The impact of fine-tuning paradigms on unknown plant diseases recognition.

Plant diseases pose significant threats to agriculture, impacting both food safety and public health. Traditional plant disease detection systems are typically limited to recognizing disease categories included in the training dataset, rendering them ineffective against new disease types. Although out-of-distribution (OOD) detection methods have been proposed to address this issue, the impact of fine-tuning paradigms on these methods has been overlooked. This paper focuses on studying the impact of fine-tuning paradigms on the performance of detecting unknown plant diseases. Currently, fine-tuning on visual tasks is mainly divided into visual-based models and visual-language-based models. We first discuss the limitations of large-scale visual language models in this task: textual prompts are difficult to design. To avoid the side effects of textual prompts, we futher explore the effectiveness of purely visual pre-trained models for OOD detection in plant disease tasks. Specifically, we employed five publicly accessible datasets to establish benchmarks for open-set recognition, OOD detection, and few-shot learning in plant disease recognition. Additionally, we comprehensively compared various OOD detection methods, fine-tuning paradigms, and factors affecting OOD detection performance, such as sample quantity. The results show that visual prompt tuning outperforms fully fine-tuning and linear probe tuning in out-of-distribution detection performance, especially in the few-shot scenarios. Notably, the max-logit-based on visual prompt tuning achieves an AUROC score of 94.8 % in the 8-shot setting, which is nearly comparable to the method of fully fine-tuning on the full dataset (95.2 % ), which implies that an appropriate fine-tuning paradigm can directly improve OOD detection performance. Finally, we visualized the prediction distributions of different OOD detection methods and discussed the selection of thresholds. Overall, this work lays the foundation for unknown plant disease recognition, providing strong support for the security and reliability of plant disease recognition systems. We will release our code at https://github.com/JiuqingDong/PDOOD to further advance this field.

The every woman study™ low- and middle-income countries edition protocol: A multi-country observational study to assess opportunities and challenges to improving survival and quality of life for women with ovarian cancer.

BACKGROUND: Ovarian cancer is a challenging disease to diagnose and treat effectively with five-year survival rates below 50%. Previous patient experience research in high-income countries highlighted common challenges and opportunities to improve survival and quality of life for women affected by ovarian cancer. However, no comparable data exist for low-and middle-income countries, where 70% of women with the disease live. This study aims to address this evidence gap. METHODS: This is an observational multi-country study set in low- and middle-income countries. We aim to recruit over 2000 women diagnosed with ovarian cancer across multiple hospitals in 24 countries in Asia, Africa and South America. Country sample sizes have been calculated (n = 70-96 participants /country), taking account of varying national five-year disease prevalence rates. Women within five years of their diagnosis, who are in contact with participating hospitals, are invited to take part in the study. A questionnaire has been adapted from a tool previously used in high-income countries. It comprises 57 multiple choice and two open-ended questions designed to collect information on demographics, women's knowledge of ovarian cancer, route to diagnosis, access to treatments, surgery and genetic testing, support needs, the impact of the disease on women and their families, and their priorities for action. The questionnaire has been designed in English, translated into local languages and tested according to local ethics requirements. Questionnaires will be administered by a trained member of the clinical team. CONCLUSION: This study will inform further research, advocacy, and action in low- and middle-income countries based on tailored approaches to the national, regional and global challenges and opportunities. In addition, participating countries can choose to repeat the study to track progress and the protocol can be adapted for other countries and other diseases.

Development of a model to predict vancomycin serum concentration during continuous infusion of vancomycin in critically ill pediatric patients.

