Search Results (1,518)

Teledermatology relies on digital transfer of dermatological images, but compression and resolution differences compromise diagnostic quality. Image enhancement techniques are crucial to compensate for these differences and improve quality for both clinical assessment and AI-based analysis. We developed a customized image degradation pipeline simulating common artifacts in dermatological images, including blur, noise, downsampling, and compression. This synthetic degradation approach enabled effective training of DermaSR-GAN, a super-resolution generative adversarial network tailored for dermoscopic images. The model was trained on 30,000 high-quality ISIC images and evaluated on three independent datasets (ISIC Test, Novara Dermoscopic, PH²) using structural similarity and no-reference quality metrics. DermaSR-GAN achieved statistically significant improvements in quality scores across all datasets, with up to 23% enhancement in perceptual quality metrics (MANIQA). The model preserved diagnostic details while doubling resolution and surpassed existing approaches, including traditional interpolation methods and state-of-the-art deep learning techniques. Integration with downstream classification systems demonstrated up to 14.6% improvement in class-specific accuracy for keratosis-like lesions compared to original images. Synthetic degradation represents a promising approach for training effective super-resolution models in medical imaging, with significant potential for enhancing teledermatology applications and computer-aided diagnosis systems. Full article

Accurately predicting the compressive strength of high-performance concrete (HPC) is critical for ensuring structural integrity and promoting sustainable construction practices. However, HPC exhibits highly complex, nonlinear, and multi-factorial interactions among its constituents (such as cement, aggregates, admixtures, and curing conditions), which pose significant challenges to conventional predictive models. Traditional approaches often fail to adequately capture these intricate relationships, resulting in limited prediction accuracy and poor generalization. Moreover, the high dimensionality and noisy nature of HPC mix data increase the risk of model overfitting and convergence to local optima during optimization. To address these challenges, this study proposes a novel bio-inspired hybrid optimization model, AP-IVYPSO-BP, which is specifically designed to handle the nonlinear and complex nature of HPC strength prediction. The model integrates the ivy algorithm (IVYA) with particle swarm optimization (PSO) and incorporates an adaptive probability strategy based on fitness improvement to dynamically balance global exploration and local exploitation. This design effectively mitigates common issues such as premature convergence, slow convergence speed, and weak robustness in traditional metaheuristic algorithms when applied to complex engineering data. The AP-IVYPSO is employed to optimize the weights and biases of a backpropagation neural network (BPNN), thereby enhancing its predictive accuracy and robustness. The model was trained and validated on a dataset comprising 1,030 HPC mix samples. Experimental results show that AP-IVYPSO-BP significantly outperforms traditional BPNN, PSO-BP, GA-BP, and IVY-BP models across multiple evaluation metrics. Specifically, it achieved an R² of 0.9542, MAE of 3.0404, and RMSE of 3.7991 on the test set, demonstrating its high accuracy and reliability. These results confirm the potential of the proposed bio-inspired model in the prediction and optimization of concrete strength, offering practical value in civil engineering and materials design. Full article

Background/Objectives: Diffuse Large B-Cell Lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma and demands precise segmentation and classification of nuclei for effective diagnosis and disease severity assessment. This study aims to evaluate the performance of HoVerNet, a deep learning model, for nuclei segmentation and classification in CMYC-stained whole slide images and to assess its integration into a user-friendly diagnostic tool. Methods: A dataset of 122 CMYC-stained whole slide images (WSIs) was used. Pre-processing steps, including stain normalization and patch extraction, were applied to improve input consistency. HoVerNet, a multi-branch neural network, was used for both nuclei segmentation and classification, particularly focusing on its ability to manage overlapping nuclei and complex morphological variations. Model performance was validated using metrics such as accuracy, precision, recall, and F1 score. Additionally, a graphic user interface (GUI) was developed to incorporate automated segmentation, cell counting, and severity assessment functionalities. Results: HoVerNet achieved a validation accuracy of 82.5%, with a precision of 85.3%, recall of 82.6%, and an F1 score of 83.9%. The model showed powerful performance in differentiating overlapping and morphologically complex nuclei. The developed GUI enabled real-time visualization and diagnostic support, enhancing the efficiency and usability of DLBCL histopathological analysis. Conclusions: HoVerNet, combined with an integrated GUI, presents a promising approach for streamlining DLBCL diagnostics through accurate segmentation and real-time visualization. Future work will focus on incorporating Vision Transformers and additional staining protocols to improve generalizability and clinical utility. Full article

