Search Results (4,949)

The rapid detection and confirmation of Suspicious Regions of Forest Fire (SRoFF) are critical for timely alerts and firefighting operations. In the early stages of forest fires, small flames and heavy occlusion lead to low accuracy, false detections, omissions, and slow inference in existing target-detection algorithms. We constructed the Suspicious Regions of Forest Fire Dataset (SRFFD), comprising publicly available datasets, relevant images collected from online searches, and images generated through various image enhancement techniques. The SRFFD contains a total of 64,584 images. In terms of effectiveness, the individual augmentation techniques rank as follows (in descending order): HSV (Hue Saturation and Value) random enhancement, copy-paste augmentation, and affine transformation. A detection model named SRoFF-Yolover is proposed for identifying suspicious regions of forest fire, based on the YOLOv8. An embedding layer that effectively integrates seasonal and temporal information into the image enhances the prediction accuracy of the SRoFF-Yolover. The SRoFF-Yolover enhances YOLOv8 by (1) adopting dilated convolutions in the Backbone to enlarge feature map receptive fields; (2) incorporating the Convolutional Block Attention Module (CBAM) prior to the Neck’s C2fLayer for small-target attention; and (3) reconfiguring the Backbone-Neck linkage via P2, P4, and SPPF. Compared with the baseline model (YOLOv8s), the SRoFF-Yolover achieves an 18.1% improvement in mAP@0.5, a 4.6% increase in Frames Per Second (FPS), a 2.6% reduction in Giga Floating-Point Operations (GFLOPs), and a 3.2% decrease in the total number of model parameters (#Params). The SRoFF-Yolover can effectively detect suspicious regions of forest fire, particularly during winter nights. Experiments demonstrated that the detection accuracy of the SRoFF-Yolover for suspicious regions of forest fire is higher at night than during daytime in the same season. Full article

Background: Advances in screening programs have led to increased detection of early-stage non-small cell lung cancer (NSCLC), including synchronous or metachronous nodules amenable to surgical resection. Patients requiring contralateral anatomical lung resections present a unique surgical challenge due to potential impairments in lung function and the complexities of one-lung ventilation. This study evaluates the feasibility, safety, and perioperative outcomes of robotic-assisted thoracic surgery (RATS) for contralateral anatomical lung resections in patients with NSCLC. Methods: A retrospective analysis was conducted on 20 patients who underwent RATS contralateral anatomical resection between January 2019 and June 2024. Preoperative pulmonary function, perioperative characteristics, and oncological outcomes were assessed. Operative parameters, including conversion rates, intraoperative oxygenation, need for extracorporeal membrane oxygenation (ECMO), and postoperative complications, were recorded. Results: Seventy percent of the patients underwent surgery for metachronous tumors. The median forced expiratory volume in 1 s (FEV1) was 75.94% (66.62–89.24). The most common resection was segmentectomy (65.0%). The median operative time was 148.0 min (108.0–194.75). There were no conversions to open surgery or ECMO requirements. Intraoperative parameters remained stable (median FiO₂: 0.8; lowest SaO₂: 92.0%). Complications occurred in 25% of the patients, mostly Clavien–Dindo grade 2. No in-hospital, 30-day, or 90-day mortality was observed. Conclusions: Robotic-assisted contralateral anatomical lung resection is a feasible and safe approach for patients with previous contralateral surgery, supporting its role as a minimally invasive alternative for complex surgical cases. Full article

Background/Objectives: Colorectal cancer (CRC) frequently metastasizes to the peritoneum, significantly worsening patient prognosis. While serum tumor markers such as carcinoembryonic antigen (CEA) and carbohydrate antigen 19-9 (CA 19-9) are routinely measured, their diagnostic or prognostic role in peritoneal fluid remains unclear. This study aimed to assess the relationship between CEA and CA 19-9 levels in both serum and peritoneal fluid, and the clinical stage of CRC, particularly focusing on the presence of peritoneal metastases and positive cytology. Methods: We retrospectively analyzed data from 89 patients with histologically confirmed CRC who underwent surgery between 2020 and 2023. All patients had preoperative assessment of CEA and CA 19-9 levels in serum and peritoneal fluid, along with cytological examination of peritoneal fluid samples. Patients were categorized based on the presence or absence of macroscopic peritoneal metastases and cytology results. Results: Elevated levels of CEA and CA 19-9 in peritoneal fluid were significantly associated with the presence of peritoneal metastases. A positive cytological finding also correlated with higher marker concentrations. Conclusions: CEA and CA 19-9 levels in peritoneal fluid strongly correlate with peritoneal dissemination in CRC. These markers may serve as additional predictive factors, aiding in early detection of peritoneal spread and improved risk stratification. Their assessment may be useful in guiding intraoperative and postoperative decision-making. Full article

