Explore the vast range of titles available.

Background Magnetic resonance imaging (MRI) is essential for brain tumor diagnosis. Deep learning models, such as Residual Network 50 Version 2 (ResNet50V2), have demonstrated strong performance in tumor classification. However, integrating attention mechanisms may further enhance diagnostic accuracy. This study evaluates the impact of different attention mechanisms on a ResNet50V2-based MRI tumor classification model for distinguishing between meningioma, glioma, pituitary tumors, and cases with no tumor. Methods A ResNet50V2-based model was trained on 3,096 annotated MRI scans from a publicly available dataset on Kaggle. Five model configurations were evaluated: baseline ResNet50V2, Squeeze-and-Excitation (SE), Convolutional Block Attention Module (CBAM), Self-Attention (SA), and Attention Gated Network (AGNet). Performance was assessed using accuracy, area under the receiver operating characteristic curve (AUC), precision, and recall. Two-proportion Z-tests were conducted to compare classification accuracies among models. Results The SE-enhanced model achieved the highest classification performance, with an accuracy of 98.4% and an AUC of 1.00, outperforming the base ResNet50V2 (92.6%) and other attention-based frameworks (CBAM: 93.5%, SA: 91.6%, AGNet: 94.2%). Compared to the baseline model, the SE model also demonstrated improved meningioma and pituitary tumor classification (Z = 2.485, p = 0.013 and Z = 2.423, p = 0.015, respectively). Additionally, the SE model demonstrated superior precision and recall across all tumor classes. Conclusion Incorporating attention mechanisms significantly improves MRI-based tumor classification, with SE proving to be the most effective. These findings suggest that SE-enhanced models may improve diagnostic accuracy in both research and clinical applications. Future research should explore hybrid attention mechanisms, such as transformer-based models, and their broader applications in medical imaging.

Background The increasing integration of artificial intelligence (AI) in medical education and clinical practice has led to a growing interest in large language models (LLMs) for diagnostic reasoning and training. LLMs have demonstrated potential in interpreting medical text, summarizing findings, and answering radiology-related questions. However, their ability to accurately analyze both written and image-based content in radiology remains uncertain with newer models. This study evaluates the performance of OpenAI's Chat Generative Pre-trained Transformer 4o (ChatGPT-4o) and Google DeepMind's Gemini Advanced on the 2022 ACR (American College of Radiology) Diagnostic Radiology In-Training (DXIT) Exam to assess their capabilities in different radiological subfields. Methods ChatGPT-4o and Gemini Advanced were tested on 106 multiple-choice questions from the 2022 DXIT exam, which included both image-based and written-based questions spanning various radiological subspecialties. Their performance was compared using overall accuracy, subfield-specific accuracy, and two-proportion z-tests to determine significant differences. Results ChatGPT-4o achieved an overall accuracy of 69.8% (74/106), outperforming Gemini Advanced, which scored 60.4% (64/106), although the difference was not statistically significant (p = 0.151). In image-based questions (n = 64), ChatGPT-4o performed better (57.8%, 37/64) than Gemini Advanced (43.8%, 28/64). For written-based questions (n = 42), ChatGPT-4o and Gemini Advanced demonstrated similar accuracy (88.1% vs. 85.7%). ChatGPT-4o exhibited stronger performance in specific subfields, such as cardiac and nuclear radiology, but neither model showed consistent superiority across all radiology domains. Conclusion LLMs show promise in radiology education and diagnostic reasoning, particularly for text-based assessments. However, limitations such as inconsistent responses and lower accuracy in image interpretation highlight the need for further refinement. Future research should focus on improving AI models' reliability, multimodal capabilities, and integration into radiology training programs.

Hepatocellular carcinoma (HCC) patients have a heightened prevalence of low bone mineral density (BMD) and the development of osteoporosis. Osteoporosis screening guidelines only recommend dual-energy X-ray absorptiometry (DEXA) scans for females 65 and older and males 70 and older. We set out to analyze the incidence of low BMD in HCC patients under 65 years old and encourage implementation of DEXA screenings for this patient population. In this retrospective cohort study, 170 patients under 65 with an HCC diagnosis were analyzed. Hounsfield units (HU) from L1 non-contrast CT scans are a reliable predictor of T-scores from DEXA scans and were used to predict BMD in patients, with scores of less than 165 HU indicative of osteopenia and less than 98 indicative of osteoporosis. The median HU score of patients was 137.2, and the mean score was 142.6 (minimum: 55.4; maximum: 303.1). Of the total 170 patients, 128 (75%) had an HU score of less than 165, indicating a high likelihood of suffering from low BMD. Among low BMD patients, 25 (20%) were identified as within a range of osteoporosis. HCC patients under 65 have an increased incidence of bone demineralization. We suggest that BMD in HCC patients is an important prognostic tool and parameter to document, as studies have shown that HCC patients with high BMD have longer overall survival than patients with low BMD. Future prospective studies using DEXA scans to assess BMD should be completed to verify the risk of osteoporosis.

