Comput Methods Programs Biomed. 2025 May 8;268:108802. doi: 10.1016/j.cmpb.2025.108802. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Pneumonia is the leading cause of hospitalisation and mortality among children under five, particularly in low-resource settings. Accurate differentiation between viral and bacterial pneumonia is essential for guiding appropriate treatment, yet it remains challenging due to overlapping clinical and radiographic features. Advances in machine learning (ML), particularly deep learning (DL), have shown promise in classifying pneumonia using chest X-ray (CXR) images. This scoping review summarises the evidence on ML techniques for classifying viral and bacterial pneumonia using CXR images in paediatric patients.

METHODS: This scoping review was conducted following the Joanna Briggs Institute methodology and the PRISMA-ScR guidelines. A comprehensive search was performed in PubMed, Embase, and Scopus to identify studies involving children (0-18 years) with pneumonia diagnosed through CXR, using ML models for binary or multiclass classification. Data extraction included ML models, dataset characteristics, and performance metrics.

RESULTS: A total of 35 studies, published between 2018 and 2025, were included in this review. Of these, 31 studies used the publicly available Kermany dataset, raising concerns about overfitting and limited generalisability to broader, real-world clinical populations. Most studies (n=33) used convolutional neural networks (CNNs) for pneumonia classification. While many models demonstrated promising performance, significant variability was observed due to differences in methodologies, dataset sizes, and validation strategies, complicating direct comparisons. For binary classification (viral vs bacterial pneumonia), a median accuracy of 92.3% (range: 80.8% to 97.9%) was reported. For multiclass classification (healthy, viral pneumonia, and bacterial pneumonia), the median accuracy was 91.8% (range: 76.8% to 99.7%).

CONCLUSIONS: Current evidence is constrained by a predominant reliance on a single dataset and variability in methodologies, which limit the generalisability and clinical applicability of findings. To address these limitations, future research should focus on developing diverse and representative datasets while adhering to standardised reporting guidelines. Such efforts are essential to improve the reliability, reproducibility, and translational potential of machine learning models in clinical settings.

PMID:40349546 | DOI:10.1016/j.cmpb.2025.108802

Food Chem. 2025 May 7;486:144649. doi: 10.1016/j.foodchem.2025.144649. Online ahead of print.

ABSTRACT

Ultrasound-assisted novel solvent extraction enhances plant bioactive compound yield via cavitation, mechanical, and thermal mechanisms. However, the high designability of novel solvents, the multiple influence factors for extracting results, the complexity of extraction mechanisms, and the safety of extraction equipment still pose many challenges for ultrasound-assisted extraction (UAE). This review highlights advancements in utilizing machine learning and deep learning models to provide actionable solutions for UAE challenges, which include accelerating novel solvent screening, promoting the discovery of active ingredients, optimizing complex extraction processes, in-depth analysis of extraction mechanisms, and real-time monitoring of ultrasound equipment. Challenges such as model interpretability, dataset standardization, and industrial scalability are discussed. Future opportunities lie in developing universal predictive frameworks for ultrasound-related technologies and fostering cross-disciplinary integration of AI, computational chemistry, and sustainable engineering. This interdisciplinary approach aligns with the goals of Industry 5.0, fostering a transition toward digitized, eco-efficient, and intelligent extraction systems.

PMID:40349518 | DOI:10.1016/j.foodchem.2025.144649

J Dairy Sci. 2025 May 9:S0022-0302(25)00320-0. doi: 10.3168/jds.2025-26328. Online ahead of print.

ABSTRACT

We conducted a large GWAS of 11 health traits belonging to 3 trait complexes: (1) metabolic diseases, (2) infectious and noninfectious feet and claw disorders, and (3) udder-related traits in 100,809 to 180,217 German Holstein cows to investigate the genetic architecture and underlying biological mechanisms behind these complex traits. The GWAS identified 12,306 genome-wide significant variants across 10 traits. The new association signals were inspected with a Bayesian fine-mapping approach, leading to the discovery of 159 novel variants with high potential for causality. Variants were in known and novel regions for the traits studied, leading to a list of 53 novel candidate genes. Our study represents the largest whole-genome sequence GWAS for health traits so far, hence ensuring the power to detect meaningful variants, especially when enhanced with fine-mapping.