Vancomycin is a frequently used antibiotic in intensive care units, and the patient's renal clearance affects the pharmacokinetic characteristics of vancomycin. Several advantages have been reported for vancomycin continuous intravenous infusion, but studies on continuous dosing regimens based on patients' renal clearance are insufficient. The aim of this study was to develop a vancomycin serum concentration prediction model by factoring in a patient's renal clearance. Children admitted to our institution between July 1, 2021, and July 31, 2022 with records of continuous infusion of vancomycin were included in the study. Sex, age, height, weight, vancomycin dose by weight, interval from the start of vancomycin administration to the time of therapeutic drug monitoring sampling, and vancomycin serum concentrations were analyzed with the linear regression analysis of the mixed effect model. Univariable regression analysis was performed using the vancomycin serum concentration as a dependent variable. It showed that vancomycin dose (p < 0.001) and serum creatinine (p = 0.007) were factors that had the most impact on vancomycin serum concentration. Vancomycin serum concentration was affected by vancomycin dose (p < 0.001) and serum creatinine (p = 0.001) with statistical significance, and a multivariable regression model was obtained as follows: Vancomycin serum concentration (mg/l) = -1.296 + 0.281 × vancomycin dose (mg/kg) + 20.458 × serum creatinine (mg/dl) (adjusted coefficient of determination, R2 = 0.66). This prediction model is expected to contribute to establishing an optimal continuous infusion regimen for vancomycin.

Age-specific breast and ovarian cancer risks associated with germline BRCA1 or BRCA2 pathogenic variants - an Asian study of 572 families.

Background: Clinical management of Asian BRCA1 and BRCA2 pathogenic variants (PV) carriers remains challenging due to imprecise age-specific breast (BC) and ovarian cancer (OC) risks estimates. We aimed to refine these estimates using six multi-ethnic studies in Asia. Methods: Data were collected on 271 BRCA1 and 301 BRCA2 families from Malaysia and Singapore, ascertained through population/hospital-based case-series (88%) and genetic clinics (12%). Age-specific cancer risks were estimated using a modified segregation analysis method, adjusted for ascertainment. Findings: BC and OC relative risks (RRs) varied across age groups for both BRCA1 and BRCA2. The age-specific RR estimates were similar across ethnicities and country of residence. For BRCA1 carriers of Malay, Indian and Chinese ancestry born between 1950 and 1959 in Malaysia, the cumulative risk (95% CI) of BC by age 80 was 40% (36%-44%), 49% (44%-53%) and 55% (51%-60%), respectively. The corresponding estimates for BRCA2 were 29% (26-32%), 36% (33%-40%) and 42% (38%-45%). The corresponding cumulative BC risks for Singapore residents from the same birth cohort, where the underlying population cancer incidences are higher compared to Malaysia, were higher, varying by ancestry group between 57 and 61% for BRCA1, and between 43 and 47% for BRCA2 carriers. The cumulative risk of OC by age 80 was 31% (27-36%) for BRCA1 and 12% (10%-15%) for BRCA2 carriers in Malaysia born between 1950 and 1959; and 42% (34-50%) for BRCA1 and 20% (14-27%) for BRCA2 carriers of the same birth cohort in Singapore. There was evidence of increased BC and OC risks for women from >1960 birth cohorts (p-value = 3.6 × 10-5 for BRCA1 and 0.018 for BRCA2). Interpretation: The absolute age-specific cancer risks of Asian carriers vary depending on the underlying population-specific cancer incidences, and hence should be customised to allow for more accurate cancer risk management. Funding: Wellcome Trust [grant no: v203477/Z/16/Z]; CRUK (PPRPGM-Nov20∖100002).

Changes in ocular extorsion after horizontal muscle surgery in patients with intermittent exotropia coexisting with hypertropia and mild inferior oblique overaction.

PURPOSE: To investigate changes in vertical strabismus and extorsion in patients with intermittent exotropia and mild unilateral inferior oblique muscle overaction (IOOA) who underwent horizontal muscle surgery without vertical or oblique muscle surgery. METHODS: The medical records of 41 patients were retrospectively analyzed. The patients were followed up for at least 6 months after surgery. Fundus photography was performed before and after surgery, and the sum of the angles of torsion in both eyes was used to measure changes in extorsion using ImageJ software. The enrolled patients were divided into two groups according to the degree of IOOA: patients with grade 1 IOOA were placed in +1 IOOA group and those with grade 2 IOOA in +2 IOOA group. The pre- and postoperative angles of horizontal and vertical strabismus and extorsion were compared between the two groups. RESULTS: The +1 IOOA and +2 IOOA groups included 24 and 17 patients, respectively. The angle of preoperative exotropia did not differ significantly: 25.54 ± 5.68 prism diopters (PD) and 25.65 ± 8.11 PD in the +1 IOOA and +2 IOOA groups, respectively. In the +1 IOOA and +2 IOOA groups, hypertropia was 2.67 ± 1.52 PD and 2.82 ± 1.13 PD, respectively, and extorsion angles were 7.14 ± 2.77° and 7.94 ± 2.87°, respectively. As the IOOA degree increased, the extent of hypertropia and extorsion also increased. However, there were no significant differences between the two groups. Postoperative angles of hypertropia and extorsion significantly decreased in both groups (p < 0.001) after surgery. The degree of change in hypertropia and extorsion was not significantly different between the two groups (p = 0.563 and p = 0.354, respectively). CONCLUSIONS: Hypertropia and extorsion improved significantly after horizontal muscle surgery in patients with mild unilateral IOOA and intermittent exotropia. There was no significant difference in the improvement in hypertropia or extorsion between IOOA grades I and II.

