Explore the vast range of titles available.

In recent years, computer vision (CV) has made enormous progress and is providing great possibilities in analyzing images for object detection, especially with the application of machine learning (ML). Unmanned Aerial Vehicle (UAV) based high-resolution images allow to apply CV and ML methods for the detection of plants or their organs of interest. Thus, this study presents a practical workflow based on the You Only Look Once version 5 (YOLOv5) and UAV images to detect maize plants for counting their numbers in contrasting development stages, including the application of a semi-auto-labeling method based on the Segment Anything Model (SAM) to reduce the burden of labeling. Results showed that the trained model achieved a mean average precision (mAP@0.5) of 0.828 and 0.863 for the 3-leaf stage and 7-leaf stage, respectively. YOLOv5 achieved the best performance under the conditions of overgrown weeds, leaf occlusion, and blurry images, suggesting that YOLOv5 plays a practical role in obtaining excellent performance under realistic field conditions. Furthermore, introducing image-rotation augmentation and low noise weight enhanced model accuracy, with an increase of 0.024 and 0.016 mAP@0.5, respectively, compared to the original model of the 3-leaf stage. This work provides a practical reference for applying lightweight ML and deep learning methods to UAV images for automated object detection and characterization of plant growth under realistic environments.

Objective With pancreatic cancer’s dismal prognosis, developing accurate predictive tools is crucial for personalized treatment. This study aims to develop and evaluate a radiomics-3D deep learning fusion model to enhance survival prediction accuracy and explore its potential for clinical risk stratification in pancreatic cancer patients. Methods This study retrospectively analyzed from pancreatic cancer patients treated at two hospitals between 2013 and 2023. Patients were split into training and test cohorts (7:3). Baseline clinical data and portal venous phase contrast-enhanced CT images were collected. Two physicians independently delineated tumor regions of interest (ROIs), and 1,037 radiomic features were extracted. After dimensionality reduction via Principal component analysis (PCA) and feature selection with LASSO regression, a radiomics model was developed using the random survival forest (RSF) algorithm to predict overall survival, accounting for censored data. A separate 3D-DenseNet model was trained using ROI-based image inputs to extract deep features. For fusion models, we adopted a binary classification approach to predict survival status at 1-, 2-, and 3-year time points. Radiomics features, 3D-DenseNet outputs, and clinical variables were integrated using logistic regression, random forest, support vector machine, and decision tree classifiers. Model performance was evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC), and accuracy. The best-performing fusion model was selected for clinical risk stratification. Kaplan-Meier curves and Log-rank tests were used to assess survival differences between risk groups. Result A total of 880 eligible patients were included in this study. In the test cohort, the performance of each model in predicting 1-year, 2-year, and 3-year survival was evaluated. The radiomics model achieved AUC values of 0.78, 0.85, and 0.91, with corresponding accuracies of 0.75, 0.77, and 0.77. The 3D-DenseNet model demonstrated AUC values of 0.81, 0.79, and 0.75, with accuracies of 0.72, 0.76, and 0.77. The fusion model, developed using logistic regression, exhibited superior predictive performance with AUC values of 0.87, 0.92, and 0.94, and accuracies of 0.84, 0.86, and 0.89, outperforming the individual unimodal models. Risk stratification based on the fusion model categorized patients into high-risk and low-risk groups, revealing a statistically significant difference in OS between the two groups ( P  < 0.001). Feature contribution analysis indicated that the 3D-DenseNet model had the greatest influence on the predictions of the fusion model, followed by the radiomics model. Conclusion This study developed a fusion model incorporating radiomics features, deep learning-derived features, and clinical data, which outperformed unimodal models in predicting survival outcomes in pancreatic cancer and demonstrated potential utility in patient risk stratification.

Background The relationship between suicide risk, cognitive impairments, and psychiatric symptoms in schizophrenia patients with insomnia remains controversial. This study aims to investigate the prevalence of suicide risk, clinical characteristics, and cognitive impairments in a large sample of chronic schizophrenia patients with insomnia. Methods We recruited 1,436 chronic schizophrenia patients. Sociodemographic data were collected from all participants. The Positive and Negative Syndrome Scale (PANSS), Insomnia Severity Index (ISI), and Beck Scale for Suicide Ideation (BSI) were used to assess patients’ psychiatric symptoms, insomnia, and severity of suicidal ideation, respectively. The Repeatable Battery for the Assessment of Neuropsychological Status (RBANS) was utilized to evaluate cognitive function in the patients. Results Insomnia prevalence was 9.5%. Patients with insomnia had a significantly higher suicide risk compared to those without (38% vs. 19.8%). In the insomnia group, the severity of suicidal ideation was negatively correlated with language function scores ( r = -0.344, p  = 0.004). Moreover, language function and general psychopathology scores were significant predictors of the severity of suicidal ideation (B = -0.59, p  = 0.008; B = 0.97, p  = 0.010). Language function and general psychopathology scores were also associated with suicide risk (B = -0.05, p  = 0.019; B = 0.11, p  = 0.012). The combined AUCROC value for these two predictors reached 0.758. Conclusion Chronic schizophrenia patients with insomnia have a higher risk of suicide. Additionally, language function and general psychopathology serve as risk factors and predictors of suicide risk in chronic schizophrenia patients with insomnia.