Streaming data is becoming more and more common in the field of big data and incremental frameworks can address its complexity. The BDFCOM algorithm achieves good results on common form datasets by introducing the ordering mechanism of beta distribution weighting. In this paper, based on the BDFCOM algorithm, two incremental beta distribution weighted fuzzy C-ordered means clustering algorithms, SPBDFCOM and OBDFCOM, are proposed by combining the two incremental frameworks of Single-Pass and Online, respectively. In order to validate the performance of SPBDFCOM and OBDFCOM, this paper selects seven real datasets for experiments and compares their performance with six other incremental clustering algorithms using six evaluation metrics. The results show that the two proposed incremental algorithms perform significantly better compared to other algorithms. Full article

Accurate above-ground biomass (AGB) quantification is confounded by signal saturation and data fusion challenges, particularly in structurally complex ecosystems like bamboo forests. To address these gaps, this study developed a two-stage framework to map the AGB of Dendrocalamus giganteus in a subtropical mountain environment. This study first employed Empirical Bayesian Kriging Regression Prediction (EBKRP) to spatialize sparse GEDI and ICESat-2 LiDAR metrics using Sentinel-2 and topographic covariates. Subsequently, a stacked ensemble model, integrating four machine learning algorithms, predicted AGB from the full suite of continuous variables. The stacking model achieved high predictive accuracy (R² = 0.84, RMSE = 11.07 Mg ha⁻¹) and substantially mitigated the common bias of underestimating high AGB, improving the predicted observed regression slope from a base model average of 0.63 to 0.81. Furthermore, SHAP analysis provided mechanistic insights, identifying the canopy photon rate as the dominant predictor and quantifying the ecological thresholds governing AGB distribution. The mean AGB density was 71.8 ± 21.9 Mg ha⁻¹, with its spatial pattern influenced by elevation and human settlements. This research provides a robust framework for synergizing multi-source remote sensing data to improve AGB estimation, offering a refined methodological pathway for large-scale carbon stock assessments. Full article

Background: Pancreatic cystic lesions (PCLs), including intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), pose a diagnostic challenge due to their variable malignant potential. Current guidelines, such as Fukuoka and American Gastroenterological Association (AGA), have moderate predictive accuracy and may lead to overtreatment or missed malignancies. Artificial intelligence (AI), incorporating machine learning (ML) and deep learning (DL), offers the potential to improve risk stratification, diagnosis, and management of PCLs by integrating clinical, radiological, and molecular data. This is the first systematic review to evaluate the application, performance, and clinical utility of AI models in the diagnosis, classification, prognosis, and management of pancreatic cysts. Methods: A systematic review was conducted in accordance with PRISMA guidelines and registered on PROSPERO (CRD420251008593). Databases searched included PubMed, EMBASE, Scopus, and Cochrane Library up to March 2025. The inclusion criteria encompassed original studies employing AI, ML, or DL in human subjects with pancreatic cysts, evaluating diagnostic, classification, or prognostic outcomes. Data were extracted on the study design, imaging modality, model type, sample size, performance metrics (accuracy, sensitivity, specificity, and area under the curve (AUC)), and validation methods. Study quality and bias were assessed using the PROBAST and adherence to TRIPOD reporting guidelines. Results: From 847 records, 31 studies met the inclusion criteria. Most were retrospective observational (n = 27, 87%) and focused on preoperative diagnostic applications (n = 30, 97%), with only one addressing prognosis. Imaging modalities included Computed Tomography (CT) (48%), endoscopic ultrasound (EUS) (26%), and Magnetic Resonance Imaging (MRI) (9.7%). Neural networks, particularly convolutional neural networks (CNNs), were the most common AI models (n = 16), followed by logistic regression (n = 4) and support vector machines (n = 3). The median reported AUC across studies was 0.912, with 55% of models achieving AUC ≥ 0.80. The models outperformed clinicians or existing guidelines in 11 studies. IPMN stratification and subtype classification were common focuses, with CNN-based EUS models achieving accuracies of up to 99.6%. Only 10 studies (32%) performed external validation. The risk of bias was high in 93.5% of studies, and TRIPOD adherence averaged 48%. Conclusions: AI demonstrates strong potential in improving the diagnosis and risk stratification of pancreatic cysts, with several models outperforming current clinical guidelines and human readers. However, widespread clinical adoption is hindered by high risk of bias, lack of external validation, and limited interpretability of complex models. Future work should prioritise multicentre prospective studies, standardised model reporting, and development of interpretable, externally validated tools to support clinical integration. Full article