PMID:40349760 | DOI:10.3168/jds.2025-26328

J Pediatr (Rio J). 2025 May 8:S0021-7557(25)00078-6. doi: 10.1016/j.jped.2024.10.013. Online ahead of print.

ABSTRACT

OBJECTIVE: The objective of the investigation was to assess the potential mediating role of mental health in the association between cardiorespiratory fitness (CRF) and academic performance in European schoolchildren.

METHOD: The study followed a cross-sectional design. 507 schoolchildren (51.5 % girls, 7.4 ± 0.4 years) from 20 schools in five European countries were included in the analyses. Academic performance was assessed using school grades, mental health was assessed through the Strengths and Difficulties Questionnaire (SDQ) for parents, and CRF was estimated through the multistage 20-m shuttle run test. Linear regression and mediation analyses were conducted to test these hypotheses.

RESULTS: Mental health difficulties were associated with worse performance on academic indicators (β ranging from -0.121 to -0.324, p < 0.05). Further, mental health difficulties were associated with lower CRF (β ranging from -0.121 to -0.189, p < 0.05). Mediation analyses revealed that the association between CRF and academic performance indicators was partially mediated (from 8 % to 25 %) by mental health [except for conduct and peer problems (β ranging from -0.025 to -0.080, p > 0.05).

CONCLUSION: The present results highlight that mental health is a possible mediator in the association between CRF and academic performance. These findings might support the importance of improving CRF levels to reduce mental health difficulties with subsequent potential benefits on academic performance.

PMID:40349722 | DOI:10.1016/j.jped.2024.10.013

Curr Opin Struct Biol. 2025 May 10;93:103050. doi: 10.1016/j.sbi.2025.103050. Online ahead of print.

ABSTRACT

Reconstitution and direct extraction of membrane proteins using saposins is an emerging technique for solubilizing and stabilizing membrane proteins. The Salipro technology offers several advantages over traditional detergent solubilization, including a more native lipid environment, increased protein stability, and maintenance of functionality. This review covers recent studies that have used Salipros to characterize membrane proteins, as well as advances in direct extraction methods that have enabled the structural and functional characterization of a variety of targets.

PMID:40349676 | DOI:10.1016/j.sbi.2025.103050

Rinsho Ketsueki. 2025;66(4):228-232. doi: 10.11406/rinketsu.66.228.

ABSTRACT

A 48-year-old man with acute myeloid leukemia underwent HLA-matched related donor peripheral blood stem cell transplantation. He developed chronic graft-versus-host disease (cGVHD) of the liver on day 359, which became dependent on cyclosporine and prednisolone. Long-term administration of cyclosporine led to progressive renal dysfunction. Ibrutinib was started, but was stopped due to acute cardiac failure. Mycophenolate mofetil was then started and liver cGVHD improved. The patient developed bacterial pneumonia and COVID-19 during this period. He began to experience limited range of motion in the shoulder joints beyond 2 years after transplantation, and suffered from progressive symptoms. To prevent additional infections due to myelosuppression, drug-induced liver dysfunction, and progression of renal dysfunction, extracorporeal photopheresis (ECP) was chosen to treat musculoskeletal cGVHD. ECP was started on day 1202 and completed 6 months later following the recommended schedule, without severe adverse events. Shoulder joint symptoms completely resolved with ECP, and the cGVHD score in joints decreased from 2 to 0. ECP is considered a promising treatment option for cGVHD patients who are at risk of infection and liver or renal dysfunction.

PMID:40350272 | DOI:10.11406/rinketsu.66.228

ACS Infect Dis. 2025 May 11. doi: 10.1021/acsinfecdis.5c00226. Online ahead of print.