Background/Objectives: Early diagnosis of Parkinson’s Disease (PD) is essential for initiating interventions that may slow its progression and enhance patient quality of life. Gait analysis provides a non-invasive means of capturing subtle motor disturbances, enabling the prediction of both disease presence and severity. This study evaluates and contrasts Bayesian-optimized convolutional neural network (CNN) and long short-term memory (LSTM) models applied directly to Vertical Ground Reaction Force (VGRF) signals for Parkinson’s disease detection and staging. Methods: VGRF recordings were segmented into fixed-length windows of 5, 10, 15, 20, and 25 s. Each segment was normalized and supplied as input to CNN and LSTM network. Hyperparameters for both architectures were optimized via Bayesian optimization using five-fold cross-validation. Results: The Bayesian-optimized LSTM achieved a peak binary classification accuracy of 99.42% with an AUC of 1.000 for PD versus control at the 10-s window, and 98.24% accuracy with an AUC of 0.999 for Hoehn–Yahr (HY) staging at the 5-s window. The CNN model reached up to 98.46% accuracy (AUC = 0.998) for binary classification and 96.62% accuracy (AUC = 0.998) for multi-class severity assessment. Conclusions: Bayesian-optimized CNN and LSTM models trained on VGRF data both achieved high accuracy in Parkinson’s disease detection and staging, with the LSTM exhibiting a slight edge in capturing temporal patterns while the CNN delivered comparable performance with reduced computational demands. These results underscore the promise of end-to-end deep learning for non-invasive, gait-based assessment in Parkinson’s disease. Full article

Background: Non-alcoholic fatty liver disease (NAFLD) is a global public health issue. Although liver biopsy remains the gold standard for diagnosing hepatosteatosis, its invasiveness, high cost, and associated risks limit its widespread use. Therefore, there is a need for reliable, non-invasive, and cost-effective biomarkers to aid in the early detection of NAFLD. Our objective was to determine the utility of the triglyceride (TG)-to-high-density-lipoprotein (HDL) ratio in predicting non-alcoholic fatty liver disease. Methods: This retrospective cross-sectional study included 2588 patients who met the inclusion criteria. Demographic data and laboratory results were collected from electronic health records. Experienced radiologists performed abdominal ultrasonography to assess fatty liver according to the EASL 2021 criteria. The TG/HDL ratio and other non-invasive scores (APRI, FIB-4, ALT/AST, TG/glucose) were calculated. Early-stage disease was defined as grade 1 or grade 2 hepatosteatosis. Results: The TG/HDL ratio was significantly higher in NAFLD patients (AUROC: 0.682) and outperformed the other non-invasive indices. At the optimal cut-off value of 1.86, the sensitivity was 80.7%, and the specificity was 45.5%. The TG/HDL ratio correlated positively with markers of glycemic control, inflammation, and liver enzymes. Conclusions: The TG/HDL ratio is an accessible and valuable parameter for predicting non-alcoholic fatty liver disease. It offers a non-invasive alternative to liver biopsy and potentially prevents complications from non-alcoholic fatty liver disease or diagnostic approaches. Full article

Evaluating the response of maize crops to different nitrogen fertilization rates is essential to ensure their agronomic, environmental, and economic efficiency. In this study, the spectral information of maize plants subjected to five distinct nitrogen fertilization strategies was analyzed. The fertilization strategies were based on the practices commonly used in maize fields in the study area, with the aim of ensuring the research findings’ applicability. The spectral reflectance was measured using a spectroradiometer covering the 350–2500 nm range, and the results enabled the identification of optimal spectral regions for monitoring plants’ nitrogen status, particularly in the visible and infrared ranges. A Principal Component Analysis (PCA) of the reflectance data revealed the key wavelengths most sensitive to the nitrogen availability: 555 nm and 720 nm during the vegetative stage and 680 nm during the reproductive stage. This information will support the development of drone-mounted multispectral sensor systems for large-scale monitoring, as well as the design of low-cost sensors for early nitrogen deficiency detection. Furthermore, the study demonstrated the feasibility of estimating the cornstalk nitrate content based on direct reflectance measurements of maize stems. The prediction model showed satisfactory performance, with a coefficient of determination (R²) of 0.845 and a root mean square error of prediction (RMSECV) of 2035.3 ppm, indicating its strong potential for predicting the NO₃-N concentrations in maize stems. Full article