Background/Objectives: To evaluate the importance of image processing in a previously validated model for detecting pancreatic neuroendocrine tumors (PanNETs) and to introduce Image2Radiomics, a new framework that ensures reproducibility of the image processing pipeline and facilitates the deployment of radiomics models. Methods: A previously validated model for identifying PanNETs from CT images served as the reference. Radiomics features were re-extracted using Image2Radiomics and compared to those from the original model using performance metrics. The impact of nine alterations to the image processing pipeline was evaluated. Prediction discrepancies were quantified using the mean ± SD of absolute differences in PanNET probability and the percentage of classification disagreement. Results: The reference model was successfully replicated with Image2Radiomics, achieving a Cohen’s kappa coefficient of 1. Alterations to the image processing pipeline led to reductions in model performance, with AUC dropping from 0.87 to 0.71 when image windowing was removed. Prediction disagreements were observed in up to 45% of patients. Even minor changes, such as switching the library used for spatial resampling, resulted in up to 21% disagreement. Conclusions: Reproducing image processing pipelines remains challenging and limits the clinical deployment of radiomics models. While this study is limited to one model and imaging modality, the findings underscore a common risk in radiomics reproducibility. The Image2Radiomics framework addresses this issue by allowing researchers to define and share complete processing pipelines in a standardized way, improving reproducibility and facilitating model deployment in clinical and multicenter settings. Full article

In this narrative review, we explore the role of artificial intelligence (AI) in managing lumbar degenerative conditions, a topic that has recently garnered significant interest. The use of AI-based solutions in spine surgery is particularly appealing due to its potential applications in preoperative planning and outcome prediction. This study aims to clarify the impact of artificial intelligence models on the diagnosis and prognosis of common types of degenerative conditions: lumbar disc herniation, spinal stenosis, and eventually spinal fusion. Additionally, the study seeks to identify predictive factors for lumbar fusion surgery based on a review of the literature from the past 10 years. From the literature search, 96 articles were examined. The literature on this topic appears to be consistent, describing various models that show promising results, particularly in predicting outcomes. However, most studies adopt a retrospective approach and often lack detailed information about imaging features, intraoperative findings, and postoperative functional metrics. Additionally, the predictive performance of these models varies significantly, and few studies include external validation. The application of artificial intelligence in treating degenerative spine conditions, while valid and promising, is still in a developmental phase. However, over the last decade, there has been an exponential growth in studies related to this subject, which is beginning to pave the way for its systematic use in clinical practice. Full article

Background/Objectives: Conventional blood collection can be challenging in a non-clinical or home-based setting. In response, vacuum-assisted lancing devices for capillary blood collection (typically from the upper arm) have gained popularity to broaden access to diagnostic testing. However, these devices are often costly relative to the reimbursement rate for common laboratory testing panels. This study describes the design and evaluation of Comfort Draw™, a simplified and economical vacuum-assisted capillary blood collection device. Methods: Comfort Draw™ was evaluated by 12 participants in a preliminary study and by 42 participants in a follow-up study. Metrics assessed included the following: vacuum pressure of the device, skin temperature generated by the Comfort Draw prep warmer, blood collection volume, and analytical accuracy (for 19 common serum-based analytes). Results: Acceptable blood volume (>400 µL) and serum volume (>100 µL) were collected by Comfort Draw in 85.5% and 95.1% of cases, respectively. Seventeen of the nineteen analytes examined were within CLIA acceptance limits compared to matched venous samples. Self-reported pain scores associated with Comfort Draw collection averaged 0.39 on a scale from 0 to 10. Conclusions: In this preliminary clinical study, Comfort Draw was found to be a valid and relatively painless method for collecting capillary blood specimens. The device’s simple design and lower cost could enable broader applications compared to more complex alternative capillary blood collection devices. Full article