ABSTRACT

Infections in the lungs of cystic fibrosis (CF) patients are often polymicrobial in nature, typically comprising Pseudomonas aeruginosa and Staphylococcus aureus. Compounds that act as an antimicrobial agent against one of these pathogens, and as an antibiotic adjuvant against the other, could provide a valuable approach to treating such infections, however a model that mimics the unique environment found with the CF lung is required for the identification and characterization of such molecules. To address this, we employed a S. aureus/P. aeruginosa coculture screening model in synthetic sputum, and identified compounds from our in-house library that simultaneously have potent anti-S. aureus activity, and potentiate colistin against colistin-resistant P. aeruginosa. The two lead compounds, 12F1 and 12G9, control growth of both species when dosed alongside sub-inhibitory concentrations of colistin, highlighting the potential of using a single molecule as both an antibiotic and antibiotic adjuvant to target multiple species in polymicrobial infections, as well as the importance of conducting activity screens in clinically relevant media.

PMID:40349215 | DOI:10.1021/acsinfecdis.5c00226

Eur J Radiol. 2025 May 3;188:112160. doi: 10.1016/j.ejrad.2025.112160. Online ahead of print.

ABSTRACT

OBJECTIVES: Optimize deep learning-based vertebrae segmentation in longitudinal CT scans of multiple myeloma patients using structural uncertainty analysis.

MATERIALS & METHODS: Retrospective CT scans from 474 multiple myeloma patients were divided into train (179 patients, 349 scans, 2005-2011) and test cohort (295 patients, 671 scans, 2012-2020). An enhanced segmentation pipeline was developed on the train cohort. It integrated vertebrae segmentation using an open-source deep learning method (Payer's) with a post-hoc structural uncertainty analysis. This analysis identified inconsistencies, automatically correcting them or flagging uncertain regions for human review. Segmentation quality was assessed through vertebral shape analysis using topology. Metrics included 'identification rate', 'longitudinal vertebral match rate', 'success rate' and 'series success rate' and evaluated across age/sex subgroups. Statistical analysis included McNemar and Wilcoxon signed-rank tests, with p < 0.05 indicating significant improvement.

RESULTS: Payer's method achieved an identification rate of 95.8% and success rate of 86.7%. The proposed pipeline automatically improved these metrics to 98.8% and 96.0%, respectively (p < 0.001). Additionally, 3.6% of scans were marked for human inspection, increasing the success rate from 96.0% to 98.8% (p < 0.001). The vertebral match rate increased from 97.0% to 99.7% (p < 0.001), and the series success rate from 80.0% to 95.4% (p < 0.001). Subgroup analysis showed more consistent performance across age and sex groups.

CONCLUSION: The proposed pipeline significantly outperforms Payer's method, enhancing segmentation accuracy and reducing longitudinal matching errors while minimizing evaluation workload. Its uncertainty analysis ensures robust performance, making it a valuable tool for longitudinal studies in multiple myeloma.

PMID:40349413 | DOI:10.1016/j.ejrad.2025.112160

Comput Biol Chem. 2025 May 5;118:108484. doi: 10.1016/j.compbiolchem.2025.108484. Online ahead of print.

ABSTRACT

Enhancers are short DNA fragments that enhance gene expression by binding to transcription factors. Accurately identifying enhancers and their strength is crucial for understanding gene regulation mechanisms. However, traditional enhancer sequencing techniques are costly and time-consuming. Therefore, it is necessary to develop computational methods to quickly and accurately identify enhancers and their strength. Given the limitations of existing computational methods, such as low performance and complex encoding, this study proposes a deep learning-based multi-task framework, iEnhancer-DS, for enhancer identification and their strength classification. First, feature embeddings characterizing DNA sequences are obtained using one-hot encoding and nucleotide chemical properties (NCP). Next, an improved DenseNet module is applied to learn implicit high-order features from the concatenated feature embeddings. Subsequently, the self-attention mechanism is used to dynamically assess the importance of features and assign weights to them, and then the features are passed to the multilayer perceptron (MLP) to calculate the prediction probabilities. Experimental results show that iEnhancer-DS achieves state-of-the-art performance in both enhancer identification and strength prediction. In the enhancer identification task, iEnhancer-DS improves ACC and MCC by 4.03% and 8.47% respectively over the current state-of-the-art methods. Similarly, in the enhancer strength prediction task, the ACC and MCC values of iEnhancer-DS increased by 1.40% and 3.81%, respectively. In addition, we used the t-SNE method to perform an interpretable analysis of the mechanism of action of iEnhancer-DS. The detailed code and raw data of iEnhancer-DS can be obtained from https://github.com/zha12ja/iEnhancer-DS.