Quality and composition of archived nucleic acids after use in SARS-CoV-2 molecular testing.

BACKGROUND: Reverse transcription real-time PCR (rRT-PCR) has been a gold-standard method to detect SARS-CoV-2, for which quality assessment of nucleic acids (NAs) is not needed. In order to prepare for future use, we evaluated NA quality from archived SARS-CoV-2 rRT-PCR samples. METHODS: NA samples were collected in February 2021 and extracted using the QIAamp DSP Virus Spin Kit, (53 SARS-CoV-2-positive and 100 SARS-CoV-2-negative). Quality, quantity, and purity of NA were measured spectrophotometrically or fluorescently. Droplet digital PCR was used to characterize the double strand DNA (dsDNA) origin and composition by quantifying 16S rDNA and RPP30. RESULTS: The RIN and purity were not significantly different between groups (p = 0.3828). RNA quantity was significantly higher than dsDNA in both groups (p < 0.0001); both dsDNA and RNA quantity were significantly higher in positive samples (dsDNA, RNA p = 0.021). For dsDNA, 16S rDNA copies were significantly greater than RPP30 in both groups (p < 0.0001), and RPP30 were significantly higher in positive samples (p < 0.0001). CONCLUSIONS: Archived NA quality after SARS-CoV-2 rRT-PCR was guaranteed for subsequent molecular research using human or bacterial DNA, especially for short targets.

Consultation-Based Deprescribing Service to Optimize Palliative Care for Terminal Cancer Patients.

(1) Background: A pharmacist-led deprescribing service previously developed within the Consultation-Based Palliative Care Team (CB-PCT) was implemented for terminal cancer patients. (2) Objective: To evaluate the clinical outcomes of the developed deprescribing service for terminal cancer patients in CB-PCT. (3) Methods: A retrospective analysis compared the active care (AC) group to the historical usual care (UC) group. The clinical outcomes included the deprescribing rate of preventive medications, the proportion of patients with one or more medication-related problems (MRPs) resolved upon discharge, and the clinical significance. The implementability of the service was also gauged by the acceptance rates of pharmacists' interventions. (4) Results: Preventive medications included lipid-lowering agents, gastroprotective agents, vitamins, antihypertensives, and antidiabetic agents. The AC group revealed a higher deprescribing rate (10.4% in the UC group vs. 29.6% in the AC group, p < 0.001). At discharge, more AC patients had one or more MRPs deprescribed (39.7% vs. 2.97% in UC, p < 0.001). The clinical significance consistently had a very significant rating (mean score of 2.96 out of 4). Acceptance rates were notably higher in the AC group (30.0% vs. 78.0%. p = 0.003). (5) Conclusions: The collaborative deprescribing service in CB-PCT effectively identified and deprescribed MRPs that are clinically significant and implementable in practice.

Effect of Nefopam on Dysesthesia, Postoperative Pain, and Satisfaction in Patients with Lumbar Spinal Stenosis Undergoing Spine Surgery: A Double-Blind, Randomized Study.