A predictive health modeling framework was developed for a family of turbofan engines, focusing on early detection of performance degradation. Turbine Gas Temperature (TGT) was employed as the primary indicator of engine health within the model, due to its strong correlation with core engine performance and thermal stress. The present research uses engine health monitoring (EHM) data acquired from in-service turbofan family engines. TGT is typically measured downstream of the high-pressure turbine stage and is regarded as the key thermodynamic variable of the gas turbine cycle. Three new training approaches were proposed using data segmentation based on time between major overhauls and compared with the conventional train–test split method. Detrending was employed to effectively remove trends and seasonality, enabling the ML-based model to learn more intrinsic relationships. Large generalized models based on the entire engine family were also investigated. Prediction performance was evaluated using selected machine learning (ML) models, including both linear and nonlinear algorithms, as well as a long short-term memory (LSTM) approach. The models were compared based on accuracy and other relevant performance metrics. The prediction accuracies of ML models depend on the selection of data size and segmentation for training and testing. For individual engines, the proposed training approaches predicted TGT with the accuracy of 4 ^∘C to 6 ^∘C in root mean square error (RMSE) by utilizing 65% less data than the train (80%)–test (20%) split method. Utilizing the data of each family engine, the large generalized model achieved similar prediction accuracy in RMSE with a smaller interquartile range. However, the amount of data required was 45–300 times larger than the proposed approaches. The sensitivity of prediction accuracy to the size of the training dataset offers valuable insights into the framework’s applicability, even for engines with limited data availability. Uncertainty quantification showed a coverage width criterion (CWC) between 29 ^∘C and 40 ^∘C, varying with different family engines. Full article

Immune checkpoint inhibitors (ICIs) and tyrosine kinase inhibitors (TKIs) have revolutionized cancer therapy, substantially improving survival across a broad range of malignancies. However, these agents are associated with a unique profile of endocrine immune-related adverse events (irAEs), including thyroiditis, hypophysitis, adrenalitis, and pancreatitis, which differ significantly from the toxicities seen with conventional chemotherapy. These complications often arise unpredictably during treatment and may result in irreversible hormone deficiencies requiring lifelong replacement, underscoring the importance of early detection. ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) has emerged as a valuable tool not only for oncologic staging and response assessment but also for detecting metabolic changes in endocrine organs. PET/CT can identify irAEs before the appearance of clinical symptoms or biochemical abnormalities. Emerging evidence suggests that the presence of endocrine irAEs identified by ¹⁸F-FDG PET/CT may correlate with improved treatment response and survival, possibly reflecting enhanced immune activation. This comprehensive review discusses the role of ¹⁸F-FDG PET/CT in the early recognition of therapy-induced endocrine toxicities, facilitating timely intervention through hormone replacement or immunosuppressive therapy while minimizing unnecessary treatment interruptions. Effective integration of metabolic imaging with clinical and laboratory evaluation requires coordinated multidisciplinary collaboration among oncologists, endocrinologists, and nuclear medicine physicians to optimize outcomes and reduce endocrine-related morbidity in the era of precision oncology. Full article

Limited labeled imagery and tight response windows hinder the accurate damage quantification for post-disaster assessment. The objective of this study is to develop and evaluate a deep learning-based Domain-Adaptive Segmentation (DASeg) workflow to detect post-disaster damage using limited information available shortly after an event. DASeg unifies three Vision Foundation Models in an automatic workflow: fine-tuned DINOv2 supplies attention-based point prompts, fine-tuned Grounding DINO yields open-set box prompts, and a frozen Segment Anything Model (SAM) generates the final masks. In the earthquake-focused case study DASeg-Quake, the pipeline boosts mean Intersection over Union (mIoU) by 9.52% over prior work and 2.10% over state-of-the-art supervised baselines. In a zero-shot setting scenario, DASeg-Quake achieves the mIoU of 75.03% for geo-damage analysis, closely matching expert-level annotations. These results show that DASeg achieves superior workflow enhancement in infrastructure damage segmentation without needing pixel-level annotation, providing a practical solution for early-stage disaster response. Full article

Background/Objectives: This study evaluated the applicability of B-mode ultrasound, Doppler, and elastography in the early diagnosis of non-azotemic acute kidney injury (AKI) in rats induced with cyclophosphamide. Methods: The prospective, randomized, and blinded experiment involved groups receiving cyclophosphamide (CG, n = 12) and saline (control, SG, n = 9). Serum biomarkers (urea, creatinine, and symmetric dimethylarginine) were assessed, along with renal histological analysis to classify AKI severity and distribution. Results: B-mode ultrasound revealed a significantly higher corticomedullary ratio at 24 and 72 h and increased renal width at 48 h in the cyclophosphamide group compared to controls. Biochemical analyses showed no significant differences between groups in early stages. Although B-mode ultrasound detected early morphological changes—specifically in corticomedullary ratio and renal size—Doppler and elastography demonstrated limited diagnostic utility in early AKI detection. Conclusions: Overall, B-mode ultrasound provided valuable early indicators of renal injury, whereas Doppler and elastography showed minimal clinical benefit at this stage. Full article