PMID:40349379 | DOI:10.1016/j.compbiolchem.2025.108484

Int J Comput Assist Radiol Surg. 2025 May 11. doi: 10.1007/s11548-025-03388-z. Online ahead of print.

ABSTRACT

PURPOSE: The principal objective of this study was to develop and evaluate a deep learning model for segmenting the common iliac vein (CIV) from intraoperative endoscopic videos during oblique lateral interbody fusion for L5/S1 (OLIF51), a minimally invasive surgical procedure for degenerative lumbosacral spine diseases. The study aimed to address the challenge of intraoperative differentiation of the CIV from surrounding tissues to minimize the risk of vascular damage during the surgery.

METHODS: We employed two convolutional neural network (CNN) architectures: U-Net and U-Net++ with a ResNet18 backbone, for semantic segmentation. Gamma correction was applied during image preprocessing to improve luminance contrast between the CIV and adjacent tissues. We used a dataset of 614 endoscopic images from OLIF51 surgeries for model training, validation, and testing.

RESULTS: The U-Net++/ResNet18 model outperformed, achieving a Dice score of 0.70, indicating superior ability in delineating the position and shape of the CIV compared to the U-Net/ResNet18 model, which achieved a Dice score of 0.59. Gamma correction increased the differentiation between the CIV and the artery, improving the Dice score from 0.44 to 0.70.

CONCLUSION: The findings demonstrate that deep learning models, especially the U-Net++ with ResNet18 enhanced by gamma correction preprocessing, can effectively segment the CIV in intraoperative videos. This approach has the potential to significantly improve intraoperative assistance and reduce the risk of vascular injury during OLIF51 procedures, despite the need for further research and refinement of the model for clinical application.

PMID:40349282 | DOI:10.1007/s11548-025-03388-z

Oncologist. 2025 May 8;30(5):oyaf090. doi: 10.1093/oncolo/oyaf090.

ABSTRACT

BACKGROUND: Accurate preoperative assessment of axillary lymph node metastasis (ALNM) in breast cancer is crucial for guiding treatment decisions. This study aimed to develop a deep-learning radiomics model for assessing ALNM and to evaluate its impact on radiologists' diagnostic accuracy.

METHODS: This multicenter study included 866 breast cancer patients from 6 hospitals. The data were categorized into training, internal test, external test, and prospective test sets. Deep learning and handcrafted radiomics features were extracted from ultrasound images of primary tumors and lymph nodes. The tumor score and LN score were calculated following feature selection, and a clinical-radiomics model was constructed based on these scores along with clinical-ultrasonic risk factors. The model's performance was validated across the 3 test sets. Additionally, the diagnostic performance of radiologists, with and without model assistance, was evaluated.

RESULTS: The clinical-radiomics model demonstrated robust discrimination with AUCs of 0.94, 0.92, 0.91, and 0.95 in the training, internal test, external test, and prospective test sets, respectively. It surpassed the clinical model and single score in all sets (P < .05). Decision curve analysis and clinical impact curves validated the clinical utility of the clinical-radiomics model. Moreover, the model significantly improved radiologists' diagnostic accuracy, with AUCs increasing from 0.71 to 0.82 for the junior radiologist and from 0.75 to 0.85 for the senior radiologist.

CONCLUSIONS: The clinical-radiomics model effectively predicts ALNM in breast cancer patients using noninvasive ultrasound features. Additionally, it enhances radiologists' diagnostic accuracy, potentially optimizing resource allocation in breast cancer management.

