Search Results (141)

This review comprehensively examines the application of deep learning technologies across the entire soybean production chain, encompassing areas such as disease and pest identification, weed detection, crop phenotype recognition, yield prediction, and intelligent operations. By systematically analyzing mainstream deep learning models, optimization strategies (e.g., model lightweighting, transfer learning), and sensor data fusion techniques, the review identifies their roles and performances in complex agricultural environments. It also highlights key challenges including data quality limitations, difficulties in real-world deployment, and the lack of standardized evaluation benchmarks. In response, promising directions such as reinforcement learning, self-supervised learning, interpretable AI, and multi-source data fusion are proposed. Specifically for soybean automation, future advancements are expected in areas such as high-precision disease and weed localization, real-time decision-making for variable-rate spraying and harvesting, and the integration of deep learning with robotics and edge computing to enable autonomous field operations. This review provides valuable insights and future prospects for promoting intelligent, efficient, and sustainable development in soybean production through deep learning. Full article

This paper presents a Self-Learning Robotic System (SLRS) for healthcare assistance using Deep Imitation Learning (DIL). The proposed SLRS solution can observe and replicate human demonstrations, thereby acquiring complex skills without the need for explicit task-specific programming. It incorporates modular components for perception (i.e., advanced computer vision methodologies), actuation (i.e., dynamic interaction with patients and healthcare professionals in real time), and learning. The innovative approach of implementing a hybrid model approach (i.e., deep imitation learning and pose estimation algorithms) facilitates autonomous learning and adaptive task execution. The environmental awareness and responsiveness were also enhanced using both a Convolutional Neural Network (CNN)-based object detection mechanism using YOLOv8 (i.e., with 94.3% accuracy and 18.7 ms latency) and pose estimation algorithms, alongside a MediaPipe and Long Short-Term Memory (LSTM) framework for human action recognition. The developed solution was tested and validated in healthcare, with the aim to overcome some of the current challenges, such as workforce shortages, ageing populations, and the rising prevalence of chronic diseases. The CAD simulation, validation, and verification tested functions (i.e., assistive functions, interactive scenarios, and object manipulation) of the system demonstrated the robot’s adaptability and operational efficiency, achieving an 87.3% task completion success rate and over 85% grasp success rate. This approach highlights the potential use of an SLRS for healthcare assistance. Further work will be undertaken in hospitals, care homes, and rehabilitation centre environments to generate complete holistic datasets to confirm the system’s reliability and efficiency. Full article

As the prevalence of related diseases continues to rise, a corresponding increase in the demand for internal limiting membrane (ILM) peeling surgery has been observed. However, significant challenges are encountered in ILM peeling surgery, including limited force feedback, inadequate depth perception, and surgeon hand tremors. Research on fully autonomous ILM peeling surgical robots has been conducted to address the imbalance between medical resource availability and patient demand while enhancing surgical safety. An automatic control framework for break initiation in ILM peeling is proposed in this study, which integrates model-predictive control with fractional-order admittance control. Additionally, a multi-vision task surgical scene perception method is introduced based on target detection, key point recognition, and sparse binocular matching. A surgical trajectory planning strategy for break initiation in ILM peeling aligned with operative specifications is proposed. Finally, validation experiments for automatic break initiation in ILM peeling were performed using eye phantoms. The results indicated that the positional error of the micro-forceps tip remained within 40 μm. At the same time, the contact force overshoot was limited to under 6%, thereby ensuring both the effectiveness and safety of break initiation during ILM peeling. Full article

