Browse Articles

An efficient YOLOv12-based framework for detecting extremely small-scale objects

Abstract Object detection in aerial imagery, particularly from UAVs and drones, presents unique challenges such as small and extremely small-scale object distributions. To address these drawbacks, the present research proposes an efficient YOLOv12 model. The first core contribution of our work is the introduction of the Area-Attention C2f (A2C2F) module, which fuses multi-head MLP blocks with localized area-attention mechanisms to strengthen spatial feature learning while maintaining lightweight computation. Second, the model integrates the Cross Stage Partial with Kernel size 2 (C3K2) module, a lightweight variant of the C3 block, which reduces convolutional complexity and computational cost while maintaining feature extraction capability for efficient detection. Third, a multi-scale fusion strategy by stacking A2C2F blocks along with Concat and Upsample operations ensures the preservation of high-resolution features for detecting small-scale objects, a common challenge in drone-captured data. Fourth, a novel detection head with decoupled classification and regression branches, enhanced by attention-guided feature fusion, improves prediction consistency and boosts inference speed. Extensive experiments conducted on the VisDrone dataset demonstrate that the proposed framework effectively detects objects with dimensions smaller than 3–5 pixels, where traditional YOLO variants typically fail, proving its robustness in extremely small-scale detection. The proposed model achieves a Precision of 69.1%, Recall of 48.5%, and F1-score of 56.99%, outperforming recent models. Notably, it achieves a mAP@50 of 58.8% and mAP@0.5:0.95 of 40.9%, showing substantial improvement over prior methods. Despite utilizing 59.1 M parameters and 198.6 GFLOPs, the model maintains an efficient inference rate of approximately 40 FPS on the A100 GPU, confirming its suitability for real-time UAV edge deployment. When compared to two-stage and anchor-based models, our model delivers higher AP scores at a lower input resolution of 640 × 640 pixels, making it a highly effective and computationally efficient framework for UAV-based small and extremely small object detection.

Perspective of healthcare professionals on barriers and facilitators in exploring end-of-life care preferences of patients with pulmonary fibrosis: A qualitative study

Background Progressive pulmonary fibrosis is a lethal disease with a survival of 3–5 years with optimal medication treatment. Palliative care and advance care planning are therefore receiving increasing attention in the literature. However, structural implementation in clinical practice is still lacking. The aim of this study was to explore the needs, facilitators, and barriers for communication on the topic of end-of-life preferences of patients from the perspective of healthcare professionals. Methods A generic qualitative study was performed with focus groups and individual semi structured interviews with healthcare professionals. Data collection and analysis were performed iteratively. A thematic analysis was performed, following the methods of Braun and Clarke. Results Three focus groups and seven individual semi-structured interviews were conducted. Three themes were generated: (1) a lack of vision on palliative care, resulting in different approaches within the same clinic and showing the need for optimization of collaboration; (2) the importance of a learning-driven environment to support healthcare professionals skills and knowledge; and (3), the central role of the individual professional in developing skills and knowledge. Conclusions/discussion This study underscores the importance of behavioral and organizational change in palliative care to optimize conversations exploring values, preferences, and needs for end-of-life care for patients with pulmonary fibrosis. Leveraging the shared motivation of healthcare professionals to provide optimal care, integrating these findings into training and coaching programs can further enhance patient-centered approach in palliative care.

Age dependent morphological changes of the normal meniscus in children based on large scale MRI analysis

