Search

Machine- and deep-learning methods are used for industrial applications in prognostics and health management (PHM) for semiconductor processing and equipment anomaly detection to achieve proactive equipment maintenance and prevent process interruptions or equipment downtime. This study proposes a Pruning Quantized Unsupervised Meta-learning DegradingNet Solution (PQUM-DNS) for the fast training and retraining of new equipment or processes with limited data for anomaly detection and the prediction of various equipment and process conditions. This study utilizes real data from a factory chiller host motor, the Paderborn current and vibration open dataset, and the SECOM semiconductor open dataset to conduct experimental simulations, calculate the average value, and obtain the results. Compared to conventional deep autoencoders, PQUM-DNS reduces the average data volume required for rapid training and retraining by about 75% with similar AUC. The average RMSE of the predictive degradation degree is 0.037 for Holt–Winters, and the model size is reduced by about 60% through pruning and quantization which can be realized by edge devices, such as Raspberry Pi. This makes the proposed PQUM-DNS very suitable for intelligent equipment management and maintenance in industrial applications. [ABSTRACT FROM AUTHOR]

Osteoporosis is a common problem in orthopedic medicine, and it has become an important medical issue in orthopedics as Taiwan is gradually becoming an aging society. In the diagnosis of osteoporosis, the bone mineral density (BMD) derived from dual-energy X-ray absorptiometry (DXA) is the main criterion for orthopedic diagnosis of osteoporosis, but due to the high cost of this equipment and the lower penetration rate of the equipment compared to the X-ray images, the problem of osteoporosis has not been effectively solved for many people who suffer from osteoporosis. At present, in clinical diagnosis, doctors are not yet able to accurately interpret X-ray images for osteoporosis manually and must rely on the data obtained from DXA. In recent years, with the continuous development of artificial intelligence, especially in the fields of machine learning and deep learning, significant progress has been made in image recognition. Therefore, it is worthwhile to revisit the question of whether it is possible to use a convolutional neural network model to read a hip X-ray image and then predict the patient's BMD. In this study, we proposed a hip X-ray image segmentation model and a hip X-ray image recognition classification model. First, we used the U-Net model as a framework to segment the femoral neck, greater trochanter, Ward's triangle, and the total hip in the hip X-ray images. We then performed image matting and data augmentation. Finally, we constructed a predictive model for osteoporosis using deep learning algorithms. In the segmentation experiments, we used intersection over union (IoU) as the evaluation metric for image segmentation, and both the U-Net model and the U-Net++ model achieved segmentation results greater than or equal to 0.5. In the classification experiments, using the T-score as the classification basis, the total hip using the DenseNet121 model has the highest accuracy of 74%. [ABSTRACT FROM AUTHOR]

Stereotactic ablative radiotherapy (SABR) may improve survival in patients with inoperable pulmonary oligometastases. However, the impact of pulmonary oligometastatic status after systemic therapy on SABR outcomes remains unclear. Hence, we investigated the outcomes of SABR in 45 patients with 77 lung tumors and the prognostic value of pulmonary oligoprogression. Eligibility criteria were pulmonary oligometastases (defined as ≤5 metastatic lung tumors), controlled extrapulmonary disease (EPD) after front-line systemic therapy, SABR as primary local treatment for inoperable pulmonary metastases, and consecutive imaging follow-up. Oligometastatic lung tumor was classified into controlled or oligoprogressive status. Overall survival (OS), in-field progression-free survival (IFPFS), out-field progression-free survival (OFPFS), and prognostic variables were evaluated. With 21.8 months median follow-up, the median OS, IFPFS, and OFPFS were 28.3, not reached, and 6.5 months, respectively. Two-year OS, IFPFS, and OFPFS rates were 56.0%, 74.2%, and 17.3%, respectively. Oligoprogressive status (p = 0.003), disease-free interval < 24 months (p = 0.041), and biologically effective dose (BED10) < 100 Gy (p = 0.006) were independently associated with inferior OS. BED10 ≥ 100 Gy (p = 0.029) was independently correlated with longer IFPFS. Oligoprogressive status (p = 0.017) and EPD (p = 0.019) were significantly associated with inferior OFPFS. Grade ≥ 2 radiation pneumonitis occurred in four (8.9%) patients. Conclusively, SABR with BED10 ≥ 100 Gy could provide substantial in-field tumor control and longer OS for systemic therapy respondents with inoperable pulmonary oligometastases. Oligoprogressive lung tumors exhibited a higher risk of out-field treatment failure and shorter OS. Hence, systemic therapy should be tailored for patients with oligoprogression to reduce the risk of out-field treatment failure. However, in the absence of effective systemic therapy, SABR is a reasonable alternative to reduce resistant tumor burden. [ABSTRACT FROM AUTHOR]