Background: Serum uric acid and serum creatinine ratio (SUA/sCr) is strongly linked to increased cardiovascular risk. Atherosclerotic renal artery stenosis (ARAS) is a secondary cause of hypertension and is associated with ischemic nephropathy, congestive heart failure, accelerated cardiovascular disease, and autonomic dysfunction. The aim of this study was to investigate whether SUA levels and SUA/sCr could represent markers of autonomic dysfunction and increased left ventricular mass index (LVMI) in patients with ARAS. Methods: Patients diagnosed with ARAS were enrolled in the study. All patients underwent clinical evaluation, biochemical analysis, 24 h electrocardiogram (ECG), and Renal Doppler Ultrasound with renal resistive index parameters. Heart rate variability for global autonomic dysfunction was assessed through the analysis of a 24 h ECG to detect the standard deviation of normal-to-normal RR intervals (SDNN). Echocardiographic measurement of LVMI was performed. Results: A total of 27 patients (F = 16 (59%), median age 67 years (IQR 60–77)) diagnosed with ARAS were enrolled in the study. We found a statistically significant negative linear correlation between SUA/sCr and SDNN (r = −0.519, p < 0.01). We found a statistically significant positive linear correlation between SUA/sCr and LVMI (r = 0.413, p < 0.05). Median SDNN was significantly lower in patients with SUA ≥ 5.6 mg/dL than in patients with SUA < 5.6 mg/dL (94.2 (IQR 86.8–108.1) vs. 112.8 (IQR 108.9–114.7), p < 0.01). Median LVMI was significantly higher in patients with SUA ≥ 5.6 mg/dL compared to patients with SUA < 5.6 mg/dL (133 g/m² (IQR 120–149) vs. 111 g/m² (IQR 99–129), p < 0.05). Conclusion: In patients with ARAS, SUA/sCr is associated with autonomic dysfunction and LVMI in ARAS patients. The ratio and related cut-off value of SUA/sCr could represent a useful biomarker to evaluate cardiovascular risk in ARAS patients. Full article

Background: Adrenal incidentalomas are detected in various medical and surgical healthcare departments, including primary healthcare. One up to three out of ten individuals confirmed with nonfunctioning adrenal incidentalomas (NFAs) actually present a mild autonomous cortisol secretion (MACS), which is distinct from Cushing’s syndrome. Objective: We aimed to assess the cortisol secretion in newly detected adrenal incidentalomas in patients who were referred by their primary healthcare physician upon accidental detection of an adrenal tumor at abdominal computed tomography (CT) scan that was performed for unrelated (non-endocrine) purposes. Methods: This retrospective study included adults diagnosed with an adrenal incidentaloma via CT during the previous 3 months. Inclusion criteria: age ≥ 40 years (y). A triple stratification of exclusion criteria involved: (1) Clinical aspects and medical records such as active malignancies or malignancies under surveillance protocols, subjects under exogenous glucocorticoid exposure (current or during the previous year), or suggestive endocrine phenotypes for any hormonal ailment; (2) Radiological appearance of suspected/confirmed (primary or secondary) adrenal malignancy, adrenal cysts, or myelolipomas; (3) Endocrine assays consistent with active endocrine tumors. Protocol of assessment included baseline ACTH, morning plasma cortisol (C-B), cortisol at 6 p.m. (C-6 pm), and after 1 mg dexamethasone suppression testing (C-1 mg-DST), 24-h urinary free cortisol (UFC), and a second opinion for all CT scans. MACS were defined based on C-1 mg-DST ≥ 1.8 and <5 µg/dL (non-MACS: C-1 mg-DST < 1.8 µg/dL). Results: The cohort (N = 60, 78.33% female; 60.72 ± 10.62 y) associated high blood pressure (HBP) in 66.67%, respectively, type 2 diabetes (T2D) in 28.37% of the patients. Females were statistically significantly older than males (62.40 ± 10.47 vs. 54.62 ± 9.11 y, p = 0.018), while subjects with unilateral vs. bilateral tumors (affecting 26.67% of the individuals) and those with MACS-positive vs. MACS-negative profile had a similar age. Body mass index (BMI) was similar between patients with unilateral vs. bilateral incidentalomas, regardless of MACS. Patients were divided into five age groups (decades); most of them were found between 60 and 69 years (40%). Left-gland involvement was found in 43.33% of all cases. The mean largest tumor diameter was 26.08 ± 8.78 mm. The highest rate of bilateral tumors was 46.67% in the 50–59 y decade. The rate of unilateral/bilateral and tumor diameters was similar in females vs. males. The MACS-positive rate was similar in females vs. males (23.40% vs. 23.08%). A statistically significant negative correlation (N = 60) was found between BMI and C-B (r = −0.193, p = 0.03) and BMI and UFC (r = −0.185, p = 0.038), and a positive correlation was found between C-B and C-6 pm (r = 0.32, p < 0.001), C-B and UFC (r = 0.226, p = 0.011), and C-6 pm and C-1 mg-DST (r = 0.229, p = 0.010), and the largest tumor diameter and C-1 mg-DST (r = 0.241, p = 0.007). Conclusions: Adrenal incidentalomas belong to a complex scenario of detection in the modern medical era, requiring a multidisciplinary collaboration since the patients might be initially detected in different departments (as seen in the current study) and then referred to primary healthcare for further decision. In these consecutive patients, we found a higher female prevalence, a MACS rate of 23.33%, regardless of uni/bilateral involvement or gender distribution, and a relatively high rate (than expected from general data) of bilateral involvement of 26.67%. The MACS-positive profile adds to the disease burden and might require additional assessments during follow-up and a protocol of surveillance, including a tailored decision of tumor removal. The identification of an adrenal incidentaloma at CT and its hormonal characterization needs to be integrated into the panel of various chronic disorders of one patient. The collaboration between endocrinologists and primary healthcare physicians might improve the overall long-term outcomes. Full article