Abstract In 2021, a meta-heuristic algorithm, Reptile Search Algorithm (RSA), was proposed. RSA mainly simulates the cooperative predatory behavior of crocodiles. Although RSA has a fast convergence speed, due to the influence of the crocodile predation mechanism, if the algorithm falls into the local optimum in the early stage, RSA will probably be unable to jump out of the local optimum, resulting in a poor comprehensive performance. Because of the shortcomings of RSA, introducing the local escape operator can effectively improve crocodiles' ability to explore space and generate new crocodiles to replace poor crocodiles. Benefiting from adding a restart strategy, when the optimal solution of RSA is no longer updated, the algorithm’s ability to jump out of the local optimum is effectively improved by randomly initializing the crocodile. Then joining Ghost opposition-based learning to balance the IRSA’s exploitation and exploration, the Improved RSA with Ghost Opposition-based Learning for the Global Optimization Problem (IRSA) is proposed. To verify the performance of IRSA, we used nine famous optimization algorithms to compare with IRSA in 23 standard benchmark functions and CEC2020 test functions. The experiments show that IRSA has good optimization performance and robustness, and can effectively solve six classical engineering problems, thus proving its effectiveness in solving practical problems. Graphical Abstract Graphical Abstract

Employing drones and hyperspectral imagers for large-scale, precise evaluation of nitrogen (N) concentration in Carya cathayensis Sarg canopies is crucial for accurately managing nitrogen fertilization in C. cathayensis Sarg cultivation. This study gathered five sets of hyperspectral imagery data from C. cathayensis Sarg plantations across four distinct locations with varying environmental stresses using drones. The research assessed the canopy nitrogen concentration of C. cathayensis Sarg trees both during singular growth periods and throughout their entire growth cycles. The objective was to explore the influence of band combinations and spectral index formula configurations on the predictive capability of the hyperspectral indices (HIs) for canopy N concentration (CNC), optimize the performance between HIs and machine learning approaches, and validate the efficacy of optimized HI algorithms. The findings revealed the following: (i) Optimized HIs demonstrated optimal predictive performance during both singular growth periods and the full growth cycles of C. cathayensis Sarg. The most effective HI model for singular growth periods was the optimized–modified–normalized difference vegetation index (opt-mNDVI), achieving an adjusted coefficient of determination (R2) of 0.96 and a root mean square error (RMSE) of 0.71. For the entire growth cycle, the HI model, also opt-mNDVI, attained an R2 of 0.75 and an RMSE of 2.11; (ii) optimized band combinations substantially enhanced HIs’ predictive performance by 16% to 71%, while the choice between three-band and two-band combinations influenced the predictive capacity of optimized HIs by 4% to 46%. Hence, utilizing optimized HIs combined with Unmanned Aerial Vehicle (UAV) hyperspectral imaging to evaluate nitrogen concentration in C. cathayensis Sarg trees under complex field conditions offers significant practical value.

Purpose To develop and validate a hybrid radiomics model to predict the overall survival in pancreatic cancer patients and identify risk factors that affect patient prognosis. Methods We conducted a retrospective analysis of 272 pancreatic cancer patients diagnosed at the First Affiliated Hospital of Soochow University from January 2013 to December 2023, and divided them into a training set and a test set at a ratio of 7:3. Pre-treatment contrast-enhanced computed tomography (CT), magnetic resonance imaging (MRI) images, and clinical features were collected. Dimensionality reduction was performed on the radiomics features using principal component analysis (PCA), and important features with non-zero coefficients were selected using the least absolute shrinkage and selection operator (LASSO) with 10-fold cross-validation. In the training set, we built clinical prediction models using both random survival forests (RSF) and traditional Cox regression analysis. These models included a radiomics model based on contrast-enhanced CT, a radiomics model based on MRI, a clinical model, 3 bimodal models combining two types of features, and a multimodal model combining radiomics features with clinical features. Model performance evaluation in the test set was based on two dimensions: discrimination and calibration. In addition, risk stratification was performed in the test set based on predicted risk scores to evaluate the model’s prognostic utility. Results The RSF-based hybrid model performed best with a C-index of 0.807 and a Brier score of 0.101, outperforming the COX hybrid model (C-index of 0.726 and a Brier score of 0.145) and other unimodal and bimodal models. The SurvSHAP(t) plot highlighted CA125 as the most important variable. In the test set, patients were stratified into high- and low-risk groups based on the predicted risk scores, and Kaplan–Meier analysis demonstrated a significant survival difference between the two groups ( p  < 0.0001). Conclusion A multi-modal model using radiomics based on clinical tabular data and contrast-enhanced CT and MRI was developed by RSF, presenting strengths in predicting prognosis in pancreatic cancer patients.