A small-scale study on dancing for people living with Parkinson’s disease

Background People with Parkinson’s disease (PD) need life-long rehabilitative interventions to slow disease progression and reduce impact of the disease on daily life activities. To be sustainable for the individual, activities should have a positive impact on physical, cognitive and mental health, and should be appealing and meaningful. Aim To quantitatively evaluate the health-related effects of a 10-week dance program for patients with PD. Methods A cross-over design with two groups. Group 1 undertook 10 weeks of dance classes; after that, group 2 began their 10 weeks of dance classes. Assessments of both groups at four timepoints (baseline, 10, 20 and 30 weeks) included physical tests and self-reported questionnaires to assess cognition, self-efficacy, well-being, fatigue, and health-related quality of life. The analysis involved comparisons of results after the dance and non-dance periods, for all instruments. Results The analyses could not show any significant differences between the assessments after the dance period compared to after the no dance period. Conclusion Despite the lack of quantitative evidence of the positive experiences earlier described from focus groups, the study provided insights into how future research could be organised to better capture the multifaceted benefits. Furthermore, the study provides additional evidence that dance as a health-promoting activity in Parkinson’s disease should be viewed in a longer-term perspective.

Identifying the coupling mechanisms between land surface temperature and urban physical form in Chengdu’s five central districts

Impacts of polymorphisms in drug-metabolizing enzyme and transporter genes on irinotecan toxicity and efficacy in Thai colorectal cancer patients

Introduction Irinotecan is a chemotherapy agent commonly prescribed for metastatic colorectal cancer but often leads to neutropenia. Variations in genes encoding drug-metabolizing enzymes and transporters may affect the toxicity and effectiveness of irinotecan. This study aimed to examine the impact of these genetic polymorphisms on irinotecan outcomes in Thai colorectal cancer patients. Methods The study retrospectively analyzed 41 metastatic colorectal cancer patients treated with irinotecan-based chemotherapy. Genotyping was conducted for 23 single nucleotide polymorphisms in genes including UGT1A1, CYP3A4, CYP3A5, CES1, ABCB1, ABCC2, ABCC5, ABCG1, ABCG2, and SLCO1B1 .Toxicity and efficacy were assessed, with statistical significance set at a Bonferroni-corrected P value < 0.002. Results In terms of toxicity, UGT1A1*6 was significantly associated with both all-grade and severe neutropenia in the first cycle ( p  < 0.001) and severe neutropenia in the second cycle ( p  < 0.002). Lower absolute neutrophil count was observed among intermediate and poor UGT1A1 metabolizers ( p  < 0.001). The ABCC2 -24C > T variant was linked to all-grade neutropenia in the second cycle ( p  = 0.001). For efficacy, patients with the wild-type UGT1A1* 6 had longer progression-free survival (PFS) ( p  < 0.002). Additionally, the SLCO1B1 521T > C variant was associated with improved PFS ( p  < 0.002). Conclusion UGT1A1*6 and ABCC2 -24C > T variants emerge as potential predictors of irinotecan-induced neutropenia, while UGT1A1*6 and SLCO1B1 521T > C may serve as markers of prolonged PFS in Thai patients. Validation through larger prospective studies is essential to confirm and refine these genetic associations.

Chronic liver disease and cirrhosis mortality following surgery for colon or rectal cancer

Mapping the microRNA-mediated crosstalk between insulin resistance and Alzheimer’s disease: A computational genomic insight

Insulin resistance (IR) and Alzheimer’s disease (AD) share overlapping molecular mechanisms, but the precise link between these conditions remains unclear. MicroRNAs, as post-transcriptional regulators of gene expression, may mediate this connection by targeting genes involved in both pathways. In this study, we employed a multi-step bioinformatics approach to identify microRNAs that simultaneously regulate genes associated with IR and AD. Twenty key IR-related genes were selected from the literature, and their microRNA regulators were predicted using five computational tools. These predictions were validated using experimentally supported databases (TarBase and miRTarBase), and each miRNA–gene interaction was scored. Sixteen high-confidence microRNAs were shortlisted based on cumulative prediction and validation scores. These microRNAs were then analyzed for their interactions with AD pathway genes via KEGG pathway analysis. The AD-related target genes were further processed through protein–protein interaction network analysis using STRING and hub gene identification via Cytoscape. Functional enrichment of these hub genes using Gene Ontology and KEGG analysis revealed their involvement in shared biological processes, including apoptosis, insulin signaling, glucose metabolism, and neuroinflammation. Prominent candidates such as miR-7-5p, miR-106b, miR-424-5p, and miR-15a were identified. These results suggest that a subset of microRNAs may serve as critical molecular links between IR and AD, offering potential targets for early diagnosis and intervention.