Background/Objectives: This systematic review aimed to synthesize current evidence on the use of impulse oscillometry (IOS) in assessing pulmonary function in patients with Parkinson’s disease (PD). IOS, as an effort-independent method, may offer advantages over conventional spirometry in detecting early or subclinical respiratory impairment in neurologically compromised populations. Methods: A systematic search was conducted across PubMed, Web of Science, Scopus, ScienceDirect and Google Scholar for observational studies published up to March 2025. The included studies involved patients diagnosed with PD who underwent respiratory assessment using IOS, either alone or in combination with spirometry. Data on IOS parameters (R5, R20, X5, AX) and their associations with disease severity, spirometric values or autonomic markers were extracted and analyzed qualitatively. Results: Four studies, published between 2020 and 2023, met the inclusion criteria. IOS revealed increased airway resistance in early-stage PD and inverse correlations with spirometric indices such as FEV1 and PEF. One study demonstrated significant correlations between IOS parameters and parasympathetic heart rate variable indices, suggesting autonomic involvement. IOS also showed stability across dopaminergic treatment states, highlighting its reliability in longitudinal monitoring. Conclusions: IOS appears to be a promising adjunct to traditional respiratory assessment in PD, capable of identifying subtle mechanical and autonomic dysfunctions. Despite encouraging results, the current evidence remains limited and further large-scale, longitudinal studies are needed to validate its clinical utility. Full article

Background/Objectives: Increasing evidence reveals the likely peripheral etiology of Parkinson’s disease; however, the mechanistic insight into α-Synuclein aggregation in the periphery remains unclear. This study aimed to explore the effect of abnormal expression of renalase on dopamine metabolism, toxic DOPAL generation, and subsequently, α-Synuclein aggregation. Methods: Blood pressure (BP) was monitored while changing the body position of rats; the serum level of renalase was detected by ELISA; the mRNA/protein of renalase and α-Synuclein were determined by qRT-PCR/Western blot; DOPAL was measured using HPLC; renalase distribution was explored by immunostaining; cell viability and ultrastructure were examined by TUNEL and electron microscopy, respectively. Results: The results showed that, in PD model rats, the serum level of renalase was increased time-dependently with up-regulated renalase gene/protein expression in the nodose ganglia, nucleus tractus solitarius, and heart; a reduced dopamine content was also detected by the renalase overexpression in PC12 cells. Strikingly, up-regulated renalase and orthostatic BP changes were observed before the behavioral changes in the model rats. Meanwhile, the levels of DOPAL and α-Synuclein were increased time-dependently. Intriguingly, the low molecular weight of α-Synuclein declined coordinately with the increase in the higher molecular weight of α-Synuclein. Clear ultrastructure damage at the cellular level supported the notion of molecular findings. Notably, the α-Synuclein aggregation-induced impairment of the axonal transport function predates neuronal degeneration mediated by renalase overexpression. Conclusions: Our results demonstrate that abnormal peripheral dopamine metabolism mediated by overexpressed renalase promotes the DOPAL-induced α-Synuclein and leads to baroreflex afferent neuronal degeneration and early autonomic failure. Full article