For effective groundwater resource management, it is essential to model the dynamic behaviour of aquifers in response to rainfall. Here, a methodological approach using a recurrent neural network, specifically a Long Short-Term Memory (LSTM) network, is used to model groundwater levels of the shallow porous aquifer in Southern Italy. This aquifer is recharged by local rainfall, which exhibits minimal variation across the catchment in terms of volume and temporal distribution. To gain a deeper understanding of the complex interactions between precipitation and groundwater levels within the aquifer, we used water level data from six wells. Although these wells were not directly correlated in terms of individual measurements, they were geographically located within the same shallow aquifer and exhibited a similar hydrogeological response. The trained model uses two variables, rainfall and groundwater levels, which are usually easily available. This approach allowed the model, during the training phase, to capture the general relationships and common dynamics present across the different time series of wells. This methodology was employed despite the geographical distinctions between the wells within the aquifer and the variable duration of their observed time series (ranging from 27 to 45 years). The results obtained were significant: the global model, trained with the simultaneous integration of data from all six wells, not only led to superior performance metrics but also highlighted its remarkable generalization capability in representing the hydrogeological system. Full article

Diffuse axonal brain injury (DAI) is a common, debilitating consequence of traumatic brain injury, yet its detection and severity grading remain challenging in clinical and experimental settings. This study evaluated the sensitivity of diffusion tensor imaging (DTI), histology, and neurological severity scoring (NSS) in assessing injury severity in a rat model of isolated DAI. A rotational injury model induced mild, moderate, or severe DAI in male and female rats. Neurological deficits were assessed 48 h after injury via NSS. Magnetic resonance imaging, including DTI metrics, such as fractional anisotropy (FA), relative anisotropy (RA), axial diffusivity (AD), mean diffusivity (MD), and radial diffusivity (RD), was performed prior to tissue collection. Histological analysis used beta amyloid precursor protein immunohistochemistry. Sensitivity and variability of each method were compared across brain regions and the whole brain. Histology was the most sensitive method, requiring very small groups to detect differences. Anisotropy-based MRI metrics, especially whole-brain FA and RA, showed strong correlations with histology and NSS and demonstrated high sensitivity with low variability. NSS identified injury but required larger group sizes. Diffusivity-based MRI metrics, particularly RD, were less sensitive and more variable. Whole-brain FA and RA were the most sensitive MRI measures of DAI severity and were comparable to histology in moderate and severe groups. These findings support combining NSS and anisotropy-based DTI for non-terminal DAI assessment in preclinical studies. Full article

Cold-water immersion (CWI), as a common recovery method, has been widely used in the field of post-exercise fatigue recovery. However, there is still a lack of comprehensive and systematic scientific evaluation of the combined effects of cold-water immersion combined with other therapies (CWI + Other). The aim of this study was to compare the effects of CWI and CWI + Other in post-exercise fatigue recovery and to explore the potential benefits of CWI + Other. We systematically searched PubMed, Embase, Web of Science, Cochrane Library and EBSCO databases to include 24 studies (475 subjects in total) and performed a meta-analysis using standardized mean difference (SMD) and 95% confidence intervals (CIs). The results showed that both CWI + Other (SMD = −0.68, 95% CI: −1.03 to −0.33) and CWI (SMD = −0.37, 95% CI: −0.65 to −0.10) were effective in reducing delayed-onset muscle soreness (DOMS). In subgroup analyses of athletes, both CWI + Other (SMD = −1.13, 95% CI: −1.76 to −0.49) and CWI (SMD = −0.47, 95% CI: −0.87 to −0.08) also demonstrated significant effects. In addition, CWI + Other significantly reduced post-exercise C-reactive protein (CRP) levels (SMD = −0.62, 95% CI: −1.12 to −0.13), and CWI with water temperatures higher than 10 °C also showed a CRP-lowering effect (MD = −0.18, 95% CI: −0.30 to −0.07), suggesting a potential benefit in anti-inflammation. There were no significant differences between the two interventions in the metrics of creatine kinase (CK; CWI: SMD = −0.01, 95% CI: −0.27 to 0.24; CWI + Other: SMD = 0.26, 95% CI: −0.51 to 1.03) or countermovement jump (CMJ; CWI: SMD = 0.22, 95% CI: −0.13 to 0.57; CWI + Other: SMD = 0.07, 95% CI: −0.70 to 0.85). Full article

