Search Results (36)

Kneeosteoarthritis (KOA) is a common degenerative joint disease that causes pain, stiffness, and impaired mobility. Automated Kellgren–Lawrence (KL) grading from knee X-ray images facilitates efficient screening and follow-up assessment. However, models trained on a single-source dataset frequently suffer performance degradation when applied to external cohorts, due to heterogeneities in image quality, acquisition protocols, class distributions, and annotation patterns. Furthermore, conventional domain adaptation approaches typically treat all source samples uniformly, making them vulnerable to negative transfer induced by ambiguous or distributionally divergent instances. To overcome these limitations, the present study develops a supervised contrastive domain adaptation framework designed for robust KOA severity grading under domain shift. The framework incorporates two task-specific modules: (1) a source-domain sample screening module that dynamically allocates class-wise quotas based on transferability and identifies high-value source samples by evaluating target intra-class affinity, inter-class separability, and source-class compactness; and (2) a target-balanced ordinal contrastive learning module that aligns the screened source samples with target features and imposes stronger constraints on negative pairs with larger KL-grade distances. The framework was evaluated bidirectionally on KneeKL (8260 images) and MedicalExpert-I (1650 images), two public knee radiograph datasets for KOA grading. With ResNet-18, it achieved a Quadratic Weighted Kappa (QWK) of 0.8557 for KneeKL-to-MedicalExpert-I transfer, exceeding source-only training and direct source–target merging by 0.2652 and 0.0468, respectively. Comparisons with representative existing methods and multiple experimental analyses further validate the competitiveness of the proposed framework. Full article

Based on the previously screened high-performance strain Lactobacillus LP707, this study systematically investigated the effects of its co-fermentation with yeast on properties of millet starch. By comparing starch samples from unfermented, yeast-only fermented, Lactobacillus-only fermented and co-fermented treatments, it was found that co-fermentation reduced the amylose content of millet starch to 17.45% and shifted the molecular weight distribution toward lower values. Scanning electron microscopy revealed more pronounced surface erosion features on the co-fermented starch granules. X-ray diffraction and Fourier-transform infrared spectroscopy confirmed that co-fermentation did not alter the A-type crystalline pattern of starch; however, the short-range ordered structure ratio (1.45), relative crystallinity (20.78%), and gelatinization enthalpy (7.32 J/g) were significantly reduced, indicating dissociation of ordered structures. Pasting property analysis showed that the final viscosity and setback value of co-fermented starch decreased significantly. Low-field nuclear magnetic resonance analysis of water distribution indicated an increased proportion of free water with reduced mobility in the co-fermented starch gel. In vitro digestion confirmed higher hydrolysis rates and increased rapidly digestible starch content in co-fermented starch. In summary, co-fermentation with Lactobacillus LP707 and yeast more effectively modified properties of millet starch, providing a theoretical foundation for targeted functional improvement through microbial co-fermentation technology. Full article

An eco-friendly green synthesis approach was employed to produce copper nanoparticles (CuNPs) using a polyherbal extract derived from two medicinally important plant species, Hygrophila auriculata (Schumach.) Heine and Leucas aspera (Willd.) Link. The plant extracts were initially subjected to phytochemical screening to identify bioactive constituents potentially involved in nanoparticle synthesis. The synthesized CuNPs were characterized using UV-visible spectroscopy, Fourier-transform infrared spectroscopy (FTIR), gas chromatography–mass spectrometry (GC-MS), field-emission scanning electron microscopy coupled with energy-dispersive X-ray analysis (FESEM-EDAX), X-ray diffraction (XRD), and thin-layer chromatography (TLC). UV-visible spectroscopy revealed a characteristic absorption peak at 233.6 nm. FTIR analysis indicated the presence of functional groups associated with nanoparticle reduction and stabilization, whereas FESEM imaging showed predominantly spherical particles with sizes ranging 63–68 nm. Elemental composition was confirmed using EDAX analysis. XRD analysis demonstrated polycrystalline nature of the CuNPs, with an average crystallite size of 11.5 nm. GC-MS analysis and phytochemical screening further confirmed the presence of bioactive compounds, whereas TLC analysis revealed differences in mobility between the plant extract and synthesized CuNPs. Antibacterial activity of the synthesized CuNPs was evaluated using the agar well diffusion method against clinically relevant bacterial strains, including those of Staphylococcus aureus, Pseudomonas aeruginosa, Escherichia coli, and Streptococcus pyogenes. The polyherbal-derived CuNPs produced larger inhibition zones than the individual plant extracts, particularly against multidrug-resistant pathogens such as P. aeruginosa and S. aureus. Additionally, the nanoparticles exhibited concentration-dependent antioxidant activity in the 2,2-diphenyl-1-picrylhydrazyl assay at concentrations ranging 10–50 mg/mL, with radical scavenging activity increasing from 29.9% to 76.5% and a corresponding decrease in absorbance from 0.698 to 0.234 (p < 0.05). Cytotoxic evaluation in HepG2 cells after 48 h of exposure demonstrated dose-dependent morphological changes and reduced cell viability. These findings suggest that polyherbal-derived CuNPs possess antibacterial, antioxidant, and cytotoxic properties with potential relevance for biomedical applications. Full article