Cotton is a vital economic crop in global agriculture and the textile industry, contributing significantly to food security, industrial competitiveness, and sustainable development. Traditional technologies such as spectral imaging and machine learning improved cotton cultivation and processing, yet their performance often falls short in complex agricultural environments. Deep learning (DL), with its superior capabilities in data analysis, pattern recognition, and autonomous decision-making, offers transformative potential across the cotton value chain. This review highlights DL applications in seed quality assessment, pest and disease detection, intelligent irrigation, autonomous harvesting, and fiber classification et al. DL enhances accuracy, efficiency, and adaptability, promoting the modernization of cotton production and precision agriculture. However, challenges remain, including limited model generalization, high computational demands, environmental adaptability issues, and costly data annotation. Future research should prioritize lightweight, robust models, standardized multi-source datasets, and real-time performance optimization. Integrating multi-modal data—such as remote sensing, weather, and soil information—can further boost decision-making. Addressing these challenges will enable DL to play a central role in driving intelligent, automated, and sustainable transformation in the cotton industry. Full article

Background: Chronic obstructive pulmonary disease (COPD) and lung cancer are the leading causes of death globally, which share common risk factors such as age and smoking exposure. In high-income countries, low-dose computed tomography (LDCT) lung cancer screening programs have decreased lung cancer mortality and facilitated the detection of emphysema, a key radiological indicator of COPD. This study aimed to assess the prevalence of emphysema during a pilot LDCT screening program for lung cancer in a middle-income country with a high smoking prevalence. Methods: A secondary analysis of the Lung Cancer Screening Database of the Autonomous Province of Vojvodina, Serbia, from 20 September 2020 to 30 May 2022. Persons aged 50–74 years, with a smoking history of ≥30 pack-years/or ≥20 pack-years with additional risks (chronic lung disease, prior pneumonia, malignancy other than lung cancer, family history of lung cancer, and professional exposure to carcinogens) were offered LDCT. Results: Of 1288 participants, mean age of 62.1 ± 6.7 years and 535 males (41.5%), 386 (30.0%) had emphysema. The majority of patients with emphysema (301/386, 78.0%) had no prior history of chronic lung diseases. Compared to the patients without emphysema, the patients with emphysema reported more shortness of breath (140/386, 36.3% vs. 276/902, 30.6%, p = 0.046), chronic cough (117/386, 30.3% vs. 209/902, 23.17% p = 0.007), purulent sputum expectoration (70/386, 18.1% vs. 95/902, 10.53%, p < 0.001), and weight loss (45/386, 11.7% vs. 63/902, 7.0%, p = 0.005). The patients with emphysema had more exposure to smoking (pack/years, 43.8 ± 18.8 vs. 39.3 ± 18.1, p < 0.001) and higher prevalence of solid or semisolid lung nodules (141/386, 36.5% vs. 278/902 30.8%, p = 0.04). Conclusions: Almost one-third of the patients who underwent the LDCT screening program in a middle-income country had emphysema that was commonly undiagnosed despite being associated with a significant symptom burden. Spirometry screening should be considered in high-risk populations. Full article