In 2021, there were 182,520 cases of brain and central nervous system (CNS) cancers in the U.S. and 25,400 new cases of brain cancer in 2024. Early detection via magnetic resonance imaging (MRI) significantly improves patient outcomes. This study fine-tunes a residual neural network 50 version 2 (ResNet50V2), a convolutional neural network (CNN), with squeeze-and-excitation (SE) attention mechanisms to enhance MRI-based tumor classification compared to a base ResNet50V2 model. By incorporating SE blocks, the model improves feature prioritization, effectively distinguishing glioma (n = 901), meningioma (n = 913), pituitary tumor (n = 844), and no tumor (n = 438). Trained on a publicly available Kaggle dataset (N = 3,096), the proposed model achieved a 98.4% classification accuracy and an area under the receiver operating characteristic curve (AUC) of 0.999, outperforming the base model's 92.6% accuracy and 0.987 AUC. Statistically significant improvements were observed in meningioma (p = 0.013) and pituitary tumor (p = 0.015) classification accuracy, highlighting the SE model's superior ability to differentiate tumor types. SE attention mechanisms enhance diagnostic precision by addressing feature extraction limitations and long-range dependencies in medical imaging. However, challenges such as dataset size constraints, overfitting risks, and potential representation bias remain. Future research will focus on expanding dataset diversity, exploring vision transformers (ViTs) for improved feature extraction, and employing generative adversarial networks (GANs) for data augmentation.

Metabolic conditions such as diabetes, and dyslipidemia are prevalent in the United States (US), serving as potential risk factors for hepatocellular carcinoma (HCC). This study aimed to examine the association between various metabolic markers and Hounsfield Units (HU) from L1 vertebral CT scans as indicators of bone mineral density (BMD) in HCC patients under age 65. A cross-sectional analysis was conducted on HCC patients under 65. Correlational and regression analyses were used to assess the association of metabolic markers and other health variables with HU scores. Race and age were significantly associated with HU scores in multivariate analyses, indicating these factors play a crucial role in bone health among HCC patients. Race showed a positive association, and age showed a negative association with HU scores. Fasting blood glucose had a significant negative correlation with BMD, but this relationship was not significant in univariate regression analysis. No significant correlations were found between HU scores and triglycerides, cholesterol, low-density lipoprotein (LDL), high-density lipoprotein (HDL), cholesterol/HDL ratio, LDL/HDL ratio, and hemoglobin A1C (HbA1c) levels. Traditional metabolic markers may not be strong predictors of osteoporosis in this specific population. Further research with larger, more diverse populations and longitudinal data is necessary to understand better the factors contributing to BMD variations in HCC patients.

Background Lung cancer is the leading cause of cancer-related mortality worldwide, with late-stage diagnosis contributing to poor survival rates. Early detection remains a critical challenge, hindered by diagnostic delays, radiologist shortages, and the limitations of current imaging workflows. Recent advances in artificial intelligence (AI), particularly deep learning, offer new avenues to enhance diagnostic accuracy and efficiency in radiology. Objective To develop and evaluate a deep learning model integrating Residual Network 50 Version 2 (ResNet50V2) with Squeeze-and-Excitation (SE) blocks for automated classification of lung cancer subtypes from computed tomography (CT) images. Methods A total of 1,000 anonymized lung CT images were obtained from a publicly available Kaggle dataset, categorized into four classes: adenocarcinoma, large cell carcinoma, squamous cell carcinoma, and normal tissue. The dataset was split into training (70%), validation (10%), and test (20%) sets. A fine-tuned ResNet50V2 architecture with SE blocks was used to enhance channel-wise feature recalibration. The model was trained using categorical cross-entropy loss with label smoothing and optimized via Adam. Performance was evaluated using accuracy, area under the receiver operating characteristic curve (AUC), precision, recall, and F1-score. Results The model achieved a test accuracy of 90.16% and an overall AUC of 0.9815. Class-wise AUCs were high across all categories: 0.9523 for adenocarcinoma, 0.9879 for large cell carcinoma, 0.9977 for normal tissue, and 0.9880 for squamous cell carcinoma. Precision ranged from 0.81 (large cell carcinoma) to 1.00 (normal tissue), while recall ranged from 0.85 (adenocarcinoma) to 0.98 (large cell carcinoma). F1-scores were consistently strong, ranging from 0.88 to 0.96. Conclusion The integration of SE blocks with ResNet50V2 yielded a high-performing model capable of accurately classifying lung cancer subtypes from CT images. The approach shows promise for assisting radiologists in diagnostic decision-making, particularly in settings with limited expert availability. Future work should focus on external validation, model interpretability, and exploration of emerging architectures such as Vision Transformers for enhanced performance and clinical adoption.