Background and Objectives: Osteoporosis is a prevalent skeletal disorder characterized by decreased bone mass and compromised bone microarchitecture, leading to an elevated risk of fractures and significant morbidity, particularly among aging populations. Early diagnosis and personalized management are critical to reducing fracture incidence and associated healthcare burdens. Recent advances in artificial intelligence (AI) and machine learning (ML) have led to potential improvements in enhancing osteoporosis care by enabling accurate diagnostic imaging analysis, robust fracture risk prediction, and personalized therapeutic strategies. Materials and Methods: We performed a narrative review to summarize and critically evaluate the current literature on AI and ML applications in osteoporosis diagnosis and management. We searched relevant literature from inception to January 2025 to provide a comprehensive perspective, focusing on key themes, methodological approaches, and clinical implications. Results: Deep learning models, especially convolutional neural networks, facilitate rapid and accurate bone mineral density assessment from routine radiographs, expanding screening capabilities beyond conventional dual-energy X-ray absorptiometry (DXA). Machine learning algorithms harness clinical and demographic data to generate fracture risk models that often outperform traditional tools, enabling timely identification of high-risk individuals. Furthermore, AI-driven analyses of historical treatment responses coupled with real-time monitoring through wearable technologies and mobile applications allow for personalized therapeutic optimization and enhance patient engagement. Despite these promising advances, challenges remain regarding ethical considerations, data privacy, legal liability, incomplete model validation, lack of standardization, and the need for critical appraisal of real-world clinical efficacy for widespread clinical adoption. Conclusions: This narrative review indicates that AI and ML hold significant promise to revolutionize osteoporosis management by enabling early detection, precise risk stratification, and tailored interventions. However, the current evidence is heterogeneous, often lacking robust external validation and quantitative synthesis. Critical gaps include insufficient evaluation of model robustness across diverse populations, discussion of negative or conflicting results, and a comprehensive assessment of the limitations inherent in current AI evidence. Strategic efforts to validate, regulate, and critically integrate these technologies into routine clinical workflows are essential to realize their full potential and address the growing burden of osteoporosis worldwide. Full article

There are many obstacles to the industrial application of CO₂ hydrogenation reduction technology, the most important of which is the high economic cost. The purpose of this study is to explore the interaction mechanism between the active component CuO-ZnO-Al₂O₃(CZA) and the zeolite carrier Zeolite Socony Mobil-5(ZSM-5), screen the simplified preparation method of catalysts with high catalytic performance, and further promote the industrial application of CO₂ hydrogenation reduction technology. In this study, the effects of the gas velocity of the feedstock, the reaction temperature, the content of acidic sites in the carrier, the filling amount of active component, and the mixing mode of the active component and the carrier on catalytic CO₂ hydrogenation reduction were investigated. The structure of the catalysts was analyzed by X-ray diffractometer (XRD), Brunauer-Emmett-Teller (BET), Fourier-transform infrared spectroscopy (FTIR), scanning electron microscope (SEM) and transmission electron microscopy (TEM). The catalyst surface properties were analyzed by X-ray photoelectron spectroscopy (XPS), ammonia temperature programmed desorption (NH₃-TPD), hydrogen temperature programed reduction (H₂-TPR) and other characterization methods. The research found that the grinding treatment led to the insertion of CZA between ZSM-5 zeolite particles in CZA@HZ5-20-GB, which was prepared via grinding both CZA and H-ZSM-5 with an Si/Al ratio of 20, inhibiting the action of strongly acidic sites in the zeolite, resulting in only CO and MeOH in the catalytic products, with no Dimethyl Ether (DME) generation. Full article