The integration of machine learning (ML) into self-governing spraying systems is one of the major developments in digital precision agriculture that is significantly improving resource efficiency, sustainability, and production. This study looks at current advances in machine learning applications for automated spraying in agricultural mechanisation, emphasising the new innovations, difficulties, and prospects. This study provides an in-depth analysis of the three main categories of autonomous sprayers—drones, ground-based robots, and tractor-mounted systems—that incorporate machine learning techniques. A comprehensive review of research published between 2014 and 2024 was conducted using Web of Science and Scopus, selecting relevant studies on agricultural robotics, sensor integration, and ML-based spraying automation. The results indicate that supervised, unsupervised, and deep learning models increasingly contribute to improved real-time decision making, performance in pest and disease detection, as well as accurate application of agricultural plant protection. By utilising cutting-edge technology like multispectral sensors, LiDAR, and sophisticated neural networks, these systems significantly increase spraying operations’ efficiency while cutting waste and significantly minimising their negative effects on the environment. Notwithstanding significant advances, issues still exist, such as the requirement for high-quality datasets, system calibration, and flexibility in a range of field circumstances. This study highlights important gaps in the literature and suggests future areas of inquiry to develop ML-driven autonomous spraying even more, assisting in the shift to more intelligent and environmentally friendly farming methods. Full article

Chronic kidney disease (CKD) is a progressive pathology characterized by gradual function loss. It is accompanied by complications including cardiovascular disorders. This study involves 4-h electrocardiographic records from the Telemetric and Holter ECG Warehouse (THEW) project database to analyze the dynamics in heart rate variability (HRV) indices of 51 patients with CKD. It proposes three algorithms to process long-term electrocardiography records: QRS complex and R-wave detection, premature ventricular contraction (PVC) identification, and tachograms. PVCs were analyzed with the consideration of the changes occurring before, during, and after hemodialysis, especially during the interdialytic period. The hour with the highest PVCs occurrence was identified and used to assess HRV fluctuations and segmented into 5 min blocks with a 0.77 min overlap, yielding a dynamic HRV vector, one for each of seven HRV indices selected to evaluate autonomic nervous system balance. R-wave and PVC identification resulted in 97.53% and 85.83% positive predictive values, respectively. PVCs’ prevalence and HRV changes’ relationship in 48 h records could relate to cardiovascular risk. The stratification of hemodialysis patients into three distinct PVC patterns (p < 0.001) identified two clinically significant high-risk subgroups: Class 1, indicative of electrical instability, and Class 3, of advanced autonomic dysfunction, demonstrating divergent arrhythmogenic mechanisms with direct implications for risk stratification. Full article

Background/Objectives: The pathological changes preceding the onset of Parkinson’s disease (PD) commence several decades before motor symptoms manifest, offering a potential window for identifying objective biomarkers for early diagnosis and disease monitoring. Among the primary non-motor features of PD is autonomic dysfunction; however, its precise assessment remains challenging, limiting its viability as a reliable biomarker. Both the pupillary light reflex (PLR) and pupillary unrest are regulated by autonomic pathways suggesting their potential as objective non-invasive indicators of the PD prodromal phase. This review systematically evaluates studies that compare PLR and pupillary unrest in individuals with PD and healthy controls to determine their utility as potential biomarkers of the disease. Methods: A systematic search strategy was designed to identify studies reporting PLR and pupillary unrest findings in PD patients. Searches were conducted across three databases (MEDLINE, Embase PsycINFO), supplemented by cross-referencing relevant studies found on Google Scholar. The literature search was last updated on 7 December 2020. Pupillometric parameters that permitted statistical synthesis included maximum constriction velocity (VMax), constriction amplitude (CAmp), and constriction latency (CL). Pooled incidence and effect sizes were determined using a random-effects model with an inverse variance DerSimonian–Laird estimator. The I² statistic was used to assess study heterogeneity. When meta-analysis was not feasible, a qualitative analysis was undertaken. Results: The initial search yielded 219 references. Following deduplication and exclusion of ineligible studies, 31 papers were selected for review. Pupillometric data from 11 studies were incorporated into the meta-analysis. Effect sizes for PD patients were significant for VMax −0.92, (p < 0.01), CAmp −0.58, (p < 0.05), and CL 0.46, (p < 0.05). Measures of pupillary unrest were elevated in PD patients compared to controls, but evidence was limited to two studies. Conclusions: Pupillary constriction in response to light is characterised by reduced speed and amplitude in PD, with effect sizes suggesting potential clinical applicability. However, evidence regarding baseline pupillary variability remains insufficient, underlining the necessity for further research. Pupillary metrics represent a promising avenue for early PD detection, though their clinical utility is constrained by methodological heterogeneity and variations in disease duration among studies. Full article