With the rapid economic boom of Asian countries, the president of Country-A has made great efforts to reform in recent years. The prospect of economic development is promising, and business opportunities are emerging gradually, depicting a prosperous scene; accordingly, people's livelihood consumption also has changed significantly. The original main point of consumption for urban and rural people was the old and traditional grocery store with poor sanitation, but due to the economic improvement, the quality of consumption has also improved, and convenience stores are gradually replacing grocery store. However, convenience store management involves performance, logistic, competition, and personnel costs. Both whether the store can create a net profit and evaluate and select a new store will be important keys that significantly influence business performance. Therefore, this study attempts to use the industry data analysis method for highlighting a concept of processing an experience procedure of named 3-4-8-2 components combination in two stages. First, in the data preprocessing stage, this research considers 22 condition attributes and two types of decision factors, that include net profit and new store selection, and use both techniques of attribute selection and data discretization through the analysis and prediction of data mining tools. Next, in the experiment execution stage, three well-known classifiers (Bayes net, logistic regression, and J48 decision tree) with past good performance and four models (without preprocessing, with attribute selection, with data discretization, and with attribute selection and data discretization) are used for eight different experiments through two data verification methods (percentage split and cross-validation). Conclusively, three key results are identified from empirical analysis: (1) It is found that the prediction accuracy of the J48 decision tree classifier is relatively high and stable among the three classifiers in this study; at the same time, the J48 decision tree can yield comprehensible knowledge-based rules to instruct interested parties. (2) The results of this study show that the important attributes for the net profit decision attribute include the store type, POS number, and cashier number, while the important attributes for the new store selection include the store type and cashier number. (3) There is a difference in the selection of important attributes. Furthermore, four key valuable contributions are addressed from the empirical results, including academic contributions, enterprise contributions, application contributions, and management contributions. It is expected that the direction of store layout expansion can be found and identified through this study, but there are still many risks hidden behind the considerable business opportunities that need to be carefully managed. [ABSTRACT FROM AUTHOR]

To promote the expansion and adoption of Digital Twins (DTs) in Smart Cities (SCs), a detailed review of the impact of DTs and digitalization on cities is made to assess the progression of cities and standardization of their management mode. Combined with the technical elements of DTs, the coupling effect of DTs technology and urban construction and the internal logic of DTs technology embedded in urban construction are discussed. Relevant literature covering the full range of DTs technologies and their applications is collected, evaluated, and collated, relevant studies are concatenated, and relevant accepted conclusions are summarized by modules. First, the historical process and construction content of a Digital City (DC) under modern demand are analyzed, and the main ideas of a DC design and construction are discussed in combination with the key technology of DTs. Then, the metaverse is the product of the combination of various technologies in different scenes. It is a key component to promote the integration of the real world and the digital world and can provide more advanced technical support in the construction of the DC. DTs urban technology architecture is composed of an infrastructure terminal information center terminal and application server end. Urban intelligent management is realized through physical urban data collection, transmission, processing, and digital urban visualization. The construction of DTs urban platform can improve the city's perception and decision-making ability and bring a broader vision for future planning and progression. The interactive experience of the virtual world covered by the metaverse can effectively support and promote the integration of the virtual and real, and will also greatly promote the construction of SCs. In summary, this work is of important reference value for the overall development and practical adoption of DTs cities, which improves the overall operation efficiency and the governance level of cities. [ABSTRACT FROM AUTHOR]