PMID:40349137 | DOI:10.1093/oncolo/oyaf090

Cell Rep. 2025 May 9;44(5):115680. doi: 10.1016/j.celrep.2025.115680. Online ahead of print.

ABSTRACT

Chromatin and DNA modifications mediate the transcriptional activity of lineage-specifying enhancers, but recent work challenges the dogma that joint chromatin accessibility and DNA demethylation are prerequisites for transcription. To understand this paradox, we established a highly resolved timeline of their dynamics during neural progenitor cell differentiation. We discovered that, while complete demethylation appears delayed relative to shorter-lived chromatin changes for thousands of enhancers, DNA demethylation actually initiates with 5-hydroxymethylation before appreciable accessibility and transcription factor occupancy is observed. The extended timeline of DNA demethylation creates temporal discordance appearing as heterogeneity in enhancer regulatory states. Few regions ever gain methylation, and resulting enhancer hypomethylation persists long after chromatin activities have dissipated. We demonstrate that the temporal methylation status of CpGs (mC/hmC/C) predicts past, present, and future chromatin accessibility using machine learning models. Thus, chromatin and DNA methylation collaborate on different timescales to shape short- and long-term enhancer regulation during cell fate specification.

PMID:40349339 | DOI:10.1016/j.celrep.2025.115680

ISME J. 2025 May 11:wraf093. doi: 10.1093/ismejo/wraf093. Online ahead of print.

ABSTRACT

Anthropogenic perturbations to the nitrogen cycle, primarily through use of synthetic fertilizers, is driving an unprecedented increase in the emission of nitrous oxide (N2O), a potent greenhouse gas and an ozone depleting substance, causing urgency in identifying the sources and sinks of N2O. Microbial denitrification is a primary contributor to biotic production of N2O in anoxic regions of soil, marine systems, and wastewater treatment facilities. Here, through comprehensive genome analysis, we show that pathway partitioning is a ubiquitous mechanism of complete denitrification within microbial communities. We have investigated mechanisms and consequences of process partitioning of denitrification through detailed physiological characterization and kinetic modeling of a synthetic community of Rhodanobacter thiooxydans FW510-R12 and Acidovorax sp. GW101-3H11. We have discovered that these two bacterial isolates, from a heavily nitrate (NO3-) contaminated superfund site, complete denitrification through the exchange of nitrite (NO2-) and nitric oxide (NO). The process partitioning of denitrification and other processes, including amino acid metabolism, contribute to increased cooperativity within this denitrifying community. We demonstrate that certain contexts, such as high NO3-, cause unbalanced growth of community members, due to differences in their substrate utilization kinetics. The altered growth characteristics of community members drives accumulation of toxic NO2-, which disrupts denitrification causing N2O off gassing.

PMID:40349173 | DOI:10.1093/ismejo/wraf093

Probl Sotsialnoi Gig Zdravookhranenniiai Istor Med. 2025 May 10;33(2):1606. doi: 10.32687/0869-866X-2025-33-2-263-272.

ABSTRACT

The chronic cardiac deficiency continues to be one of the leading health care problems requiring innovative solutions. The article presents mathematical algorithm to evaluate drug interactions and targeted to minimize side effects and to optimize chronic cardiac deficiency therapy. The mathematical model, elaborated using AI, is based on analysis of fully connected sub-graphs and ranking of side effects of combined application of medications. This approach permits to implement optimal selection of the safest and most effective combinations of medications. This is particularly important with regard for co-morbid conditions when patients take simultaneously several different medications. The proposed approach can significantly improve risk prediction and favor more precise selection of combined therapy. The algorithm surmises necessity for further extension and specification of model, including consideration of wider spectrum of medications and mechanism of their interaction. In the context of rapidly advancing digital medicine, models based on mathematical algorithms and machine learning can complement systems of clinical decision support. These models also can become valuable tool improving treatment of various diseases, especially in co-morbid conditions opening new horizons in medical practice.

