Search Results (89)

Background/Objectives: Adolescent Idiopathic Scoliosis persisting into adulthood (AAIS) presents progressive stiffening and degenerative changes that are not fully captured by existing classifications. This heterogeneity complicates clinical decision-making and surgical planning. The aim of this study was to propose a novel, treatment-oriented classification system for AAIS. Methods: A retrospective review was performed on patients with AAIS who underwent surgical correction between 2018 and 2022. Pre- and postoperative radiographs, CT scans, and MRI were analyzed to define curve characteristics and evaluate surgical outcomes. Subgroups were identified according to age and deformity features, and corresponding surgical strategies were outlined. Results: AAIS was stratified into Young Adult Idiopathic Scoliosis (YAdIS, 19–30 years) and Adult Idiopathic Scoliosis (AdIS, >30 years). YAdIS was divided into mild, flexible curves (YAdIS 1) and severe/stiff curves (YAdIS 2). AdIS was classified into three categories: AdIS 1 (isolated coronal deformity), AdIS 2 (combined coronal and sagittal deformity), and AdIS 3 (revision cases). Within AdIS 1, additional refinement by age (30–45, 45–60, >60 years) reflected increasing stiffness and degenerative changes. Tailored surgical strategies included selective fusions, posterior releases, high-density constructs, three-column osteotomies, and combined anterior–posterior approaches, depending on curve type and age group. Conclusions: This classification provides a comprehensive, treatment-oriented framework to support surgical decision-making in AAIS, enabling optimized planning and improved outcomes for adult patients with scoliosis of adolescent onset. Full article

Identifying the material composition of objects is crucial for many recycling sector applications. Traditionally, object classification relies either on hyperspectral imaging (HSI), which analyses the chemometric properties of objects to infer material types, or on RGB imaging, which captures an object’s visual appearance and compares it to a reference sample. While both approaches have their strengths, each also suffers from limitations, particularly in challenging scenarios such as robotic municipal waste sorting, where objects are often heavily deformed or contaminated with various forms of dirt, complicating material recognition. This work presents a novel method for material-based object classification that jointly exploits HSI and RGB imaging. The proposed approach aims to mitigate the weaknesses of each technique while amplifying their respective advantages. It involves the real-time alignment of HSI and RGB data streams to ensure reliable result correlation, alongside a machine learning framework that learns to exploit the strengths and compensate for the weaknesses of each modality across different material types. Experimental validation on a municipal waste sorting facility demonstrates that the combined HSI–RGB approach significantly outperforms the individual methods, achieving robust and accurate classification even in highly challenging conditions. Full article

Background: Cerebral palsy (CP) is a static, non-progressive brain pathology that affects mobility and musculoskeletal health. Objective: This review aims to describe the pediatric orthopedic management strategy at one specialty center with focus on optimal lifelong mobility function for ambulatory CP. Methods: Beginning in the 1990s, a protocol was developed to proactively monitor children with surgical or conservative interventions. After three decades, we undertook a prospective institutional review, board-approved 25–45-year-old adults callback study. Inclusion criteria were all children treated through childhood who could be located and were willing to return for a full evaluation. Results: Pediatric orthopedic interventions focused on regular surveillance with proactive treatment of progressive deformities. When function was impacted, we utilized multi-level orthopedic surgery guided by instrumented gait analysis. Childhood outcomes of this approach were evaluated through retrospective studies. Results show high correction rates were achieved for planovalgus foot deformity, knee flexion contracture, torsional malalignments, and stiff-knee gait. Our prospective adult callback study evaluated 136 adults with CP, gross motor function classification system levels I (21%), II (51%), III (22%), and IV (7%), with average ages of 16 ± 3 years (adolescent visit) compared with 29 ± 3 years (adult visit). Adults in the study had an average of 2.5 multi-level orthopedic surgery events and 10.4 surgical procedures. Compared with adults without disability, daily walking ability was lower in adults with CP. Adults with CP had limitations in physical function but no increased depression. A higher frequency of chronic pain compared with normal adults was present, but pain interference in daily life was not different. Adults demonstrated similar levels of education but higher rates of unemployment, caregiver needs, and utilization of Social Security disability insurance. Conclusions: The experience from our center suggests that consistent, proactive musculoskeletal management at regular intervals during childhood and adolescence may help maintain in gait and mobility function from adolescence to young adulthood in individuals with CP. Full article