Postoperative residual pain and dysesthesia in patients with lumbar spinal stenosis (LSS) can reduce patient satisfaction. We investigated the effects of nefopam on dysesthesia, postoperative pain, and satisfaction in patients with LSS who underwent spine surgery. A total of 73 patients were randomly assigned to two groups: the nefopam group (n = 35), receiving a 20 mL normal saline-based solution containing nefopam 20 mg, and the control group (n = 38), which received 20 mL of normal saline 1 h before the end of the operation. Postoperative incisional pain, dysesthesia scores, and overall satisfaction with postoperative pain management were evaluated. The severity of dysesthesia within 12 and 24 h in the nefopam group was significantly lower than that in the control group (2.3 ± 1.9 and 1.7 ± 1.6 vs. 3.3 ± 2.1, and 2.6 ± 1.9, respectively; p = 0.029 and p = 0.048). Satisfaction scores for postoperative pain management were significantly higher in the nefopam group (3.7 ± 0.6 vs. 3.1 ± 1.0, respectively; p = 0.006). The administration of nefopam effectively reduced the severity of dysesthesia within 24 h of surgery in geriatric patients undergoing spine surgery and increased patient satisfaction with postoperative pain management.

Investigating preoperative myoglobin level as predictive factor for acute kidney injury following cardiac surgery with cardiopulmonary bypass: a retrospective observational study

Abstract Background: Early identification of patients at risk of AKI after cardiac surgery is of critical importance for optimizing perioperative management and improving outcomes. This study aimed to identify the association between preoperative myoglobin levels and postoperative acute kidney injury (AKI) in patients undergoing valve surgery or coronary artery bypass graft surgery (CABG) with cardiopulmonary bypass. Methods: This retrospective study included 293 patients aged over 17 years who underwent valve surgery or CABG with cardiopulmonary bypass. We excluded 87 patients as they met the exclusion criteria. Therefore, 206 patients were included in the final analysis. The patients' demographics as well as intraoperative and postoperative data were collected from electronic medical records. AKI was defined according to the Acute Kidney Injury Network classification system. Results: Of the 206 patients included in this study, 77 developed AKI. The patients who developed AKI were older, had a history of hypertension, underwent valve surgery with concomitant CABG, had lower preoperative hemoglobin levels, and experienced prolonged extracorporeal circulation (ECC) times. Multivariate logistic regression analysis revealed that preoperative myoglobin levels and ECC time were correlated with the development of AKI. A higher preoperative myoglobin level was an independent risk factor for the development of cardiac surgery-associated AKI. Conclusions: Higher preoperative myoglobin levels may enable physicians to identify patients at risk of developing AKI and optimize management accordingly.

Noninvasive Imaging of Conjunctival Goblet Cells as a Method for Diagnosing Dry Eye Disease in an Experimental Mouse Model.

Purpose: The purpose of this study was to evaluate a noninvasive conjunctival goblet cell (GC) imaging method for assessing dry eye disease (DED) in an experimental mouse model. Methods: Moxifloxacin-based fluorescence microscopy (MBFM) was used to examine GCs noninvasively in 56 mice. Forty-two (42) DED-induced mice were divided into 2 groups and treated topically for 14 days with cyclosporine (CsA) or normal saline (NS). In vivo MBFM imaging and clinical DED evaluations were performed and goblet cell density (GCD) and goblet cell area (GCA) were obtained and compared with histological GCD using periodic acid-Schiff (PAS) staining. Correlation and receiver operating characteristic (ROC) analyses showed MBFM's high diagnostic value. Results: The GCD and GCA of the DED mice obtained from in vivo MBFM imaging were highly correlated with clinical DED parameters and GCD obtained from PAS histology. The therapeutic effect of CsA, as observed by in vivo MBFM, was significant with respect to that of NS treatment. The ROC curves derived from in vivo MBFM showed high diagnostic value in assessing DED. Conclusions: The proposed noninvasive method has high diagnostic value in assessing the severity of DED and the effect of treatment for this disease. Translational Relevance: A noninvasive imaging method using moxifloxacin-based fluorescence microscopy was evaluated for assessing DED in an experimental mouse model. The method showed high diagnostic value in assessing the severity of DED and the effect of treatment, bridging the gap between basic research and clinical treatment. The study provides a promising tool for diagnosing and monitoring DED.

Improving Known-Unknown Cattle's Face Recognition for Smart Livestock Farm Management.