Multi-view text classification through integrated RNN autoencoder learning of word, sentence, emotion and paragraph representations

Professional identity and work-related quality of life among obstetric nurses: Mediating role of psychological resilience and moderating effect of internet+ participation willingness

Background As the “Internet plus” era unfolds, the domain of obstetric nursing has ushered in the innovative development model of Internet plus Nursing Services(IPNS). This shift has led to alterations in the professional environment and work demands faced by obstetric nursing personnel, consequently bringing the work-related quality of life of these nursing professionals to the forefront of attention. Objective This research aims to investigate the mediating and moderating effects of psychological resilience and the willingness to engage in IPNS among obstetric nurses on the relationship between professional identity and work-related quality of life, under the premise that these factors have a significant impact on work-related quality of life. Methods This study selected obstetric nurses from 33 tertiary hospitals in Anhui Province, China, that have implemented IPNS to date and met the specified criteria for inclusion and exclusion. The assessment focused on their professional identity, psychological resilience, work-related quality of life, and willingness to engage in providing “Internet plus Nursing Services.” AMOS was used for mediation effect analysis, and the PROCESS macro in SPSS was employed to investigate moderated mediation effects. Results In the context of IPNS, psychological resilience acts as a mediator in the relationship between professional identity and work-related quality of life among obstetric nurses. Furthermore, psychological resilience and the willingness to participate exhibit a moderated mediation effect in this relationship—specifically, psychological resilience modulates the latter segment of the pathway from professional identity to work-related quality of life via the mediation of participation willingness. Conclusion The findings suggest that nursing administrators, while focusing on the work-related quality of life of obstetric nurses, should concurrently consider nurses’ psychological resilience and their willingness to participate. This approach facilitates the development of effective employee motivation and support strategies, which in turn can enhance the work-related quality of life of obstetric nurses in the IPNS context.

Response of saffron (Crocus sativus L.) to irrigation water salinity following corm priming with cold plasma technology

Unravelling drought stress adaptation in sugarcane interspecific hybrids: A multi-level analysis

Drought stress, a major abiotic stress, severely limits sugarcane productivity through adversely altered cellular processes. Identifying key traits linked to physiological and biochemical responses during water stress and recovery is vital for screening and breeding drought stress-tolerant varieties. The present study assessed 18 sugarcane genotypes based on morpho-physiological, biochemical, and molecular changes during drought stress and at stress recovery in a complete randomized block design. Cane height, number of internodes, Soil Plant Analytical Development (SPAD) index, Leaf Area Index (LAI), Relative Water Content (RWC), Nitrate Reductase (NR), and proline were positively correlated to drought stress. Among the genotypes studied, AS-04-1687, AS-04-635, Co 86032, Co 85019, CoM 0265, AS-04-2097, and AS-04-245 were identified as potential clones with high potential for drought stress tolerance in sugarcane. Expression profiling of ten stress-induced genes, namely NAC, MYB59, peroxidase, GST (glutathione transferase), GLY I (glyoxylase I), GLY III (glyoxylase III), RAB (response to abscisic acid), CesA3 (cellulose synthase), heat shock proteins, and stress-related proteins in sugarcane stem tissues under drought-stressed conditions revealed significant differences between tolerant and susceptible genotypes. The interspecific hybrid, AS-04-1687, outperformed for all the genes under drought stress conditions and could be a potential donor in further drought tolerance breeding programmes. We have also cloned and characterised drought stress-induced transcription factor MYB59 (a negative regulator of Ca + signalling), which could be used in genetic engineering programmes for the development of drought stress-tolerant genotypes.