Aperiodic tessellations of polykite unitiles, such as hats and turtles, and the recently introduced hares, red squirrels, and gray squirrels, have attracted significant interest due to their structural and combinatorial properties. Our primary objective here is to learn how we could build a self-assembling polyhedron that would have an aperiodic tessellation of its surface using only a single type of polykite unitile. Such a structure would be analogous to some viral capsids that have been reported to have a quasicrystal configuration of capsomeres. We report on our use of a graph–theoretic approach to examine the adjacency and symmetry constraints of these unitiles in tessellations because by using graph theory rather than the usual geometric description of polykite unitiles, we are able (1) to identify which particular vertices and/or edges join one another in aperiodic tessellations; (2) to take advantage of being scale invariant; and (3) to use the deformability of shapes in moving from the plane to the sphere. We systematically classify their connectivity patterns and structural characteristics by utilizing Hamiltonian cycles of vertex degrees along the perimeters of the unitiles. In addition, we applied Blumeyer’s 2 × 2 classification framework to investigate the influence of chirality and periodicity, while Heesch numbers of corona structures provide further insights into tiling patterns. Furthermore, we analyzed the distribution of polykite unitiles with Voronoi tessellations and their Delaunay triangulations. The results of this study contribute to a better understanding of self-assembling structures with potential applications in biomimetic materials, nanotechnology, and synthetic biology. Full article

Background/Objectives: Lung and colon cancers remain among the most prevalent and fatal diseases worldwide, and their early detection is a serious challenge. The data used in this study was obtained from the Lung and Colon Cancer Histopathological Images Dataset, which comprises five different classes of image data, namely colon adenocarcinoma, colon normal, lung adenocarcinoma, lung normal, and lung squamous cell carcinoma, split into training (80%), validation (10%), and test (10%) subsets. In this study, we propose the ViT-DCNN (Vision Transformer with Deformable CNN) model, with the aim of improving cancer detection and classification using medical images. Methods: The combination of the ViT’s self-attention capabilities with deformable convolutions allows for improved feature extraction, while also enabling the model to learn both holistic contextual information as well as fine-grained localized spatial details. Results: On the test set, the model performed remarkably well, with an accuracy of 94.24%, an F1 score of 94.23%, recall of 94.24%, and precision of 94.37%, confirming its robustness in detecting cancerous tissues. Furthermore, our proposed ViT-DCNN model outperforms several state-of-the-art models, including ResNet-152, EfficientNet-B7, SwinTransformer, DenseNet-201, ConvNext, TransUNet, CNN-LSTM, MobileNetV3, and NASNet-A, across all major performance metrics. Conclusions: By using deep learning and advanced image analysis, this model enhances the efficiency of cancer detection, thus representing a valuable tool for radiologists and clinicians. This study demonstrates that the proposed ViT-DCNN model can reduce diagnostic inaccuracies and improve detection efficiency. Future work will focus on dataset enrichment and enhancing the model’s interpretability to evaluate its clinical applicability. This paper demonstrates the promise of artificial-intelligence-driven diagnostic models in transforming lung and colon cancer detection and improving patient diagnosis. Full article

In recent years, hybrid models that integrate Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs) have achieved significant improvements in hyperspectral image classification (HSIC). Nevertheless, their complex architectures often lead to computational redundancy and inefficient feature fusion, particularly struggling to balance global modeling and local detail extraction in high-dimensional spectral data. To solve these issues, this paper proposes a Spectral-Cube Gated Harmony Network (SCGHN) that achieves efficient spectral–spatial joint feature modeling through a dynamic gating mechanism and hierarchical feature decoupling strategy. There are three primary innovative contributions of this paper as follows: Firstly, we design a Spectral Cooperative Parallel Convolution (SCPC) module that combines dynamic gating in the spectral dimension and spatial deformable convolution. This module adopts a dual-path parallel architecture that adaptively enhances key bands and captures local textures, thereby significantly improving feature discriminability at mixed ground object boundaries. Secondly, we propose a Dual-Gated Fusion (DGF) module that achieves cross-scale contextual complementarity through group convolution and lightweight attention, thereby enhancing hierarchical semantic representations with significantly lower computational complexity. Finally, by means of the coordinated design of 3D convolution and lightweight classification decision blocks, we construct an end-to-end lightweight framework that effectively alleviates the structural redundancy issues of traditional hybrid models. Extensive experiments on three standard hyperspectral datasets reveal that our SCGHN requires fewer parameters and exhibits lower computational complexity as compared with some existing HSIC methods. Full article

