Browse Articles
Discover research articles across all indexed journals
Determination of the oral carcinoma and sarcoma in contrast enhanced CT images using deep convolutional neural networks
Abstract Oral cancer is a hazardous disease and a major cause of morbidity and mortality worldwide. The purpose of this study was to develop the deep convolutional neural networks (CNN)-based multiclass classification and object detection models for distinguishing and detection of oral carcinoma and sarcoma in contrast-enhanced CT images. This study included 3,259 slices of CT images of oral cancer cases from the cancer hospital and two regional hospitals from 2016 to 2020. Multiclass classification models were constructed using DenseNet-169, ResNet-50, EfficientNet-B0, ConvNeXt-Base, and ViT-Base-Patch16-224 to accurately differentiate between oral carcinoma and sarcoma. Additionally, multiclass object detection models, including Faster R-CNN, YOLOv8, and YOLOv11, were designed to autonomously identify and localize lesions by placing bounding boxes on CT images. Performance evaluation on a test dataset showed that the best classification model achieved an accuracy of 0.97, while the best detection models yielded a mean average precision (mAP) of 0.87. In conclusion, the CNN-based multiclass models have a great promise for accurately determining and distinguishing oral carcinoma and sarcoma in CT imaging, potentially enhancing early detection and informing treatment strategies.
HPV cancer burden by anatomical site, country, and region in 2022
Copper only SOD repeat proteins likely act as an extracellular superoxide dismutase in oyster antioxidant defense
Age-related decline in behavior and reproductive health in male mice
The management of patients who self-harm in adult inpatient mental health settings: A policy analysis of English NHS mental health trusts
The management of self-harm is a critical focus for staff in inpatient mental health settings. This study aimed to better understand how staff are guided through policies to manage self-harm via the following objectives: 1) to assess the alignment of policies from English NHS Mental Health trusts with national guidelines, 2) identify which aspects of the national guidelines are most and least frequently reflected in these policies, and 3) determine whether trusts with dedicated self-harm policies better reflect national guidelines. We conducted a content analysis of self-harm-related policies across 50 English NHS mental health trusts against a framework of 20 standards created from National Institute for Health and Care Excellence self-harm guidelines. Our analysis revealed a significant difference (U = 36.50, p = .002) in the number of standards met by trusts with a specific self-harm policy (M = 11.44, SD = 3.00) compared to those without (M = 7.26, SD = 3.00), with the number of standards met ranging from zero to 15. Notably, trusts failed to meet the majority of standards (M = 11.69, SD = 3.30). The findings of this study highlight several new insights into NHS trust policy on self-harm: 1) trusts exhibit variability in how they organise information across their policies, 2) dedicated self-harm policies may support trusts to better meet guidance but risk complicating guidance for staff, 3) policy content varies across trusts, 4) the importance of patient voice is acknowledged but the facilitators of good participation are poorly supported in the same policies, 5) trusts rarely define self-harm and some trusts use definitions which do not reflect guidelines, and 6) harm-reduction remains underrepresented in policies, reflecting ongoing contention surrounding its implementation. Further research is needed to understand the role that policy and guidelines play in guiding staff practices when managing self-harm.
Mamba-fusion for privacy-preserving disease prediction
Gradual poisoning of a chest x-ray convolutional neural network with an adversarial attack and AI explainability methods
H3 lysine 18 lactylation-mediated RRAS2 facilitates migration and invasion of head and neck squamous cell carcinoma
Hydration assessment and physical performance of mountain bike cyclists in competition in a hot environment
Downregulation of UDP-glucose 6-dehydrogenase predicts adverse outcomes in patients with colorectal cancer and promotes tumorigenesis
Effects of LPBF printing parameters on the columnar-to-equiaxed grain transition in FeCoCrNiMn alloys
Exploring the regulatory mechanisms of reproductive dysfunction in obese patients with PCOS
NaLRR-RK4 mediates MAPK signaling to enhance plant defense against Alternaria alternata in Nicotiana attenuata
Neutrophil-targeting drug seeks first approval in an inflammatory lung disease
Research on urban resilience assessment and driving forces based on Production-Living-Ecological Spaces: A case study of the Three Gorges Reservoir Area in China
This study aims to develop a resilience evaluation approach based on production-living-ecological spaces and identify the key drivers of urban resilience in less-developed areas, taking the Three Gorges Reservoir Area in China as a case study. Understanding how to increase urban resilience and how to coordinate the three types of space in urban areas is critical for the healthy and stable development of cities. In this work, we develop an integrated assessment methodology for resilience in three dimensions: production space, living space, and ecological space. The geographical agglomeration impact is studied using the spatial approach, such as the Jenks natural breakpoint method and spatial autocorrelation analysis. Geographic Detectors are used to identify the drivers and to provide tailored optimization solutions. It was discovered that: (1) from 2010 to 2020, the comprehensive resilience of counties in the Three Gorges Reservoir Area of China continues to increase, as does the sub-spatial resilience; (2) both the resilience of counties and the sub-spatial resilience exhibit “unbalanced” characteristics, and the spatial distribution exhibits “randomization”. There appears to be no evident clustering influence; (3) each county’s production space has a high level of resilience, which is the component that has the greatest influence on the county’s total resilience and the living space is next, followed by the ecological space; (4) the vast majority of interactions between the driving factors are two-factor enhancement, with just a small percentage being non-linear enhancement. The study’s findings can provide theoretical guidance and technical help for the study of urban resilience in less-developed locations. Furthermore, the findings are extremely important for the development of resilient cities.
Ultrasound features of myofascial trigger points: a multimodal study integrating preliminary histological findings from the upper trapezius
Investigating health literacy and sociodemographic factors in college students
Energy optimization model of multi-energy system considering distributed photovoltaic coordinated carbon reduction
Comparative analysis of humoral immunity kinetics following three COVID-19 vaccines in a multi-ethnic cohort of medical students and healthcare professionals across Malaysia
Abstract The objective of our study was to evaluate the time-dependent humoral immunity kinetics among multi-ethnic population of medical students and healthcare professionals across Malaysia following two doses of Comirnaty, Vaxzevria, and CoronaVac vaccines. Prospective observational cohort research was carried out from September 2021-March 2023. 242 vaccine recipients have completed the follow-up. After second vaccination dosage, peripheral blood was drawn every four weeks from week 0–24. Anti-S IgG and percentage of neutralization were measured from each individual plasma sample. Recipients of Comirnaty and Vaxzevria vaccine, exhibited adequate anti-S IgG and neutralizing antibody till week 24. In compared to Comirnaty/Vaxzevria vaccine group, CoronaVac group showed significant decrease of antibody as early as week 12. The Comirnaty vaccine peaked anti-S IgG production at week 4, while the Vaxzevria and CoronaVac vaccines peaked at week 2. The Comirnaty vaccine (91.3%) showed strong Ig-RBD neutralizing antibody response even after week 24, which led to the slowest rate of antibody waning when compared to CoronaVac (13%), which never achieves high Ig-RBD neutralizing antibody. The percentage of inhibition of Ig-RBD binding on ACE2 receptor and anti-S IgG seroconversion were significantly higher in the Comirnaty vaccine. The antibody response of Comirnaty was lower in recipients with higher BMIs than in those with normal or low BMIs. Higher BMI, however, was associated with more robust humoral immune responses to Vaxzevria vaccine. Following immunisation, the Chinese and Indian populations might exhibit a stronger humoral immune response than the Malay population.