Using meta-analysis of 479 sites across Chinese forests from 136 publications, we quantified changes in soil microbial diversity across forest successional stages and compared patterns between plantation and natural secondary forests. Our systematic review included 136 publications (92 in Chinese, 44 in English), spanning tropical to cold temperate climate zones from 1995–2025. Microbial $\alpha$-diversity exhibited a significant U-shaped pattern across successional stages: early succession (0–15 years) and mature forests (>50 years) had higher Shannon diversity (4.56 ± 0.34 and 4.72 ± 0.41, respectively) than middle-aged forests (16–50 years, 4.18 ± 0.27; standardized mean difference = 0.54, 95% CI: 0.39–0.69, p < 0.01). Response patterns differed significantly among microbial groups (Q = 8.74, p = 0.013), with fungi showing the strongest successional responses (SMD = 0.61, 95% CI: 0.43–0.79), followed by bacteria (SMD = 0.49, 95% CI: 0.32–0.66) and actinomycetes (SMD = 0.42, 95% CI: 0.24–0.60). Natural secondary forests consistently supported higher microbial diversity than plantations (SMD = 0.42, 95% CI: 0.28–0.56), particularly for fungal communities (SMD = 0.47, 95% CI: 0.31–0.63). The climate zone significantly moderated diversity–succession relationships, with subtropical regions showing the largest changes ($\Delta$Shannon = 0.68 ± 0.07) compared to temperate ($\Delta$Shannon = 0.42 ± 0.05) and tropical regions ($\Delta$Shannon = 0.54 ± 0.06). Meta-analytic structural equation modeling revealed that soil organic carbon (path coefficient $\beta$ = 0.68, p < 0.001), total nitrogen ($\beta$ = 0.43, p < 0.001), and pH ($\beta$ = −0.35, p < 0.01) were key mediators connecting succession stage with microbial diversity. Despite substantial between-study heterogeneity (I² = 83.6%), a publication bias was not detected (Egger’s test, p = 0.347). These findings provide the first comprehensive quantification of microbial diversity patterns during forest succession in China, with important implications for forest management and ecological restoration strategies targeting microbial conservation. Full article

Diffuse axonal injury (DAI) is one of the most severe consequences of traumatic brain injury (TBI), characterized by widespread axonal damage in the cerebral white matter. DAI plays a crucial role in determining clinical outcomes, significantly contributing to long-term disability and mortality in severe cases. Despite advancements in neuroscience and clinical management, the diagnosis and prognosis of DAI remain challenging due to its complex pathophysiology and the difficulty of detecting axonal damage in its early stages. This study critically analyzes the clinical and post-mortem methodologies used to assess DAI, highlighting their strengths and limitations. Traditional histopathological grading systems provide valuable insights into disease progression, yet their correlation with long-term functional outcomes remains controversial. Advanced neuroimaging techniques, such as diffusion-weighted MRI, have improved lesion detection, although their routine clinical application is still limited. Additionally, emerging approaches involving biomarkers and artificial intelligence-based models hold promise for enhancing diagnostic accuracy and prognostic predictions. By synthesizing current knowledge on DAI, this work aims to outline a comprehensive framework for improving diagnosis and outcome assessment. Furthermore, it seeks to foster collaboration among clinicians and researchers, ultimately advancing the understanding of DAI and refining strategies to improve patient care. Full article