Polyurethane (PU) has become one of the most widely used materials in the industrial field due to its excellent performance and wide range of applications. The increasing consumption of polyurethane materials has resulted in significant polyurethane waste. We can recycle waste polyurethane to obtain recycled polyurethane, but to make the recycled polyurethane meet different performance requirements in terms of utility and cost and enable the recycled polyether polyol to be further applied to high-end applications, it is necessary to improve the use value of recycled polyether polyol. In this paper, self-made Fluorodiol was added to the degradation process of waste polyurethane to obtain fluorinated regenerated polyether polyol. Recycled fluorinated polyurethane with excellent performance was prepared using fluorine-containing recycled polyether polyol. The regenerated fluorinated polyether polyols were characterized by infrared spectroscopy, viscosity, hydroxyl value, and GPC molecular weight distribution. The density, apparent morphology, water absorption, mechanical strength, thermal conductivity, and thermal stability of RFPU rigid foams with different fluorine contents were studied by scanning electron microscopy. The results show that when the addition of Fluorodiol was 8% of the mass of waste polyurethane, the density was 41.2 kg/m3, the immersion loss rate was 2.125%, the compressive strength was 0.315 Mpa, and the thermal conductivity was 0.0227 W/m·K. The RFPU prepared by Fluorodiol has low surface energy, good compressive strength, hydrolysis resistance, and is expected to be widely used in special insulation materials. Thus, the sustainable recycling of polyurethane is achieved. [ABSTRACT FROM AUTHOR]

Angiogenesis plays an important role in the development of bone and bone regeneration to provide the required molecules. Mesenchymal stem cells (MSCs) are pluripotent, self-renewing, and spindle-shaped cells, which can differentiate into multiple lineages such as chondrocytes, osteocytes, and adipocytes. MSCs derived from bone marrow (BMMSCs), adipose tissue (ADMSCs), and Wharton's jelly (UCMSCs) are popular in the field of tissue regeneration. MSCs have been proposed that can promote bone regeneration by enhancing vascularization. In this study, the angiogenic potential of secretomes of undifferentiated and osteo-differentiated BMMSCs, ADMSCs, and UCMSCs seeded on human decellularized allogeneic bone were compared. Human umbilical vein endothelial cells (HUVECs) were treated with MSC secretomes. Cell growth, cell migration, and angiogenesis of HUVECs were analyzed by MTT, wound healing, and tube formation assays. Angiogenic gene expression levels of MSCs were evaluated using real-time quantitative PCR. Antibody neutralization was performed to validate the candidate target. Our study demonstrates that the angiogenic gene expression profile is tissue-dependent and the angiogenic ability of secretomes is independent of the state of differentiation. We also explore that IL-1b is important for MSC angiogenic potential. Taken together, this study proves that IL-1b in the secretomes plays a vital role in angiogenesis. [ABSTRACT FROM AUTHOR]

The five-year overall survival rate of patients without neck lymph node recurrence is over 50% higher than those with lymph node metastasis. This study aims to investigate the prognostic impact of computed tomogram (CT)-based radiomics on the outcome of metastatic neck lymph nodes in patients with head and neck cancer (HNC) receiving definitive radiotherapy or chemoradiotherapy for organ preservation. The pretreatment 18F-FDG PET/CT of 79 HNC patients was retrospectively analyzed with radiomics extractors. The imbalanced data was processed using two techniques: over-sampling and under-sampling, after which the prediction model was established with a machine learning model using the XGBoost algorithm. The imbalanced dataset strategies slightly decreased the specificity but greatly improved the sensitivity. To have a higher chance of predicting neck cancer recurrence, however, clinical data combined with CT-based radiomics provides the best prediction effect. The original dataset performed was as follows: accuracy = 0.76 ± 0.07, sensitivity = 0.44 ± 0.22, specificity = 0.88 ± 0.06. After we used the over-sampling technique, the accuracy, sensitivity, and specificity values were 0.80 ± 0.05, 0.67 ± 0.11, and 0.84 ± 0.05, respectively. Furthermore, after using the under-sampling technique, the accuracy, sensitivity, and specificity values were 0.71 ± 0.09, 0.73 ± 0.13, and 0.70 ± 0.13, respectively. The outcome of metastatic neck lymph nodes in patients with HNC receiving radiotherapy for organ preservation can be predicted based on the results of machine learning. This way, patients can be treated alternatively. A further external validation study is required to verify our findings. [ABSTRACT FROM AUTHOR]

Simple Summary: Neoadjuvant chemoradiotherapy (NCRT) before surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model was introduced to predict responses to NCRT. The model employed metric learning combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. Using this model, the area under the receiver operating characteristic curve was 0.96 for predicting a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. After further external validation, oncologists may use the proposed model to advise patients on the relative suitability of treatment options, including the therapeutic decision between NCRT and neoadjuvant chemotherapy. Integrating this approach would have a notable effect on counseling patients about treatment alternatives or prognoses. Objectives: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT. Patients and Methods: This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. Results: In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively. Conclusions: The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model's predictive value. [ABSTRACT FROM AUTHOR]