Accurate identification of individual cattle is of paramount importance in precision livestock farming, enabling the monitoring of cattle behavior, disease prevention, and enhanced animal welfare. Unlike human faces, the faces of most Hanwoo cattle, a native breed of Korea, exhibit significant similarities and have the same body color, posing a substantial challenge in accurately distinguishing between individual cattle. In this study, we sought to extend the closed-set scope (only including identifying known individuals) to a more-adaptable open-set recognition scenario (identifying both known and unknown individuals) termed Cattle's Face Open-Set Recognition (CFOSR). By integrating open-set techniques to enhance the closed-set accuracy, the proposed method simultaneously addresses the open-set scenario. In CFOSR, the objective is to develop a trained model capable of accurately identifying known individuals, while effectively handling unknown or novel individuals, even in cases where the model has been trained solely on known individuals. To address this challenge, we propose a novel approach that integrates Adversarial Reciprocal Points Learning (ARPL), a state-of-the-art open-set recognition method, with the effectiveness of Additive Margin Softmax loss (AM-Softmax). ARPL was leveraged to mitigate the overlap between spaces of known and unknown or unregistered cattle. At the same time, AM-Softmax was chosen over the conventional Cross-Entropy loss (CE) to classify known individuals. The empirical results obtained from a real-world dataset demonstrated the effectiveness of the ARPL and AM-Softmax techniques in achieving both intra-class compactness and inter-class separability. Notably, the results of the open-set recognition and closed-set recognition validated the superior performance of our proposed method compared to existing algorithms. To be more precise, our method achieved an AUROC of 91.84 and an OSCR of 87.85 in the context of open-set recognition on a complex dataset. Simultaneously, it demonstrated an accuracy of 94.46 for closed-set recognition. We believe that our study provides a novel vision to improve the classification accuracy of the closed set. Simultaneously, it holds the potential to significantly contribute to herd monitoring and inventory management, especially in scenarios involving the presence of unknown or novel cattle.

An iterative noisy annotation correction model for robust plant disease detection.

Previous work on plant disease detection demonstrated that object detectors generally suffer from degraded training data, and annotations with noise may cause the training task to fail. Well-annotated datasets are therefore crucial to build a robust detector. However, a good label set generally requires much expert knowledge and meticulous work, which is expensive and time-consuming. This paper aims to learn robust feature representations with inaccurate bounding boxes, thereby reducing the model requirements for annotation quality. Specifically, we analyze the distribution of noisy annotations in the real world. A teacher-student learning paradigm is proposed to correct inaccurate bounding boxes. The teacher model is used to rectify the degraded bounding boxes, and the student model extracts more robust feature representations from the corrected bounding boxes. Furthermore, the method can be easily generalized to semi-supervised learning paradigms and auto-labeling techniques. Experimental results show that applying our method to the Faster-RCNN detector achieves a 26% performance improvement on the noisy dataset. Besides, our method achieves approximately 75% of the performance of a fully supervised object detector when 1% of the labels are available. Overall, this work provides a robust solution to real-world location noise. It alleviates the challenges posed by noisy data to precision agriculture, optimizes data labeling technology, and encourages practitioners to further investigate plant disease detection and intelligent agriculture at a lower cost. The code will be released at https://github.com/JiuqingDong/TS_OAMIL-for-Plant-disease-detection.

Relationship between ocular surface temperature and 0.1% cyclosporine a in dry eye syndrome with meibomian gland dysfunction.

To determine the relationship between ocular surface temperature (OST) and 0.1% cyclosporine A in patients with dry eye syndrome and meibomian gland dysfunction (MGD). This study retrospectively analyzed 35 eyes from 18 patients with dry eye disease (DED) and MGD, who were divided into two groups. Group 1 was treated with artificial tears, and eyelid margin scrubs without anti-inflammatory eye drops, while group 2 received the same treatment as group 1 along with 0.1% cyclosporine A. The ocular surface disease index (OSDI), tear meniscus height (TMH), noninvasive tear breakup time (NIBUT), lipid layer thickness (LLT), meibum quality score (MQS), and OST were measured at baseline and 1 month later. Nineteen and 16 eyes were included in groups 1 and 2, respectively. Both groups showed a significant decrease in OSDI and OST; however, the decrease was more significant in group 2. No other significant differences in TMH, NIBUT, and LLT were observed; however, MQS significantly differed in group 2. This study found that 0.1% CsA administration can relieve symptoms in patients with DED and MGD although there were no definite keratitis clues, such as epithelial erosion. In addition, the conjunctival temperature showed a correlation with symptom improvement.