Background Hyperprolactinemia frequently occurs during antipsychotic treatment but is also observed in antipsychotic-naïve schizophrenia patients. The relationship between prolactin (PRL) and treatment resistance remains underexplored in real-world populations. Objective To characterize age-/sex-stratified PRL distribution in first-hospitalized schizophrenia spectrum disorder (SSD) patients and examine associations with treatment resistance proxies (clozapine use/rehospitalization). Methods We analyzed 4,103 first-hospitalized SSD patients using real-world data. PRL levels were stratified by age/sex. Binary logistic regression evaluated PRL-clozapine/rehospitalization associations with confounder adjustment. ROC analysis assessed PRL’s discriminative capacity for clozapine use. Results Elevated PRL prevalence was highest in females aged 18–45 (71.5%). PRL negatively correlated with clozapine use in males ( P  < 0.001), with lower median levels in users vs. non-users (374.40 vs. 529.10 mIU/L, P  < 0.001). This persisted in males aged 18–45 (434.90 vs. 558.60 mIU/L) and ≥ 55 years (308.60 vs. 583.30 mIU/L) (both P  < 0.01). In males ≥ 55, each 1 mIU/L PRL increase reduced clozapine use probability by 0.2% (aOR = 0.998, 95%CI:0.997-1.000). ROC analysis showed moderate discriminative capacity (AUC = 0.72, sensitivity 78.6%, specificity 39.4%). No significant associations occurred in females or for rehospitalization. Conclusion The PRL demonstrates inverse, age-specific associations with clozapine use in male SSD patients, suggesting potential as a stratification biomarker for treatment resistance. Highlights First report on hyperprolactinemia prevalence and predictive role of PRL in a large real-world cohort of first-hospitalized SSD patients (N=4,103). Elevated prolactin levels may serve as a marker associated with clozapine use in males aged ≥55 years with SSD. Moderate discriminative capacity (AUC=0.721) for treatment resistance proxies supports PRL as stratified biomarker.

Background Social isolation and loneliness, objective and subjective features of dysfunctional social relationships, are more prevalent in patients with schizophrenia (SCZ) than in the general population. This study aimed to explore sex differences in loneliness and social isolation among Chinese chronic SCZ patients, and to investigate their relationships with psychiatric symptoms and cognitive functioning. Methods A total of 323 SCZ patients, comprising 136 males and 187 females, were recruited. Psychopathology, cognitive functioning, loneliness, social isolation were assessed using the Positive and Negative Syndrome Scale (PANSS), the Repeated Battery for Assessment of Neuropsychological Status (RBANS), the UCLA (University of California, Los Angeles) Loneliness Scale (Version 3) and the Social Isolation Index (ISI). Multiple linear regression models were conducted to test the independent, relative, and synergistic efects of loneliness and social isolation on psychiatric symptoms and cognitive performance for male and female patients separately. Results Male patients exhibited higher UCLA loneliness scale scores and social isolation scores compared to female patients ( p s < 0.05). In male patients, both loneliness and social isolation significantly predicted PANSS total scores ( p s < 0.01), negative subscale scores ( p s < 0.05) and general psychopathology subscale scores ( p s < 0.05). For female patients, loneliness (not social isolation) significantly predicted immediate memory ( p  < 0.001), language ( p  = 0.013), delayed memory ( p  = 0.017), and RBANS total scores ( p  = 0.002). Further examination of loneliness components in female patients revealed that personal feelings of isolation were negatively associated with language ( r = -0.21, p  = 0.001) and a negative correlation exists between lack of collective connectedness and delayed memory ( r = -0.19, p  = 0.048). Conclusion Loneliness and social isolation are more pronounced in male SCZ patients than in female patients. Both loneliness and social isolation are positively related to psychiatric symptoms in male patients, while loneliness is negatively associated with cognitive functioning in female patients. Highlights Loneliness and social isolation exhibit higher prevalence in male patients with schizophrenia (SCZ) compared to females. Positive relationships are observed between loneliness, social isolation and psychiatric symptoms in male patients. Loneliness demonstrates a negative relationship with cognitive functioning in female patients.

Photoelectric sensor, with its high sensitivity and global instantaneous communication ability, has become an important technical support in intelligent higher education. The background of this research is the rapid development of higher education, the rapid progress of intelligent technology and the popularization and application of 5G computing network. This paper investigates how photoelectric sensors can be used to achieve more efficient teaching and learning methods in intelligent higher education. A 5G computer network model including initial mapping model and migration mapping model is constructed. The initial mapping model compresses and encrypts the data before sending, and converts it into a format suitable for transmission in the network, ensuring the security and transmission efficiency of the data. The migration mapping model performs secondary processing on the data when it arrives at the receiving end and converts it into the format acceptable to the receiving end to ensure that the data can be properly received and processed. The findings suggest that photoelectric sensors can be used for real-time monitoring and feedback during the teaching process to provide more accurate assessment results, thereby improving the quality of teaching, and can also be applied to virtual laboratories and distance education to provide students with a wider range of practical and learning opportunities.