Recombinant human thrombomodulin (rhTM), an angiogenesis factor, has been demonstrated to stimulate cell proliferation, keratinocyte migration and wound healing. The objective of this study was to develop nanostructured lipid carrier (NLC) formulations encapsulating rhTM for promoting chronic wound healing. RhTM-loaded NLCs were prepared and characterized. Encapsulation efficiency was more than 92%. The rate of rhTM release from different NLC formulations was influenced by their lipid compositions and was sustained for more than 72 h. Studies on diabetic mouse wound model suggested that rhTM-NLC 1.2 µg accelerated wound healing and was similar to recombinant human epidermal growth factor-NLC (rhEGF-NLC) 20 µg. By incorporating 0.085% carbopol (a highly crosslinked polyacrylic acid polymer) into rhTM NLC, the NLC-gel presented similar particle characteristics, and demonstrated physical stability, sustained release property and stability within 12 weeks. Both rhTM NLC and rhTM NLC-gel improved wound healing of diabetic mice and cell migration of human epidermal keratinocyte cell line (HaCaT) significantly. In comparison with rhTM solution, plasma concentrations of rhTM post applications of NLC and NLC-gel formulations were lower and more sustained in 24 h. The developed rhTM NLC and rhTM NLC-gel formulations are easy to prepare, stable and convenient to apply to the wound with reduced systemic exposure, which may warrant potential delivery systems for the care of chronic wound patients. [ABSTRACT FROM AUTHOR]

Allogeneic bone grafts are a promising material for bone implantation due to reduced operative trauma, reduced blood loss, and no donor-site morbidity. Although human decellularized allogeneic bone (hDCB) can be used to fill bone defects, the research of revitalizing hDCB blocks with human mesenchymal stem cells (hMSCs) for osteochondral regeneration is missing. The hMSCs derived from bone marrow, adipose tissue, and Wharton's jelly (BMMSCs, ADMSCs, and UMSCs, respectively) are potential candidates for bone regeneration. This study characterized the potential of hDCB as a scaffold for osteogenesis and chondrogenesis of BMMSCs, ADMSCs, and UMSCs. The pore sizes and mechanical strength of hDCB were characterized. Cell survival and adhesion of hMSCs were investigated using MTT assay and F-actin staining. Alizarin Red S and Safranin O staining were conducted to demonstrate calcium deposition and proteoglycan production of hMSCs after osteogenic and chondrogenic differentiation, respectively. A RT-qPCR was performed to analyze the expression levels of osteogenic and chondrogenic markers in hMSCs. Results indicated that BMMSCs and ADMSCs exhibited higher osteogenic potential than UMSCs. Furthermore, ADMSCs and UMSCs had higher chondrogenic potential than BMMSCs. This study demonstrated that chondrogenic ADMSCs- or UMSCs-seeded hDCB might be potential osteochondral constructs for osteochondral regeneration. [ABSTRACT FROM AUTHOR]

We developed a method based on surface-enhanced Raman spectroscopy (SERS) and a sample pretreatment process for rapid, sensitive, reproducible, multiplexed, and low-cost detection of illegal drugs in urine. The abuse of new psychoactive substances (NPS) has become an increasingly serious problem in many countries. However, immunoassay-based screening kits for NPS are usually not available because of the lack of corresponding antibodies. SERS has a great potential for rapid detection of NPS because it can simultaneously detect multiple kinds of drugs without the use of antibodies. To achieve highly sensitive SERS detection of drugs, sodium bromide was first employed to induce the rapid formation of Ag nanoclusters by aggregating silver nanoparticles (AgNPs) in the extracted sample solution. SERS measurements were performed immediately after the sample pretreatment without incubation. The three-dimensional SERS hot spots were believed to form significantly within the nanoclusters, providing strong SERS enhancement effects. The displacement of citrate molecules on the surfaces of the AgNPs by bromide ions helped increase the adsorption of drug molecules, increasing their areal density. We demonstrated the simultaneous detection of two kinds of NPS, methcathinone and 4-methylmethcathinone, in urine at a concentration as low as 0.01 ppm. [ABSTRACT FROM AUTHOR]