Altered gut microbiome plays an important role in AKI to CKD transition in aged mice.

Introduction: This study investigated the role of renal-intestinal crosstalk in the transition from acute kidney injury (AKI) to chronic kidney disease (CKD) in elderly individuals. Methods: Using young and aged mice, we induced bilateral ischemia-reperfusion injury (IRI) and compared intestinal and kidney inflammation over 28 days. To determine the role of the microbiome in gut-kidney crosstalk, we analyzed the microbiome of fecal samples of the young vs. aged mice and examined the effects of probiotic supplementation. Results: In the post-IRI recovery phase, prolonged intestinal and renal inflammation along with dysbiosis were evident in aged vs. younger mice that was associated with severe renal dysfunction and fibrosis progression in aged mice. Probiotic supplementation with Bifidobacterium bifidum BGN4 and Bifidobacterium longum BORI alleviated intestinal inflammation but not intestinal leakage, characterized by decreased inflammatory cytokine levels and decreased infiltration of macrophages, neutrophils, and Th17 cells. This was associated with improved M1-dominant renal inflammation and ultimately improved renal function and fibrosis, suggesting that renal-intestinal crosstalk in aged mice contributes to the transition from AKI to CKD. Discussion: Our study findings suggest that exacerbation of chronic inflammation through the gut-kidney axis might be an important mechanism in the transition from AKI to CKD in the elderly.

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning.

Recent advancements in deep learning have brought significant improvements to plant disease recognition. However, achieving satisfactory performance often requires high-quality training datasets, which are challenging and expensive to collect. Consequently, the practical application of current deep learning-based methods in real-world scenarios is hindered by the scarcity of high-quality datasets. In this paper, we argue that embracing poor datasets is viable and aims to explicitly define the challenges associated with using these datasets. To delve into this topic, we analyze the characteristics of high-quality datasets, namely, large-scale images and desired annotation, and contrast them with the limited and imperfect nature of poor datasets. Challenges arise when the training datasets deviate from these characteristics. To provide a comprehensive understanding, we propose a novel and informative taxonomy that categorizes these challenges. Furthermore, we offer a brief overview of existing studies and approaches that address these challenges. We point out that our paper sheds light on the importance of embracing poor datasets, enhances the understanding of the associated challenges, and contributes to the ambitious objective of deploying deep learning in real-world applications. To facilitate the progress, we finally describe several outstanding questions and point out potential future directions. Although our primary focus is on plant disease recognition, we emphasize that the principles of embracing and analyzing poor datasets are applicable to a wider range of domains, including agriculture. Our project is public available at https://github.com/xml94/EmbracingLimitedImperfectTrainingDatasets.

A New Deep Learning-based Dynamic Paradigm Towards Open-World Plant Disease Detection.

Plant disease detection has made significant strides thanks to the emergence of deep learning. However, existing methods have been limited to closed-set and static learning settings, where models are trained using a specific dataset. This confinement restricts the model's adaptability when encountering samples from unseen disease categories. Additionally, there is a challenge of knowledge degradation for these static learning settings, as the acquisition of new knowledge tends to overwrite the old when learning new categories. To overcome these limitations, this study introduces a novel paradigm for plant disease detection called open-world setting. Our approach can infer disease categories that have never been seen during the model training phase and gradually learn these unseen diseases through dynamic knowledge updates in the next training phase. Specifically, we utilize a well-trained unknown-aware region proposal network to generate pseudo-labels for unknown diseases during training and employ a class-agnostic classifier to enhance the recall rate for unknown diseases. Besides, we employ a sample replay strategy to maintain recognition ability for previously learned classes. Extensive experimental evaluation and ablation studies investigate the efficacy of our method in detecting old and unknown classes. Remarkably, our method demonstrates robust generalization ability even in cross-species disease detection experiments. Overall, this open-world and dynamically updated detection method shows promising potential to become the future paradigm for plant disease detection. We discuss open issues including classification and localization, and propose promising approaches to address them. We encourage further research in the community to tackle the crucial challenges in open-world plant disease detection. The code will be released at https://github.com/JiuqingDong/OWPDD.