PMID:40349243 | DOI:10.32687/0869-866X-2025-33-2-263-272

Expert Opin Drug Metab Toxicol. 2025 May 10. doi: 10.1080/17425255.2025.2505637. Online ahead of print.

ABSTRACT

BACKGROUND: Tegoprazan (LXI-15028), a novel potassium-competitive acid blocker, has shown great efficacy in treating acid-related disorders. However, its metabolic and excretion characteristics are not fully understood.

RESEARCH DESIGN AND METHODS: A single oral dose of 50 mg/150 μCi [14C]tegoprazan was administered to six healthy subjects. Blood, urine and fecal samples were collected and measured for total radioactivity (TRA), tegoprazan and metabolites. Its safety was also assessed.

RESULTS: The maximum concentrations (Cmax) of tegoprazan and TRA in plasma were 634 ng/mL and 990 ng eq./mL, respectively, at 0.5 h post dose. Tegoprazan and its N-demethylation metabolite (M1) were the major drug-related compounds in plasma, accounting for 34.84% and 40.10% of TRA, respectively. The half-life (t1/2) of TRA (8.72 h) was longer than that of tegoprazan (4.33 h) in plasma, indicating slower metabolite elimination. Tegoprazan was excreted through both the urine (50.51 ± 3.35%) and feces (47.26 ± 3.06%). The main metabolic pathways of tegoprazan are demethylation, oxidation, glucuronidation and sulfation. There were no serious adverse events observed in this study.

CONCLUSIONS: Tegoprazan is widely metabolized and excreted completely in humans. Tegoprazan and M1 were the primary compounds present in the circulation.

CLINICAL TRIAL REGISTRATION: www.clinicaltrials.gov identifier is NCT05883306.

PMID:40349123 | DOI:10.1080/17425255.2025.2505637

BMC Gastroenterol. 2025 May 10;25(1):356. doi: 10.1186/s12876-025-03952-6.

ABSTRACT

OBJECTIVE: This study aims to create a reliable framework for grading esophageal cancer. The framework combines feature extraction, deep learning with attention mechanisms, and radiomics to ensure accuracy, interpretability, and practical use in tumor analysis.

MATERIALS AND METHODS: This retrospective study used data from 2,560 esophageal cancer patients across multiple clinical centers, collected from 2018 to 2023. The dataset included CT scan images and clinical information, representing a variety of cancer grades and types. Standardized CT imaging protocols were followed, and experienced radiologists manually segmented the tumor regions. Only high-quality data were used in the study. A total of 215 radiomic features were extracted using the SERA platform. The study used two deep learning models-DenseNet121 and EfficientNet-B0-enhanced with attention mechanisms to improve accuracy. A combined classification approach used both radiomic and deep learning features, and machine learning models like Random Forest, XGBoost, and CatBoost were applied. These models were validated with strict training and testing procedures to ensure effective cancer grading.

RESULTS: This study analyzed the reliability and performance of radiomic and deep learning features for grading esophageal cancer. Radiomic features were classified into four reliability levels based on their ICC (Intraclass Correlation) values. Most of the features had excellent (ICC > 0.90) or good (0.75 < ICC ≤ 0.90) reliability. Deep learning features extracted from DenseNet121 and EfficientNet-B0 were also categorized, and some of them showed poor reliability. The machine learning models, including XGBoost and CatBoost, were tested for their ability to grade cancer. XGBoost with Recursive Feature Elimination (RFE) gave the best results for radiomic features, with an AUC (Area Under the Curve) of 91.36%. For deep learning features, XGBoost with Principal Component Analysis (PCA) gave the best results using DenseNet121, while CatBoost with RFE performed best with EfficientNet-B0, achieving an AUC of 94.20%. Combining radiomic and deep features led to significant improvements, with XGBoost achieving the highest AUC of 96.70%, accuracy of 96.71%, and sensitivity of 95.44%. The combination of both DenseNet121 and EfficientNet-B0 models in ensemble models achieved the best overall performance, with an AUC of 95.14% and accuracy of 94.88%.