Breast cancer is one of the leading causes of death among women of all ages and backgrounds globally. In recent years, the growing deficit of expert radiologists—particularly in underdeveloped countries—alongside a surge in the number of images for analysis, has negatively affected the ability to secure timely and precise diagnostic results in breast cancer screening. AI technologies offer powerful tools that allow for the effective diagnosis and survival forecasting, reducing the dependency on human cognitive input. Towards this aim, this research introduces a deep meta-learning framework for swift analysis of mammography images—combining a Siamese network model with a triplet-based loss function—to facilitate automatic screening (recognition) of potentially suspicious breast cancer cases. Three pre-trained deep CNN architectures, namely GoogLeNet, ResNet50, and MobileNetV3, are fine-tuned and scrutinized for their effectiveness in transforming input mammograms to a suitable embedding space. The proposed framework undergoes a comprehensive evaluation through a rigorous series of experiments, utilizing two different, publicly accessible, and widely used datasets of digital X-ray mammograms: INbreast and CBIS-DDSM. The experimental results demonstrate the framework’s strong performance in differentiating between tumorous and normal images, even with a very limited number of training samples, on both datasets. Full article

Background: Sarcopenia is a progressive muscle disease that compromises mobility and quality of life in older adults. Although dual-energy X-ray absorptiometry (DXA) is the standard for assessing Appendicular Lean Mass Index (ALMI), it is costly and often inaccessible. This study aims to develop machine learning models using anthropometric measurements to predict low ALMI for the diagnosis of sarcopenia. Methods: A cross-sectional study was conducted on 183 Mexican adults (67.2% women and 32.8% men, ≥60 years old). ALMI was measured using DXA, and anthropometric data were collected following the International Society for the Advancement of Kinanthropometry (ISAK) protocols. Predictive models were developed using Logistic Regression (LR), Decision Trees (DTs), Random Forests (RFs), Artificial Neural Networks (ANNs), and LASSO regression. The dataset was split into training (70%) and testing (30%) sets. Model performance was evaluated using classification performance metrics and the area under the ROC curve (AUC). Results: ALMI indicated strong correlations with BMI, corrected calf girth, and arm relaxed girth. Among models, DT achieved the best performance in females (AUC = 0.84), and ANN indicated the highest AUC in males (0.92). Regarding the prediction of low ALMI, specificity values were highest in DT for females (100%), while RF performed best in males (92%). The key predictive variables varied depending on sex, with BMI and calf girth being the most relevant for females and arm girth for males. Conclusions: Anthropometry combined with machine learning provides an accurate, low-cost approach for identifying low ALMI in older adults. This method could facilitate sarcopenia screening in clinical settings with limited access to advanced diagnostic tools. Full article

Hallux valgus is a common foot deformity. Traditional diagnosis mainly relies on X-ray images, which present radiation risks and require professional equipment, limiting their use in daily screening. In addition, in large-scale community screenings and resource-limited regions, where rapid processing of numerous patients is required, access to radiographic equipment or specialists may be constrained. Therefore, this study improves the MobileNetV3 model to automatically determine the presence of hallux valgus from digital foot photographs. In this study, we used 2934 foot photos from different organizations, combined with the segment anything model (SAM) to extract foot regions and replace the photo backgrounds to simulate different shooting scenarios, and used data enhancement techniques such as rotations and noise to extend the training set to more than 10,000 images to improve the diversity of the data and the model’s generalization ability. We evaluated several classification models and achieved over 95% accuracy, precision, recall, and F1 score by training the improved MobileNetV3. Our model offers a cost-effective, radiation-free solution to reduce clinical workload and enhance early diagnosis rates in underserved areas. Full article