Local refinement mechanism for improved plant leaf segmentation in cluttered backgrounds.

Plant phenotyping is a critical field in agriculture, aiming to understand crop growth under specific conditions. Recent research uses images to describe plant characteristics by detecting visual information within organs such as leaves, flowers, stems, and fruits. However, processing data in real field conditions, with challenges such as image blurring and occlusion, requires improvement. This paper proposes a deep learning-based approach for leaf instance segmentation with a local refinement mechanism to enhance performance in cluttered backgrounds. The refinement mechanism employs Gaussian low-pass and High-boost filters to enhance target instances and can be applied to the training or testing dataset. An instance segmentation architecture generates segmented masks and detected areas, facilitating the derivation of phenotypic information, such as leaf count and size. Experimental results on a tomato leaf dataset demonstrate the system's accuracy in segmenting target leaves despite complex backgrounds. The investigation of the refinement mechanism with different kernel sizes reveals that larger kernel sizes benefit the system's ability to generate more leaf instances when using a High-boost filter, while prediction performance decays with larger Gaussian low-pass filter kernel sizes. This research addresses challenges in real greenhouse scenarios and enables automatic recognition of phenotypic data for smart agriculture. The proposed approach has the potential to enhance agricultural practices, ultimately leading to improved crop yields and productivity.

Mechanisms of Piperacillin/Tazobactam Nephrotoxicity: Piperacillin/Tazobactam-Induced Direct Tubular Damage in Mice.

Piperacillin/tazobactam (PT) is one of the most commonly prescribed antibiotics for critically ill patients in intensive care. PT has been reported to cause direct nephrotoxicity; however, the underlying mechanisms remain unknown. We investigated the mechanisms underlying PT nephrotoxicity using a mouse model. The kidneys and sera were collected 24 h after PT injection. Serum blood urea nitrogen (BUN), creatinine, neutrophil gelatinase-associated lipocalin (NGAL), and renal pathologies, including inflammation, oxidative stress, mitochondrial damage, and apoptosis, were examined. Serum BUN, creatinine, and NGAL levels significantly increased in PT-treated mice. We observed increased IGFBP7, KIM-1, and NGAL expression in kidney tubules. Markers of oxidative stress, including 8-OHdG and superoxide dismutase, also showed a significant increase, accompanied by mitochondrial damage and apoptosis. The decrease in the acyl-coA oxidase 2 and Bcl2/Bax ratio also supports that PT induces mitochondrial injury. An in vitro study using HK-2 cells also demonstrated mitochondrial membrane potential loss, indicating that PT induces mitochondrial damage. PT appears to exert direct nephrotoxicity, which is associated with oxidative stress and mitochondrial damage in the kidney tubular cells. Given that PT alone or in combination with vancomycin is the most commonly prescribed antibiotic in patients at high risk of acute kidney injury, caution should be exercised.

Multiview Monitoring of Individual Cattle Behavior Based on Action Recognition in Closed Barns Using Deep Learning.

Cattle behavior recognition is essential for monitoring their health and welfare. Existing techniques for behavior recognition in closed barns typically rely on direct observation to detect changes using wearable devices or surveillance cameras. While promising progress has been made in this field, monitoring individual cattle, especially those with similar visual characteristics, remains challenging due to numerous factors such as occlusion, scale variations, and pose changes. Accurate and consistent individual identification over time is therefore essential to overcome these challenges. To address this issue, this paper introduces an approach for multiview monitoring of individual cattle behavior based on action recognition using video data. The proposed system takes an image sequence as input and utilizes a detector to identify hierarchical actions categorized as part and individual actions. These regions of interest are then inputted into a tracking and identification mechanism, enabling the system to continuously track each individual in the scene and assign them a unique identification number. By implementing this approach, cattle behavior is continuously monitored, and statistical analysis is conducted to assess changes in behavior in the time domain. The effectiveness of the proposed framework is demonstrated through quantitative and qualitative experimental results obtained from our Hanwoo cattle video database. Overall, this study tackles the challenges encountered in real farm indoor scenarios, capturing spatiotemporal information and enabling automatic recognition of cattle behavior for precision livestock farming.