Accurate forecasting of emergency department (ED) patient volumes is critical for optimizing hospital resource allocation and staffing. This preliminary study evaluates the performance of an eXtreme Gradient Boosting (XGBoost)-based regression model in predicting daily ED visit counts across three simulated hospitals, using time-series features derived from synthetic hospital data retrieved from a publicly available Kaggle dataset (n=300). For each hospital, we trained an XGBoost model using engineered temporal features, recent lagged values, and rolling averages of past patient volumes. Feature engineering included day of the week, month, week of the year, quarter of the year, and weekend status. Model performance was benchmarked against three general baselines: a naive lag-1 predictor, a constant mean predictor, and a three-day rolling mean. Performance was assessed using mean squared error (MSE), root MSE (RMSE), mean absolute error (MAE), and R² score. The XGBoost model consistently outperformed all baseline methods across all hospitals. For Hospital 101, it achieved an R² of 0.55 compared to 0.27 for the rolling mean and negative R² values for naive and mean baselines. Hospital 102 showed improved accuracy with an R² of 0.69 versus 0.12 for the rolling mean. The best performance was observed at Hospital 103, where XGBoost achieved an R² of 0.81, significantly outperforming all baselines. Across all sites, XGBoost reduced RMSE and MAE by more than 40% relative to the best-performing baseline. Leveraging temporal and historical patterns in simulated ED data, the XGBoost model delivers markedly more accurate volume forecasts than traditional baseline methods. These findings on synthetic data support the potential for machine learning-based forecasting models in enhancing hospital operational decision-making, with future directions involving the use of real-world hospital data.

It is unclear when the synovial-based inflammatory process of gout begins. The aim of this study was to determine the percentage of patients with inter-critical gout who have chronic synovial-based inflammation as evidenced by synovial pannus on a contrast-enhanced magnetic resonance imaging (MRI) of their most involved joint and determine if the presence and/or severity correlates with their serum urate levels. All patients received a 3 T MRI of their index joint, serum urate level, CRP, and creatinine. The primary endpoint was to determine the prevalence of synovial pannus and the correlation of serum urate levels with the presence and/or severity of the synovial pannus on that same joint. MRI erosions, tophi, swelling, effusion, and osteitis were also documented. Seventy-two of 74 subjects (90 % men) completed the protocol. Fifty-three of 72 (74 %) index joints were the first metatarsophalangeal joint. Thirty-nine (54.2 %) of the patients were on urate-lowering therapy; 15 (20.8 %) and 7 (9.7 %) were taking colchicine or a NSAID daily, respectively. Of the 72 subjects, 63 (87.5 %) had synovial pannus on their MRI with good inter-reader agreement between the two radiologists. The mean serum urate level was 7.93 mg/dL. There was no correlation with the presence ( p  = 0.33) or severity ( p  = 0.34) of synovial pannus and serum urate levels. There was also no correlation with the presence or severity of synovial pannus and the secondary endpoints. The majority of patients with inter-critical gout have evidence of chronic synovial-based inflammation. However, the presence and severity of this inflammation do not appear to correlate with serum urate levels.

Micro-plasma transferred arc ( µ PTA) additive manufacturing is one of the newest options for remanufacturing of dies and molds surfaces in the near-millimeter range leading to extended usage of the same. We deployed an automatic micro-plasma deposition setup to deposit a wire of 300  µ m of AISI P20 tool steel on the substrate of same material for the potential application in remanufacturing of the die and mold surface. Our present research effort is to establish µ PTA additive manufacturing as a viable economical and cleaner methodology for potential industrial applications. We undertook the optimization of single weld bead geometry as the first step in our present study. Bead-on-plate trials were conducted to deposit single bead geometry at various processing parameters. The bead geometry (shape and size) and dilution were measured and the parametric dependence was derived. A set of parameters leading to reproducible regular and smooth single bead geometry were identified and used to prepare a thin wall for mechanical testing. The deposits were subjected to material characterization such as microscopic studies, micro-hardness measurements and tensile testing. The process was compared qualitatively with other deposition processes involving high-energy density beams and was found to be advantageous in terms of low initial and running costs with comparable properties. The outcome of the study confirmed the process capability of µ PTA deposition leading to deployment of cost-effective and environmentally friendlier technology for die and mold remanufacturing.

This article investigates the effect of hydrostatic pressure on the optoelectronic characteristics of the InAsNBi/InAs quantum well (QW) system using an expanded version of the standard 8-band k dot p Hamiltonian. The effect of hydrostatic pressure on important structural and electronic parameters such as elastic constants, band gap, band offset, band structure, and effective masses are investigated in this manuscript. These factors assisted in the computation of optical gain spectra for different quantum well structures. Furthermore, this study is extended to several heterostructures by including diverse barrier materials such as GaAs, GaSb, and InP with InAsNBi QW. The optical analysis of these heterostructures can help the researchers to design and fabricate optoelectronic devices that can operate in LWIR regimes owing to the narrow bandgap of quaternary InAsNBi. Additionally, we examined the optical characteristics in TE mode for variations in hydrostatic pressure.