Real time sugarcane stem health detection with YOLOv8 tinier and RepNCSP ELAN

Correction: Potential evidence of reengagement attempts following interruptions of a triadic social game in bonobos and chimpanzees

Dynamic optimization and coordination of the new energy vehicle supply chain based on credit trading and green innovation

Hyperglycemia and bladder cancer prognosis in a Finnish population-based cohort

Background Diabetes might increase risk of bladder cancer (BCa) incidence and bladder cancer specific death. Objective To assess the potential association between diabetes and prognosis of BCa. Design, setting and participants Register-based cohort study included 14,638 participants with BCa diagnosed in Finland during 1995–2012. Three databases were used to obtain information on BCa, diabetes and comorbidities. Hyperglycemia was determined by blood glucose or HbA1c. The role of antidiabetic medication use was also assessed. Outcome measurements and statistical analysis Associations between diabetes and BCa-specific and overall mortality were evaluated using multivariable Cox regression models. Results and limitation During median follow-up of 4.3 years after BCa diagnosis 3,582 (24.5%) participants died of BCa. Diabetic post-diagnostic blood glucose level was associated with worse BCa-specific HR 1.58 (1.10–2.28) and overall survival HR 1.50 (1.20–1.89). The risk increase was slightly lower among hyperglycemic DM medication users (HR 1.43 (0,68–3.02) than non-users HR 1.80 (1.13–2.85). The main limitation of this study was insufficient information on tobacco smoking. Conclusions Diabetes and diabetic glycemic status were associated with increased risk of both overall and BCa-specific death. Patient summary In a Finnish population-based cohort study, diabetic bladder cancer patients had worse prognosis compared to non-diabetics. This was observed in both genders.

Correction: 2-aminoethoxydiphenylborane intervenes intracellular calcium signaling and attenuates myocardial ischemia-reperfusion injury in mice through ITPR1/MCU pathway

Therapeutic mechanism of Pithecellobium clypearia Benth. on imiquimod-induced psoriasis revealed by tissue transcriptomics in mice

Background Psoriasis is an erythema papulosquamous dermatosis that cannot be cured at present. Pithecellobium clypearia Benth. belonging to the Leguminosae family and is clinically used as a treatment for gastroenteritis, acute tonsillitis, acute pharyngitis, and upper respiratory tract infections. Our previous studies have found that P. clypearia can improve imiquimod (IMQ)-induced psoriasis in mice and have revealed some differential metabolites and pathways using metabolomics methods. However, the underlying molecular mechanisms remain obscure. The purpose of this study is to investigate the therapeutic mechanism of the anti-psoriatic effects of P. clypearia using transcriptomics technology. Methods The psoriasis model was induced in male Balb/c mice by applying IMQ on their backs. To identify the differentially expressed genes (DEGs) among groups, RNA sequencing was employed. DEGs were analyzed using Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis, and protein-protein interaction (PPI) network analysis. Furthermore, quantitative real-time PCR (qPCR) was employed for validation of these results. Results A total of 26 DEGs were identified, with several enriched pathways, including the MAPK signaling pathway, unfolded proteins response, hedgehog signaling pathways, NADH dehydrogenase activity, oxidative phosphorylation. Additionally, PPI network analysis revealed that gene Hspa1a was connected with Hspa1b , Bcl2 and GzmA , and Asns was related to Trib3 , Slc7a5 and Chac1 , and mt-Nd4l was correlated with mt-Nd5 and mt-Nd6 . The RNA-seq results were concordant with the qPCR results. Conclusions P. clypearia may ameliorate inflammation in psoriasis mice by modulating genes such as Hspa1a , Hspa1b , mt-Nd4l , mt-Nd5 , mt-Nd6 , Bcl2 , Asns , Trib3 , and associated pathways related to energy metabolism, cell growth, and apoptosis. Our study explored the underlying molecular mechanisms at the transcriptome level and provided a theoretical basis for further investigation into the efficacy of P. clypearia .