Intermittent claudication is the most common manifestation of peripheral arterial disease as well as a lifestyle-limiting disease with a favorable prognosis. Despite societal guideline recommendations, most claudicants do not trial optimal medical therapy (OMT) and supervised exercise therapy (SET) or receive a quality-of-life (QoL) assessment prior to intervention. In this review, we discuss the components of OMT and SET and the trials establishing their clear benefits in claudicants. We assess adherence rates to OMT/SET and qualitative and quantitative studies attempting to understand the barriers to adoption. We also review how patient-reported outcome metrics were developed to assess QoL in claudicants and reasons for their underutilization in daily clinical practice. Last, we describe novel initiatives seeking to improve adherence to OMT, SET, and QoL assessment. Full article

The dramatic increase in urban construction waste poses severe environmental challenges. Utilizing waste concrete to produce recycled aggregates (RA) for manufacturing recycled concrete (RC) represents an effective strategy for resource utilization. However, inherent defects in RA, such as high porosity, microcracks, and adherent old mortar layers, lead to significant performance degradation of the resulting RC, limiting its widespread application. Traditional methods for enhancing RA often suffer from limitations, including high energy consumption, increased costs, or the introduction of new pollutants. MICP offers an innovative approach for enhancing RC performance. This technique employs the metabolic activity of specific microorganisms to induce the formation of a three-dimensionally interwoven calcium carbonate gel network within the pores and on the surface of RA. This gel network can improve the inherent defects of RA, thereby enhancing the performance of RC. Compared to conventional techniques, this approach demonstrates significant environmental benefits and enhances concrete compressive strength by 5–30%. Furthermore, embedding mineralizing microbial spores within the pores of RA enables the production of self-healing RC. This review systematically explores recent research advances in microbial mineral gel network for improving RC performance. It begins by delineating the fundamental mechanisms underlying microbial mineralization, detailing the key biochemical reactions driving the formation of calcium carbonate (CaCO₃) gel, and introducing the common types of microorganisms involved. Subsequently, it critically discusses the key environmental factors influencing the effectiveness of MICP treatment on RA and strategies for their optimization. The analysis focuses on the enhancement of critical mechanical properties of RC achieved through MICP treatment, elucidating the underlying strengthening mechanisms at the microscale. Furthermore, the review synthesizes findings on the self-healing efficiency of MICP-based RC, including such metrics as crack width healing ratio, permeability recovery, and restoration of mechanical properties. Key factors influencing self-healing effectiveness are also discussed. Finally, building upon the current research landscape, the review provides perspectives on future research directions for advancing microbial mineralization gel techniques to enhance RC performance, offering a theoretical reference for translating this technology into practical engineering applications. Full article

More than 14% of the world’s population suffered from diabetes mellitus in 2022. This metabolic condition is defined by increased blood glucose concentrations. Among the different types of diabetes, type 1 diabetes, caused by a lack of insulin secretion, is particularly challenging to treat. In this regard, automatic glucose level estimation implements Continuous Glucose Monitoring (CGM) devices, showing positive therapeutic outcomes. AI-based glucose prediction has commonly followed a deterministic approach, usually with a lack of interpretability. Therefore, these AI-based methods do not provide enough information in critical decision-making scenarios, like in the medical field. This work intends to provide accurate, interpretable, and personalized glucose prediction using the Temporal Fusion Transformer (TFT), and also includes an uncertainty estimation. The TFT was trained using two databases, an in-house-collected dataset and the OhioT1DM dataset, commonly used for glucose forecasting benchmarking. For both datasets, the set of input features to train the model was varied to assess their impact on model interpretability and prediction performance. Models were evaluated using common prediction metrics, diabetes-specific metrics, uncertainty estimation, and interpretability of the model, including feature importance and attention. The obtained results showed that TFT outperforms existing methods in terms of RMSE by at least 13% for both datasets. Full article