Fire blight, a devastating bacterial disease affecting Rosaceae plants, particularly pear and apple, has recently emerged in China’s Xinjiang Uyghur Autonomous Region, causing significant damage to the local Pyrus sinkiangensis industry. Phylogenetic analysis of identified Erwinia amylovora strains revealed that all eight Xinjiang isolates belonged to the A-genotype in CRR1 genotyping tests, aligning with findings from 53 strains isolated in Kazakhstan and Kyrgyzstan between 2011 and 2019. A quantitative PCR detection system based on the trp gene sequence was developed and optimized. The system performed optimally with primer concentrations of 200 nmol/L and an annealing temperature of 60 °C. The detection limits were established at 10² CFU/mL for bacterial suspensions and 0.05 pg/µL for bacterial DNA, demonstrating 100-fold greater sensitivity than conventional PCR. The system successfully detected E. amylovora in all 31 tested samples (25 symptomatic and six asymptomatic plant tissues), confirming the reliability of the detection method for pear fire blight. Full article

As an evolutionarily conserved and ubiquitous mechanism of host defense, non-immune cells in vertebrates possess the intrinsic ability to autonomously detect and combat intracellular pathogens. This process, termed cell-autonomous immunity, is distinct from classical innate immunity. In this review, we comprehensively examine the defense mechanisms employed by non-immune cells in response to intracellular pathogen invasion. We provide a detailed analysis of the cytosolic sensors that recognize aberrant nucleic acids, lipopolysaccharide (LPS), and other pathogen-associated molecular patterns (PAMPs). Specifically, we elucidate the molecular mechanisms underlying key signaling pathways, including the cyclic GMP-AMP synthase (cGAS)-stimulator of interferon genes (STING) pathway, the retinoic acid-inducible gene I (RIG-I)-like receptors (RLRs)-mitochondrial antiviral signaling (MAVS) axis, and the guanylate-binding proteins (GBPs)-mediated pathway. Furthermore, we critically evaluate the involvement of these pathways in the pathogenesis of various diseases, including autoimmune disorders, inflammatory conditions, and malignancies, while highlighting their potential as therapeutic targets. Full article

Background: Heart rate variability (HRV) provides both linear and nonlinear autonomic proxies that can be informative of health status in fibromyalgia (FM), where sympatho-vagal abnormalities are common. This retrospective observational study aims to: 1. detect differences in correlation dimension (D2) between FM patients and healthy controls (HCs); 2. correlate D2 with standard HRV parameters; 3. correlate the degree of HRV changes using a global composite parameter called HRV grade, derived from three linear indices (SDNN = intervals between normal sinus beats; RMSSD = mean square of successive differences; total power), with FM clinical outcomes; 4. correlate all linear and nonlinear HRV parameters with clinical variables in patients. Methods: N = 85 patients were considered for the analysis and compared to 35 healthy subjects. According to standard diagnostic protocol, they underwent a systematic HRV protocol with a 5-min paced breathing task. Disease duration, pain intensity, mood, sleep, fatigue, and quality of life were assessed. Non-parametric tests for independent samples and pairwise correlations were performed using JMP (all p < 0.001). Results: Mann-Whitney U found a significant difference in D2 values between FM patients and HCs (p < 0.001). In patients, D2 was associated with all HRV standard indices (all p < 0.001) and FM impairment (FIQ = −0.4567; p < 0.001). HRV grade was also associated with FM impairment (FIQ = 0.5058; p < 0.001). Conclusion: Combining different HRV measurements may help understand the correlates of autonomic dysregulation in FM. Specifically, clinical protocols could benefit from the inclusion and validation of D2 and HRV parameters to target FM severity and related dysautonomia. Full article