Exploring the relationship between space weather conditions and power performance of EgyptSat-1 using machine learning

Abstract The growing reliance on satellites highlights the need to understand how space weather quantitatively impacts the reliability and efficiency of power subsystems. While it is well established that space weather disturbances can trigger anomalies in satellite operations, most existing studies lack integrated, data-driven approaches capable of capturing the complex, nonlinear interactions between space weather parameters and satellite health telemetry. This study addresses this gap by introducing a novel four-stage data driven workflow to examine the relationship between key space weather indicators (proton flux, AL index, galactic cosmic rays (GCR), and solar wind density) and the NN1_Voltage and TBS1_Current and temperature of the EgyptSat-1 satellite power subsystem (T1BS, T3BS). The workflow includes: (1) data preprocessing; (2) To handle the high dimensionality and complexity of the data, a two-stage non-linear feature selection approach was employed. In the first stage, an unsupervised Restricted Boltzmann Machine (RBM) was applied to extract a compact and structurally stable feature subset. This was followed by a supervised mutual information (MI) validation step to ensure maximum predictive relevance to the satellite target parameters (T1BS and T3BS). (3) six machine learning models namely: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Random Forest Regressor, Adaptive Boost, Gradient Boosting, and Voting Regressor, to capture dynamic system behaviours; and (4) anomaly detection and validation by correlating prediction residuals with space weather disturbances, using STL decomposition and Z-score for GCR and P10 anomaly detection, and coincidence rate analysis to assess temporal alignment. The Random Forest (RF) model exhibited strong predictive performance. For NN1_Voltage, the mean squared error (MSE) was 0.00147 (95% CI: 0.00120–0.00184), the root mean squared error (RMSE) was 0.038 (95% CI: 0.0346–0.0428), the mean absolute error (MAE) was 0.028 (95% CI: 0.026–0.031), and the mean absolute percentage error (MAPE) was 0.09% (95% CI: 0.08–0.10%). For TBS1_Current, RF achieved an MSE of 0.0405 (95% CI: 0.0319–0.0489), RMSE of 0.201 (95% CI: 0.179–0.221), MAE of 0.153 (95% CI: 0.136–0.169), and MAPE of 2.4% (95% CI: 2.1–2.6%). Furthermore, analysis of detected anomalies revealed temporal coincidence rates of 31% with GCR disturbances and 27% with P10 proton events. Statistical validation using chi-squared and Fisher’s exact tests yielded significant p-values (e.g., p  = 2.83 × 10⁻³ for GCR; p  = 5.63 × 10⁻⁷ for P10), suggesting a potential relationship worth further investigation. This analysis is particularly relevant for assessing unexplained satellite failures such as the loss of EgyptSat-1 and contributes to improved resilience and monitoring strategies for future missions. While the proposed workflow shows strong predictive performance, its validation is currently limited to a single satellite dataset, highlighting the need for broader cross-mission testing. This study not only enhances our understanding of space weather impacts on satellite power systems but also demonstrates the potential of machine learning in improving anomaly detection and resilience of satellites operating in challenging space environments.

“This needs to be told to everyone”: Content analysis of written immediate responses from an online experiment examining health warning messages about alcohol consumption and breast cancer risk

Alcohol consumption increases breast cancer risk. We evaluated the responses of 748 United States female participants ages 21–29 to health warning messages addressing the relationship between alcohol consumption and increased breast cancer risk. In an online experiment, participants were randomly assigned to view standalone health warning messages about alcohol, breast cancer, and breast cancer health effects with varying picture and text attributes. Participants then completed post-message exposure assessments that included an immediate open-ended response to the message prompt. We conducted a qualitative content analysis of the responses and coded deductively based on constructs from the Message Impact Framework including message reactions, attitudes and beliefs, and behavioral intentions. These constructs and corresponding variables were present in participants’ responses. Response type did not vary by participants’ demographics or the attributes of the health warning message they viewed. The code new information was applied to 20% of the responses, indicating that those participants had no prior knowledge of alcohol and breast cancer risk. Alcohol and breast cancer messaging could impact drinking behaviors. Given the frequency of responses indicating a lack of awareness, more work in cancer prevention and population health messaging is warranted.