Small waste from electrical and electronic equipment (WEEE) such as waste mobile phones are rich in plastic components. Recycling mobile phones is particularly challenging, since the main interest for recyclers is printed circuit boards, rich in valuable metals, while the plastic components are usually destined for thermal recovery. This study is dedicated to the assessment of the recyclability potential of the plastic fractions of end-of-life (EoL) mobile phones according to the European Union’s (EU) Restriction of Hazardous Substances (RoHS) and Registration, Evaluation, Authorization and Restriction of Chemicals (REACH) directives. A total of 275 plastic items (inventoried as casings, frames, and screens) were dismantled from 100 EoL mobile phones and analyzed to identify the type and abundance of polymers via Fourier-transform infrared spectroscopy (FTIR) and the presence of hazardous elements such as Br, Cl, Pb, and Cd via X-ray fluorescence (XRF). Polycarbonate (PC) (57% of samples) and polymethyl methacrylate (PMMA) (27% of the items) were identified as the most common prevalent polymers. In total, 67% of the items contained Cl (0.84–40,700 mg/kg), and 26% contained Br (0.08–2020 mg/kg). Hg was detected only in one item (17 mg/kg). Cr was found in 17% of the items, with concentrations between 0.37 mg/kg and 915 mg/kg, while Pb was found in 15% of the items in low concentrations (1–90 mg/kg). In conclusion, while hazardous elements are present in the plastic fractions of EoL mobile phones (with higher values in smartphones), their concentrations were below the regulatory limits, suggesting compliance with recycling regulations in the EU. Full article

Background: The Xpert MTB/RIF Ultra assay (Ultra) is a second-generation molecular diagnostic test for tuberculosis (TB). The “Trace Call” result was added as a semi-quantitative category for extremely low bacillary loads. The prevalence and interpretation of Trace Call results remains insufficiently elucidated in the context of community-based active case finding (ACF). Methods: We organized 56 days of mobile chest X-ray (CXR) screening events in Ho Chi Minh City, Viet Nam, between October 2020 and March 2021. Participants were screened verbally and by CXR and tested by Ultra, if eligible. Persons with a Trace Call were re-tested on Ultra per national guidelines. qXRv3 computer-aided detection software was used for post hoc quality control of CXR interpretation. We calculated descriptive statistics and fitted mixed-effect multivariate regression models to identify factors associated with Trace Call results and confirmatory diagnosis. Results: A total of 16,698 people were screened by CXR to detect 185 Ultra-positive participants, including 142 persons with a confirmed TB diagnosis. Among Ultra-positive participants, 38.4% (71/185) had Trace Call results. Of these, 85.9% (61/71) were re-tested, and 45.9% (28/61) were bacteriologically-confirmed, comprising 19.7% (28/142) of the final number of confirmed diagnoses. Having a low qXR abnormality score (<0.5) (aOR = 4.97; 95%CI: [1.88, 13.14]; p = 0.001) and a history of TB within 5 recent years (aOR = 3.53; 95%CI: [1.69, 7.35]; p = 0.001) were associated with an initial Trace Call. Conclusions: The Trace Call can improve ACF detection, particularly in earlier stages of disease with limited pulmonary deterioration. However, participants with a history of TB had higher rates of Trace Call, reinforcing the need to interpret test results in this group with caution. Full article

The traditional scoliosis examination based on X-ray film is not suitable for large-scale screening, and it is also not suitable for dynamic evaluation during rehabilitation. Therefore, based on computer vision technology, this paper puts forward an evaluation method of scoliosis with different photos of the back taken by mobile phones, which involves three aspects: first, based on the key point detection model of YOLOv8, an algorithm for judging the type of spinal coronal curvature is proposed; second, an algorithm for evaluating the coronal plane of the spine based on the key points of the human back is proposed, aiming at quantifying the deviation degree of the spine in the coronal plane; third, the measurement algorithm of trunk rotation (ATR angle) based on multi-scale automatic peak detection (AMPD) is proposed, aiming at quantifying the deviation degree of the spine in sagittal plane. The public dataset and clinical paired data (mobile phone photo and X-ray) are used to test. The results show that this method has high accuracy and effectiveness in distinguishing the type of spinal curvature and evaluating the degree of deviation, which is higher than other deep learning algorithms. Full article