CONCLUSIONS: This study improves esophageal cancer grading by combining radiomics and deep learning. It enhances diagnostic accuracy, reproducibility, and interpretability, while also helping in personalized treatment planning through better tumor characterization.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40348987 | DOI:10.1186/s12876-025-03952-6

Sci Rep. 2025 May 10;15(1):16328. doi: 10.1038/s41598-025-98086-w.

ABSTRACT

Forest fires are severe ecological disasters worldwide that cause extensive ecological destruction and economic losses while threatening biodiversity and human safety. With the escalation of climate change, the frequency and intensity of forest fires are increasing annually, underscoring the urgent need for effective monitoring and early warning systems. This study investigates the application effectiveness of deep learning-based object detection technology in forest fire smoke recognition by using the YOLOv11x algorithm to develop an efficient fire detection model. The objective is to enhance early fire detection capabilities and mitigate potential damage. To improve the model's applicability and generalizability, two publicly available fire image datasets, WD (Wildfire Dataset) and FFS (Forest Fire Smoke), encompassing various complex scenarios and external conditions, were employed. After 501 training epochs, the model's detection performance was comprehensively evaluated via multiple metrics, including precision, recall, and mean average precision (mAP50 and mAP50-95). The results demonstrate that YOLOv11x excels in bounding box loss (box loss), classification loss (cls loss), and distribution focal loss (dfl loss), indicating effective optimization of object detection performance across multiple dimensions. Specifically, the model achieved a precision of 0.949, a recall of 0.850, an mAP50 of 0.901, and an mAP50-95 of 0.786, highlighting its high detection accuracy and stability. Analysis of the precision‒recall (PR) curve revealed an average mAP@0.5 of 0.901, further confirming the effectiveness of YOLOv11x in fire smoke detection. Notably, the mAP@0.5 for the smoke category reached 0.962, whereas for the flame category, it was 0.841, indicating superior performance in smoke detection compared with flame detection. This disparity primarily arises from the distinct visual characteristics of flames and smoke; flames possess more vivid colors and defined shapes, facilitating easier recognition by the model, whereas smoke exhibits more ambiguous and variable textures and shapes, increasing detection difficulty. In the test set, 86.89% of the samples had confidence scores exceeding 0.85, further validating the model's reliability. In summary, the YOLOv11x algorithm demonstrates excellent performance and broad application potential in forest fire smoke recognition, providing robust technical support for early fire warning systems and offering valuable insights for the design of intelligent monitoring systems in related fields.

PMID:40348915 | DOI:10.1038/s41598-025-98086-w

Sci Rep. 2025 May 10;15(1):16325. doi: 10.1038/s41598-025-99533-4.

ABSTRACT

To achieve low-power video communication in Internet of Things, this study presents a new deep learning-based fast transcoding algorithm from distributed video coding (DVC) to high efficiency video coding (HEVC). The proposed method accelerates transcoding by minimizing HEVC encoding complexity. Specifically, it models the selections of coding unit (CU) partitions and prediction unit (PU) partition modes as classification tasks. To address these tasks, a novel lightweight deep learning network has been developed acting as the classifier in a top-down transcoding strategy for improved efficiency. The proposed transcoding algorithm operates efficiently at both CU and PU levels. At the CU level, it reduces HEVC encoding complexity by accurately predicting CU partitions. At the PU level, predicting PU partition modes for non-split CUs further streamlines the encoding process. Experimental results demonstrate that the proposed CU-level transcoding reduces complexity overhead by 45.69%, with a 1.33% average Bjøntegaard delta bit-rate (BD-BR) increase. At the PU level, the transcoding achieves an even greater complexity reduction, averaging 60.97%, with a 2.16% average BD-BR increase. These results highlight the algorithm's efficiency in balancing computational cost and compression performance. The proposed method provides a promising low-power video coding scheme for resource-constrained terminals in both upstream and downstream video communication scenarios.