Background/Objectives: Heart failure (HF) often develops from a prolonged asymptomatic phase where early detection could prevent progression. Pre-heart failure (pre-HF) populations—those with risk factors (Stage A) or subclinical myocardial changes (Stage B)—are critical for intervention. Cardiac magnetic resonance (CMR) with T1 and extracellular volume (ECV) mapping offers a non-invasive approach to detect early myocardial changes in these groups. This systematic review evaluates the role of T1 and ECV mapping in pre-HF populations, focusing on their diagnostic and prognostic utility. Methods: A systematic search of PubMed, EMBASE, and Cochrane was conducted up to April 2025, identifying 17 studies that met inclusion criteria. Data was extracted directly into Excel, and methodological quality was assessed using the Newcastle–Ottawa Scale (NOS) for cohort and cross-sectional studies and AMSTAR-2 for systematic reviews and meta-analyses. A meta-analysis was performed using Review Manager (RevMan) to compare T1 and ECV values between pre-HF and control groups. Results: Studies consistently reported elevated T1 (989.6–1415.41 milliseconds) and ECV (25.7–42.81%) in pre-HF groups compared to controls (T1: 967–1310.63 ms, ECV: 23.5–29.9%). Meta-analysis showed a significant increase in T1 (MD: 27.62 ms, 95% CI: 8.04–47.19, p < 0.006) and ECV (MD: 2.97%, 95% CI: 1.88–4.06, p < 0.00001) in pre-HF groups. RQS scores ranged from 17.2% to 77.8% (mean: 37.9%), and NOS scores ranged from 5 to 8 (mean: 6.2), reflecting variability in study quality. The AMSTAR-2 rating for the systematic review was moderate. Conclusions: T1 and ECV mapping enhance CMR-based detection of early myocardial changes in pre-HF, offering a promising non-invasive approach to predict HF risk. However, variability in study quality, small sample sizes, and methodological inconsistencies limit generalisability. Future research should focus on standardised protocols, prospective designs, and multi-center studies to integrate these techniques into clinical practice, potentially guiding preventive therapies such as SGLT2is and tafamidis. Full article

Paraneoplastic syndromes (PNSs) are pathologic conditions produced by neoplasms not attributable to tumor invasion or metastasis. The clinical manifestations of PNSs can precede the diagnosis; these symptoms may serve as early indicators of underlying malignancy. Standard imaging modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), have limited sensitivity in detecting small or early-stage PNS-associated tumors. FDG PET/CT identifies hypermetabolic lesions suggestive of malignancy and, therefore, facilitates early diagnosis, refined treatment planning, and potentially prolonged patient survival. This review evaluates the diagnostic accuracy, clinical utility, and emerging role of FDG PET/CT in detecting occult malignancies. Syndrome-targeted applications discussed include limbic encephalitis, cerebellar degeneration, Lambert-Eaton myasthenic syndrome, Cushing’s syndrome, hypercalcemia of malignancy, dermatomyositis, and tumor-induced osteomalacia. In addition, the limitations of FDG PET/CT, including false-positive or false-negative findings, are reviewed, while newer PET tracers, like ⁶⁸Ga-DOTATATE, are also highlighted. Ultimately, FDG PET/CT has transformed clinical decision-making, enabling more timely interventions and improved patient management in the context of PNSs. Future directions in imaging, including PET/MRI and ongoing refinements in tracer design, promise to further enhance diagnostic precision, and therapeutic outcomes are also discussed. Full article

Colorectal cancer (CRC) remains one of the leading causes of cancer-related morbidity and mortality worldwide. Despite significant advances in screening and treatment, the prognosis for advanced-stage disease continues to be poor. One thriving area of research focuses on the use of epigenetic alterations for the diagnosis, prediction of treatment response, and prognosis of CRC. In this study, we evaluated original studies and meta-analyses published within the past five years to identify the most clinically relevant epigenetic biomarkers. DNA methylation-based assays, particularly those targeting SDC2 and SEPT9 in stool and plasma, exhibit superior diagnostic accuracy compared to other epigenetic modalities. Circulating microRNAs (miRNAs), including miR-211, miR-197, and miR-21, as well as specific long non-coding RNAs (lncRNAs) such as SNHG14, LINC01485, and ASB16-AS1, also show promising diagnostic potential. Furthermore, panels combining multiple epigenetic markers, especially those incorporating DNA methylation targets, have demonstrated improved sensitivity and specificity for early-stage CRC detection. In the context of therapeutic prediction, microRNAs such as miR-140, miR-21, and miR-4442 have been associated with chemotherapy resistance and recurrence risk. DNA methylation markers like LINE-1, mSEPT9 and ERCC1 have also shown predictive value, while lncRNAs including MALAT1 and GAS6-AS1 remain less validated. Regarding prognosis, miRNAs appear to be the most promising biomarkers, with miR-675-5p and miR-150 being associated with poor survival, while miR-767-5p and miR-215 predict favorable outcomes. Methylation of NKX6.1, IGFBP3, and LMX1A has been identified as an independent negative prognostic factor, while SFRP2 hypermethylation is linked to better prognosis. Selected lncRNAs, including THOR and LINC01094, have also demonstrated significant prognostic value. Despite these advances, challenges persist, including inconsistent reporting, limited external validation, and a lack of replication by independent research groups. Full article