Obtaining high-resolution 3D structures of membrane proteins through X-ray crystallography remains a longstanding bottleneck in the field of structural biology. This challenge has led to the optimization of purification methods to acquire high-yielding, pure proteins suitable for crystallization. In this study, we performed crystallization screenings of purified human α4β2 nAChR using a polarized in meso method. After reconstituting the detergent-solubilized α4β2 nAChR into the LCP matrix, the samples were incubated in a polarized lipid matrix using the RMP@LMx device developed in our laboratory. The results showed that under these conditions, the α4β2-nAChR-LFC 16 complex gave a mobile fraction >0.8, suggesting that its diffusion in the polarized lipid matrix is favorable for crystal nucleation. Voltages above 70 mV restricted crystal formation due to sample dehydration. Furthermore, a lipid analysis using UPLC-ESI MS/MS revealed a profile necessary for preserving protein integrity and promoting diffusion across the LCP. We harvested a single crystal and subjected it to X-ray diffraction, resulting in reflections comparable to previous studies of the muscle-type nAChR from Torpedo californica. X-ray diffraction of a single crystal gave distinct low-resolution diffractions of protein nature. These findings lay the groundwork for further optimization of membrane protein crystallization in polarized in meso phases. Full article

This paper presents a formative assessment for the implementation of mobile portable chest X-ray (PDX) machines for tuberculosis (TB) contact tracing in the Oyo and Osun states, Nigeria. This descriptive qualitative study was carried out in eight local government areas, and 24 focus group discussions and 30 key informant interviews were conducted using a four-stage sampling technique to select participants. Validated transcribed notes were entered and analyzed using Nvivo. The respondents’ ages ranged from 17 to 85 years, with a mean age of 42.08 ± 14.9 years, and 4.0% had a postgraduate degree. The majority of government officials stated that deploying the PDX machine for screening at the community level is the best means for implementation because it will offer a level of proximity convenience to the TB contacts and assuage concerns about the cost of transportation to the health facility. In addition, it was suggested that TB community screening should be carried out with screening for other health conditions such as high blood pressure and diabetes. This portable X-ray machine intervention, therefore, should be implemented at the community level for contact tracing to allow more TB contacts living with the index patient to be screened without proximity and transportation constraints. Full article

COVID-19 significantly disrupted tuberculosis (TB) services in Vietnam. In response, the National TB Program (NTP) integrated TB screening using mobile chest X-rays into COVID-19 vaccination events. This prospective cohort study evaluated the integrated model’s yield, treatment outcomes, and costs. We further fitted regressions to identify risk factors and conduct interrupted time-series analyses in the study area, Vietnam’s eight economic regions, and at the national level. At 115 events, we conducted 48,758 X-ray screens and detected 174 individuals with TB. We linked 89.7% to care, while 92.9% successfully completed treatment. The mean costs per person diagnosed with TB was $547. TB risk factors included male sex (aOR = 6.44, p < 0.001), age of 45–59 years (aOR = 1.81, p = 0.006) and ≥60 years (aOR = 1.99, p = 0.002), a history of TB (aOR = 7.96, p < 0.001), prior exposure to TB (aOR = 3.90, p = 0.001), and symptomatic presentation (aOR = 2.75, p < 0.001). There was a significant decline in TB notifications during the Delta wave and significant increases immediately after lockdowns were lifted (IRR(γ₁) = 5.00; 95%CI: (2.86, 8.73); p < 0.001) with a continuous upward trend thereafter (IRR(γ₂) = 1.39; 95%CI: (1.22, 1.38); p < 0.001). Similar patterns were observed at the national level and in all regions but the northeast region. The NTP’s swift actions and policy decisions ensured continuity of care and led to the rapid recovery of TB notifications, which may serve as blueprint for future pandemics. Full article

Mechanochemical activation, by means of high-energy ball milling, was applied to CeO₂ as a strategy to enhance its physicochemical properties. Different milling times were screened to evaluate their effect on ceria. The fluorite-type structure of cerianite was maintained in all cases, no matter the amount of energy introduced by the milling process, as observed via X-ray diffraction (XRD). A decrease in crystallite sizes and a consequent increase in specific surface area (S_BET) were observed through XRD and N₂ sorption (BET method). Pore diameters and total pore volumes were also in line with the duration of CeO₂ milling. Moreover, redox properties and oxygen mobility studied through H₂ temperature-programmed reduction (H₂- TPR) showed an increase in reducibility with milling time, including signals of both bulk and surface ceria, due to the greater number of defects and/or oxygen vacancies achieved by mechanochemical activation. The obtained features could play an essential role in terms of metal–support interaction, reactant adsorption and/or oxygen supply during catalytic reactions. Thus, high-energy ball milling is a useful, simple and green method for the design of materials with catalytic applications. Full article