PMID:40348899 | DOI:10.1038/s41598-025-99533-4

Eur Radiol. 2025 May 10. doi: 10.1007/s00330-025-11559-4. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aimed to validate the agreement and diagnostic performance of a deep-learning-based coronary artery calcium scoring (DL-CACS) system for ECG-gated and non-gated low-dose chest CT (LDCT) across multivendor datasets.

MATERIALS AND METHODS: In this retrospective study, datasets from Seoul National University Hospital (SNUH, 652 paired ECG-gated and non-gated CT scans) and the Stanford public dataset (425 ECG-gated and 199 non-gated CT scans) were analyzed. Agreement metrics included intraclass correlation coefficient (ICC), coefficient of determination (R²), and categorical agreement (κ). Diagnostic performance was assessed using categorical accuracy and the area under the receiver operating characteristic curve (AUROC).

RESULTS: DL-CACS demonstrated excellent performance for ECG-gated CT in both datasets (SNUH: R² = 0.995, ICC = 0.997, κ = 0.97, AUROC = 0.99; Stanford: R² = 0.989, ICC = 0.990, κ = 0.97, AUROC = 0.99). For non-gated CT using manual LDCT CAC scores as a reference, performance was similarly high (R² = 0.988, ICC = 0.994, κ = 0.96, AUROC = 0.98-0.99). When using ECG-gated CT scores as the reference, performance for non-gated CT was slightly lower but remained robust (SNUH: R² = 0.948, ICC = 0.968, κ = 0.88, AUROC = 0.98-0.99; Stanford: R² = 0.949, ICC = 0.948, κ = 0.71, AUROC = 0.89-0.98).

CONCLUSION: DL-CACS provides a reliable and automated solution for CACS, potentially reducing workload while maintaining robust performance in both ECG-gated and non-gated CT settings.

KEY POINTS: Question How accurate and reliable is deep-learning-based coronary artery calcium scoring (DL-CACS) in ECG-gated CT and non-gated low-dose chest CT (LDCT) across multivendor datasets? Findings DL-CACS showed near-perfect performance for ECG-gated CT. For non-gated LDCT, performance was excellent using manual scores as the reference and lower but reliable when using ECG-gated CT scores. Clinical relevance DL-CACS provides a reliable and automated solution for CACS, potentially reducing workload and improving diagnostic workflow. It supports cardiovascular risk stratification and broader clinical adoption, especially in settings where ECG-gated CT is unavailable.

PMID:40348882 | DOI:10.1007/s00330-025-11559-4

Sci Rep. 2025 May 10;15(1):16291. doi: 10.1038/s41598-025-01146-4.

ABSTRACT

Due to complex environmental conditions and varying noise levels, traditional models are limited in their effectiveness for detecting anomalies in video sequences. Aiming at the challenges of accuracy, robustness, and real-time processing requirements in the field of image and video processing, this study proposes an anomaly detection and recognition algorithm for video image data based on deep learning. The algorithm combines the innovative methods of spatio-temporal feature extraction and noise suppression, and aims to improve the processing performance, especially in complex environments, by introducing an improved Variable Auto Encoder (VAE) structure. The model named Spatio-Temporal Anomaly Detection Network (STADNet) captures the spatio-temporal features of video images through multi-scale Three-Dimensional (3D) convolution module and spatio-temporal attention mechanism. This approach improves the accuracy of anomaly detection. Multi-stream network architecture and cross-attention fusion mechanism are also adopted to comprehensively consider different factors such as color, texture, and motion, and further improve the robustness and generalization ability of the model. The experimental results show that compared with the existing models, the new model has obvious advantages in performance stability and real-time processing under different noise levels. Specifically, the AUC value of the proposed model is 0.95 on UCSD Ped2 dataset, which is about 10% higher than other models, and the AUC value on Avenue dataset is 0.93, which is about 12% higher. This study not only proposes an effective image and video processing scheme but also demonstrates wide practical potential, providing a new perspective and methodological basis for future research and application in related fields.

PMID:40348836 | DOI:10.1038/s41598-025-01146-4