Mineral identification technology is a key technology in the construction of intelligent mines. In ore classification and detection, mining scenarios present challenges, such as diverse ore types, significant scale variations, and complex surface textures. Traditional detection models often suffer from insufficient multi-scale feature representation and weak dynamic adaptability, leading to the missed detection of small targets and misclassification of similar minerals. To address these issues, this paper proposes an efficient multi-scale ore classification and detection model, YOLO-EDH. To begin, standard convolution is replaced with deformable convolution, which efficiently captures irregular defect patterns, significantly boosting the model’s robustness and generalization ability. The C3k2 module is then combined with a modified dynamic convolution module, which avoids unnecessary computational overhead while enhancing the flexibility and feature representation. Additionally, a content-guided attention fusion (HGAF) module is introduced before the detection phase, ensuring that the model assigns the correct importance to various feature maps, thereby highlighting the most relevant object details. Experimental results indicate that YOLO-EDH surpasses YOLOv11, improving the precision, recall, and mAP50 by 0.9%, 1.7%, and 1.6%, respectively. In conclusion, YOLO-EDH offers an efficient solution for ore detection in practical applications, with considerable potential for industries like intelligent mine resource sorting and safety production monitoring, showing notable commercial value. Full article

Background/Objectives: Adolescent idiopathic scoliosis (AIS) is a three-dimensional spinal deformity often requiring surgical correction in severe cases. Halo-gravity traction (HGT) is commonly employed preoperatively to enhance spinal flexibility and reduce curve severity. This study aimed to evaluate the effectiveness of HGT in reducing Cobb angles in AIS and to assess how patient age, skeletal maturity (Risser score), and curve type (Lenke classification) influence treatment response. Methods: We conducted a retrospective cohort study of 28 AIS patients with Cobb angles > 65° who underwent preoperative HGT followed by posterior spinal fusion. Traction was applied for a mean of 24.64 days, reaching 40–50% of each patient’s body weight. Radiographic measurements were collected pre-traction, post-traction, and postoperatively. Statistical analyses included paired t-tests, Pearson correlations, Kruskal–Wallis tests, and linear regression. Results: Mean primary Cobb angle was reduced from 82.46° pre-traction to 61.00° post-traction (26.09% reduction) and further to 29.54° postoperatively (64.58% total reduction). Similar reductions were observed in secondary curves. No statistically significant correlations were found between age or Risser score and the magnitude of correction. Lenke type 3 showed the highest traction response, while type 5 had the greatest surgical gain. Curve type and skeletal maturity did not significantly affect final outcomes. Conclusions: Halo-gravity traction is a safe and effective adjunct in the surgical treatment of severe AIS, achieving substantial Cobb angle reduction. The degree of correction was not significantly influenced by age, Risser score, or curve type, supporting the broad applicability of HGT across adolescent patients. Full article

Background/Objectives: Knee osteoarthritis (KOA) is a prevalent disorder affecting both older adults and younger individuals, leading to compromised joint function and mobility. Early and accurate detection is critical for effective intervention, as treatment options become increasingly limited as the disease progresses. Traditional diagnostic methods rely heavily on the expertise of physicians and are susceptible to errors. The demand for utilizing deep learning models in order to automate and improve the accuracy of KOA image classification has been increasing. In this research, a unique deep learning model is presented that employs autoencoders as the primary mechanism for feature extraction, providing a robust solution for KOA classification. Methods: The proposed model differentiates between KOA-positive and KOA-negative images and categorizes the disease into its primary severity levels. Levels of severity range from “healthy knees” (0) to “severe KOA” (4). Symptoms range from typical joint structures to significant joint damage, such as bone spur growth, joint space narrowing, and bone deformation. Two experiments were conducted using different datasets to validate the efficacy of the proposed model. Results: The first experiment used the autoencoder for feature extraction and classification, which reported an accuracy of 96.68%. Another experiment using autoencoders for feature extraction and Extreme Learning Machines for actual classification resulted in an even higher accuracy value of 98.6%. To test the generalizability of the Knee-DNS system, we utilized the Butterfly iQ+ IoT device for image acquisition and Google Colab’s cloud computing services for data processing. Conclusions: This work represents a pioneering application of autoencoder-based deep learning models in the domain of KOA classification, achieving remarkable accuracy and robustness. Full article

