density reduction (inferior 0.30 vs. 0.34; temporal 0.44 vs. 0.48; superonasal 0.44 vs. 0.49). Visual-field phenotypes were normal (44–52%), enlarged blind spot (19–29%), and other localized defects (24–29%); the longitudinal decline averaged −0.23 ± 0.26 dB/year with 88% slow progressors. In pseudopapilledema, single-test yields were ultrasound at 87.2%, OCT at 80.2%, and FAF at 62.8%; OCT alone distinguished buried ODD from mild papilledema with 50–64% accuracy (κ ≈ 0.35). Among young NAION, ODD affected 56.7% of patients and 53.3% of eyes; bilaterality was 95.2%, and only 35.9% were ophthalmoscopically visible. Conclusions: Multimodal imaging shows structural thickening, microvascular rarefaction, and modest functional loss in ODD, with slow average progression. In suspected papilledema, protocolized multimodal workflows outperform OCT alone. ODD are common in young NAION, supporting risk stratification and longitudinal monitoring. Full article

Introduction: The aim of this study was to investigate the spatial relationship between the incisive canal (IC) and apical region of the maxillary central incisors in the Korean population, using cone-beam computed tomography (CBCT) imaging. The findings are intended to inform and improve the planning and execution of immediate implant placement in the maxillary esthetic zone. Materials and methods: CBCT data were collected from 94 patients (48 men, 46 women) aged 20–79 years at Gangnam Dental Clinic, Seoul, South Korea. The sample was divided according to age into three groups: 20–39 years, 40–59 years, and 60–79 years. Exclusion criteria included missing maxillary anterior teeth, severe crowding, periodontitis, pathology, and image artifacts. Measurements of the distance from the root apex to the incisive canal (RIC-11-P, RIC-21-P) and from the root apex to the buccal bone (RBB-11-B, RBB-21-B) were taken from CBCT images. Statistical analyses were conducted using Welch’s t-test, ANOVA, and Pearson correlation, with significance set at p < 0.05. Results: The mean distances from the root apex to the incisive canal were 3.77 mm (RIC-11-P) and 3.62 mm (RIC-21-P), while the mean distances to the buccal bone were 0.86 mm and 0.94 mm, respectively. Males exhibited significantly greater distances compared to females, both in the NPC-to-root apex and buccal bone measurements. Age-related variations were observed, with younger individuals showing shorter distances from the IC to the root apex. However, ANOVA tests and Pearson correlation analysis indicated no statistically significant correlation in these distances across different age groups. The study highlights significant gender differences in maxillary central incisor anatomy, with males having larger distances from the root apex to both the IC and buccal bone, which has implications for implant placement. While age-related changes were observed, they did not significantly affect the mean distances in a statistically meaningful way. Conclusions: These findings underscore the need for personalized treatment planning in immediate implant placement, particularly in relation to gender and age. Comparisons with other population studies suggest that these anatomical differences may be consistent across various ethnic groups, though individual variance factors should still be considered. Full article

Objectives: This study aimed to compare the skeletal and dentoalveolar effects of a fully customized elastodontic appliance with those of the traditional Twin Block appliance in growing patients with Class II malocclusion during the mixed dentition phase. Methods: A total of 35 patients were included: 18 treated with a customized elastodontic appliance (C-Ela group) and 17 with a Twin Block appliance (TB group). Digital dental models and lateral cephalometric radiographs were obtained at baseline (T1) and after 12 months of treatment (T2). All patients were treated by experienced clinicians according to standardized appliance protocols. Data analysis was performed by a blinded operator using Ortho Analyzer and Dolphin Imaging software. The Shapiro–Wilk test was applied to verify the normal distribution of the data. Paired-sample t-tests were used to assess within-group changes between T1 and T2. For intergroup comparisons two-tail independent-sample t-tests were used, and chi-square tests were used for categorical variables. Statistical significance was set at p < 0.05. Results: Both groups showed significant intragroup improvements in overjet (C-Ela: −2.77 ± 2.07; TB: −2.30 ± 2.72 mm), overbite (C-Ela: −1.79 ± 1.95; TB: −1.40 ± 2.65 mm), and sagittal molar relationship (p < 0.05) after treatment. The C-Ela group exhibited a significantly greater reduction in anterior dental crowding (p < 0.05) and better control of upper (C-Ela: −4.93 ± 7.65°; TB: −1.80 ± 5.72°) and lower incisor inclination (C-Ela: +1.70 ± 4.80°; TB: +4.35 ± 6.22°). In intergroup comparisons, the TB group showed a significantly greater proclination of the lower incisors at T2 (L1/Go-Gn: +4.35°; L1/A-Pog: +1.44 mm), whereas the C-Ela more effectively limited these changes (L1/Go-Gn: +1.70°; L1/A-Pog: +1.18 mm). Skeletal analysis revealed an increase in ANB angle in both groups (C-Ela: −1.49 ± 2.62°; TB: −1.78 ± 2.78°), with no statistically significant intergroup differences, and no other skeletal parameters showed significant between-group changes. Conclusions: Both appliances effectively corrected Class II malocclusions. However, the customized elastodontic device provided better dentoalveolar control, particularly in managing anterior crowding and incisor inclination. Its individualized fit may enhance biomechanical precision and improve overall treatment outcomes in growing patients. Full article

Background: Identifying the etiological factors of syringomyelia, which can cause progressive neurological deficits in the spinal cord, is critically important for both diagnosis and treatment. This study aimed to assess the cranial morphometric features of patients with idiopathic syringomyelia by conducting comparative analyses with individuals diagnosed with Chiari Type I, Chiari Type I accompanied by syringomyelia, and healthy controls, in order to elucidate the potential structural contributors to the pathogenesis of idiopathic syringomyelia. Methods: In this retrospective and comparative study, a total of 172 patients diagnosed with Chiari Type I and/or syringomyelia between 2016 and 2024, along with 156 radiologically normal individuals, were included. The participants were categorized into four groups: healthy controls, Chiari Type I, Chiari Type I with syringomyelia, and idiopathic syringomyelia (defined as syringomyelia without an identifiable cause). Midline sagittal T1-weighted MR images were used to obtain quantitative measurements of the posterior fossa, cerebellum, intracranial area, and foramen magnum. All measurements were stratified and statistically analyzed by sex. Results: In cases with idiopathic syringomyelia, both the posterior fossa area and the cerebellum/posterior fossa ratio differed significantly from those of healthy controls. In male patients, the foramen magnum diameter was significantly larger in the Chiari + syringomyelia group compared with the idiopathic group. A significant correlation was found between the degree of tonsillar descent and selected morphometric parameters in female subjects, whereas no such correlation was observed in males. Both Chiari groups exhibited significantly smaller posterior fossa dimensions compared with the healthy and idiopathic groups, indicating greater neural crowding. Additionally, in Chiari Type I patients, increasing degrees of tonsillar descent were associated with a decreased incidence of syringomyelia. Conclusions: Anatomical variations such as a reduced posterior fossa area or altered foramen magnum diameter may contribute to the pathogenesis of idiopathic syringomyelia. Cranial morphometric analysis appears to offer diagnostic value in these cases. Further prospective, multicenter studies incorporating advanced neuroimaging modalities, particularly those assessing cerebrospinal fluid dynamics, are warranted to better understand the mechanisms underlying syringomyelia of unknown etiology. Full article