Low-Cost Plant-Protection Unmanned Ground Vehicle System for Variable Weeding Using Machine Vision.

This study presents a machine vision-based variable weeding system for plant- protection unmanned ground vehicles (UGVs) to address the issues of pesticide waste and environmental pollution that are readily caused by traditional spraying agricultural machinery. The system utilizes fuzzy rules to achieve adaptive modification of the Kp, Ki, and Kd adjustment parameters of the PID control algorithm and combines them with an interleaved period PWM controller to reduce the impact of nonlinear variations in water pressure on the performance of the system, and to improve the stability and control accuracy of the system. After testing various image threshold segmentation and image graying algorithms, the normalized super green algorithm (2G-R-B) and the fast iterative threshold segmentation method were adopted as the best combination. This combination effectively distinguished between the vegetation and the background, and thus improved the accuracy of the pixel extraction algorithm for vegetation distribution. The results of orthogonal testing by selected four representative spraying duty cycles-25%, 50%, 75%, and 100%-showed that the pressure variation was less than 0.05 MPa, the average spraying error was less than 2%, and the highest error was less than 5% throughout the test. Finally, the performance of the system was comprehensively evaluated through field trials. The evaluation showed that the system was able to adjust the corresponding spraying volume in real time according to the vegetation distribution under the decision-making based on machine vision algorithms, which proved the low cost and effectiveness of the designed variable weed control system.

Deep Learning with Transformer or Convolutional Neural Network in the Assessment of Tumor-Infiltrating Lymphocytes (TILs) in Breast Cancer Based on US Images: A Dual-Center Retrospective Study.

This study aimed to explore the feasibility of using a deep-learning (DL) approach to predict TIL levels in breast cancer (BC) from ultrasound (US) images. A total of 494 breast cancer patients with pathologically confirmed invasive BC from two hospitals were retrospectively enrolled. Of these, 396 patients from hospital 1 were divided into the training cohort (n = 298) and internal validation (IV) cohort (n = 98). Patients from hospital 2 (n = 98) were in the external validation (EV) cohort. TIL levels were confirmed by pathological results. Five different DL models were trained for predicting TIL levels in BC using US images from the training cohort and validated on the IV and EV cohorts. The overall best-performing DL model, the attention-based DenseNet121, achieved an AUC of 0.873, an accuracy of 79.5%, a sensitivity of 90.7%, a specificity of 65.9%, and an F1 score of 0.830 in the EV cohort. In addition, the stratified analysis showed that the DL models had good discrimination performance of TIL levels in each of the molecular subgroups. The DL models based on US images of BC patients hold promise for non-invasively predicting TIL levels and helping with individualized treatment decision-making.

Development and assessment of novel machine learning models to predict medication non-adherence risks in type 2 diabetics.

Background: Medication adherence is the main determinant of effective management of type 2 diabetes, yet there is no gold standard method available to screen patients with high-risk non-adherence. Developing machine learning models to predict high-risk non-adherence in patients with T2D could optimize management. Methods: This cross-sectional study was carried out on patients with T2D at the Sichuan Provincial People's Hospital from April 2018 to December 2019 who were examined for HbA1c on the day of the survey. Demographic and clinical characteristics were extracted from the questionnaire and electronic medical records. The sample was randomly divided into a training dataset and a test dataset with a radio of 8:2 after data preprocessing. Four imputing methods, five sampling methods, three screening methods, and 18 machine learning algorithms were used to groom data and develop and validate models. Bootstrapping was performed to generate the validation set for external validation and univariate analysis. Models were compared on the basis of predictive performance metrics. Finally, we validated the sample size on the best model. Results: This study included 980 patients with T2D, of whom 184 (18.8%) were defined as medication non-adherence. The results indicated that the model used modified random forest as the imputation method, random under sampler as the sampling method, Boruta as the feature screening method and the ensemble algorithms and had the best performance. The area under the receiver operating characteristic curve (AUC), F1 score, and area under the precision-recall curve (AUPRC) of the best model, among a total of 1,080 trained models, were 0.8369, 0.7912, and 0.9574, respectively. Age, present fasting blood glucose (FBG) values, present HbA1c values, present random blood glucose (RBG) values, and body mass index (BMI) were the most significant contributors associated with risks of medication adherence. Conclusion: We found that machine learning methods could be used to predict the risk of non-adherence in patients with T2D. The proposed model was well performed to identify patients with T2D with non-adherence and could help improve individualized T2D management.