Background/Objectives: Semiquantitative grading of the vertebral body (SQ) is an easy screening method for vertebral body deformation. The validity of SQ as a risk factor and screening tool for incident osteoporotic fractures in the vertebral body (OF) was investigated using retrospective case-control data. Methods: Outpatients with osteoporosis who were followed up for ≥2 years as patients with osteoporosis were recruited. All of them were tested using X-ray images of the lateral thoracolumbar view and other tests at baseline. Patients were classified according to the SQ grade, and potential risk factors were compared for each SQ group. Cox regression analyses were conducted on the incident OFs. Statistical differences in the possible risk factors among the groups and the likelihood of incident OFs in the variables were examined. After propensity score matching (PSM) and inverse probability of treatment weighting (IPTW) for confounding factors, the possibility of incident OFs was compared between the SQ grade groups. Results: In the crude dataset, the probability of incident OF in SQ Grade 3 was significantly higher than in other grade groups. Using a Cox regression analysis in multivariate mode, SQ grade was the only statistically significant factor for incident OF. However, no significant differences were observed between PSM and IPTW. Conclusions: These results suggest that the SQ classification was inappropriate for predicting incident OFs. However, the grading showed a significantly higher risk than that available for screening. Full article

Background and Objectives: Artificial intelligence (AI) has seen rapid integration into various areas of medicine, particularly with the advancement of machine learning (ML) and deep learning (DL) techniques. In pediatric orthopedics, the adoption of AI technologies is emerging but still not comprehensively reviewed. The purpose of this study is to review the latest evidence on the applications of artificial intelligence in the field of pediatric orthopedics. Materials and Methods: A literature search was conducted using PubMed and Web of Science databases to identify peer-reviewed studies published up to March 2024. Studies involving AI applications in pediatric orthopedic conditions—including spinal deformities, hip disorders, trauma, bone age assessment, and limb discrepancies—were selected. Eligible articles were screened and categorized based on application domains, AI models used, datasets, and reported outcomes. Results: AI has been successfully applied across several pediatric orthopedic subspecialties. In spinal deformities, models such as support vector machines and convolutional neural networks achieved over 90% accuracy in classification and curve prediction. For developmental dysplasia of the hip, deep learning algorithms demonstrated high diagnostic performance in radiographic interpretation. In trauma care, object detection models like YOLO and ResNet-based classifiers showed excellent sensitivity and specificity in pediatric fracture detection. Bone age estimation using DL models often matched or outperformed traditional methods. However, most studies lacked external validation, and many relied on small or single-institution datasets. Concerns were also raised about image quality, data heterogeneity, and clinical integration. Conclusions: AI holds significant potential to enhance diagnostic accuracy and decision making in pediatric orthopedics. Nevertheless, current research is limited by methodological inconsistencies and a lack of standardized validation protocols. Future efforts should focus on multicenter data collection, prospective validation, and interdisciplinary collaboration to ensure safe and effective clinical integration. Full article

Background: Hypotension is a common adverse effect associated with the use of propofol and sodium thiopental. The objective of this study was to examine the impact of thiopental and propofol on erythrocyte (RBC) nitric oxide (NO) synthase activity and RBC-mediated NO release. Methods: A prospective, interventional in vitro trial. Male patients aged between 18 and 45 years with a classification of American Society of Anesthesiologists (ASA) class I, defined as healthy individuals, were included in this study. Venous blood samples (20 mL) were obtained from patients who met the inclusion criteria. Measurements were performed using the specific fluorescent probes for NO and calcium (Ca²⁺). Propofol and sodium thiopental were added to the suspensions at doses of 100, 250, 500, and 1000 μM and incubated for 30 min. All suspensions were proceeded to flow cytometric analysis. Nitrite/nitrate concentration was measured in the supernatant of RBC suspensions after centrifugation. RBC deformability and aggregation were measured by laser diffraction analysis using an ektacytometer. The primary outcome was to evaluate the effects of sodium thiopental and propofol on RBC-NOS activity. Results: Sodium thiopental caused significant increase in intracellular NO concentrations at all doses studied (p < 0.001). Importantly, the intracellular NO concentration increment was positively correlated with sodium thiopental concentration in the suspensions. The presence of L-N-acetylmethyl-arginine in the experimental medium abolished NO production in RBCs in response to sodium thiopental. Sodium thiopental caused increased nitrite and nitrate levels in the suspension medium in a dose-dependent manner. Incubation with thiopental caused an increase in intracellular free Ca⁺² levels while propofol induced no change. Sodium thiopental and propofol caused significant decrement in RBC aggregation. Conclusions: This study presents the initial evidence of augmented RBC-mediated NO production and release in response to sodium thiopental administration. In contrast to the effects observed with sodium thiopental, our results demonstrated that propofol had no impact on RBC-mediated NO production. Full article

Early and accurate identification of landslide-prone areas is critical for monitoring and early-warning systems, forming the foundation of disaster prevention and mitigation. However, current landslide susceptibility assessment methods often rely on arbitrary probability classification thresholds, leading to subjective and regionally non-adaptive results that neglect low-susceptibility areas, thereby limiting their practical utility in disaster management. To address these limitations, this study proposes a novel method for identifying landslide-prone areas by integrating multi-factor analysis with adaptive probability thresholds. The methodology combines landslide catalog data with key landslide influencing factors, including geology, topography, precipitation, surface deformation, and human activities. The gradient boosting decision tree (GBDT) algorithm is employed to estimate landslide susceptibility probabilities, while an adaptive threshold criterion—based on minimizing the Jensen–Shannon (JS) divergences weighted sum between landslide-prone areas and positive samples—is established to objectively classify regions. Validation experiments were conducted in the northern Tongren region of the Longwu River Basin, Qinghai Province, China. Historical landslides (February 2016–June 2017) were used for model training, and subsequent landslides (June 2017–November 2022) served as validation data. The results demonstrate exceptional performance: the susceptibility model achieved an AUC value of 0.99, with 94.07% accuracy in classifying landslides positive samples. Furthermore, 77.78% of post-2017 landslides occurred within the identified prone areas, yielding a 22.22% omission rate. These findings highlight the method’s ability to dynamically adapt to regional characteristics, balance sensitivity and specificity, and provide actionable insights for landslide risk management. Full article

Robotic manipulation of objects with diverse shapes, sizes, and properties, especially deformable ones, remains a significant challenge in automation, necessitating human-like dexterity through the integration of perception, learning, and control. This study enhances a previous framework combining YOLOv8 for object detection and LSTM networks for adaptive grasping by introducing Gaussian Processes (GPs) for robust grasp predictions and Transformer models for efficient multi-modal sensory data integration. A Random Forest classifier also selects optimal grasp configurations based on object-specific features like geometry and stability. The proposed grasping framework achieved a 95.6% grasp success rate using Transformer-based force modulation, surpassing LSTM (91.3%) and GP (91.3%) models. Evaluation of a diverse dataset showed significant improvements in grasp force modulation, adaptability, and robustness for two- and three-finger grasps. However, limitations were observed in five-finger grasps for certain objects, and some classification failures occurred in the vision system. Overall, this combination of vision-based detection and advanced learning techniques offers a scalable solution for flexible robotic manipulation. Full article

The recognition and classification of building shapes are the prerequisites and foundation for building simplification, matching, and change detection, which have always been important research problems in the field of cartographic generalization. Due to the ambiguity and uncertainty of building shape outlines, it is difficult to describe them using unified rules, which has always limited the quality and automation level of building shape recognition. In response to the above issues, by introducing object detection technology in computer vision, this article proposes a building shape recognition and classification method based on the YOLO object detection model. Firstly, for different types of buildings, four levels of building training data samples are constructed, and YOLOv5, YOLOv8, YOLOv9, and YOLOv9 integrating attention modules are selected for training. The trained models are used to test the shape judgment of buildings in the dataset and verify the learning effectiveness of the models. The experimental results show that the YOLO model can accurately classify and locate the shape of buildings, and its recognition and detection effect have the ability to simulate advanced human visual cognition, which provides a new solution for the fuzzy shape recognition of buildings with complex outlines and local deformation. Full article