Search Results (38)

Pavement condition assessment using computer vision has emerged as an efficient alternative to traditional manual surveys, which are often labor-intensive and time-consuming. Leveraging deep learning, pavement distress such as cracks can be automatically detected, segmented, and quantified from high-resolution images captured by survey vehicles. Although numerous segmentation models have been proposed to generate crack masks, they typically require extensive pixel-level annotations, leading to high labeling costs. To overcome this limitation, this study integrates the Segmentation Anything Model (SAM), which produces accurate segmentation masks from simple bounding box prompts while leveraging its zero-shot capability to generalize to unseen images with minimal retraining. However, since SAM alone is not an end-to-end solution, we incorporate YOLOv8 for automated crack detection, eliminating the need for manual box annotation. Furthermore, the framework applies local refinement techniques to enhance mask precision and employs Optical Character Recognition (OCR) to automatically extract embedded GPS coordinates for geospatial mapping. The proposed framework is empirically validated using open-source pavement images from Yamanashi, demonstrating effective automated detection, classification, quantification, and geospatial mapping of pavement cracks. The results support automated pavement distress mapping onto real-world road networks, facilitating efficient maintenance planning for road agencies. Full article

Background: Placental thickness has been associated with adverse perinatal outcomes, but the relationship to specific fetal abnormalities seems to not yet be well understood. This study investigates whether increased placental thickness correlates with the severity of fetal cardiac and extracardiac conditions using a structured classification and severity-weighted scoring system. Methods: We undertook a retrospective analysis of 1452 fetal echocardiograms conducted during the third trimester at a tertiary referral institution from the years 2022 to 2025. The diagnoses were categorized into four distinct classifications: congenital heart anomalies, cardiac dysfunctions, extracardiac malformations, and extracardiac dysfunctions. Each diagnostic category was allocated a severity weight predicated on established fetal and neonatal mortality risk literature. The evaluation of placental thickness was regarded not merely as a persistent variable but also categorized into three distinct classifications: thin (≤40 mm), intermediate (41–69 mm), and thick (≥70 mm). The examination of correlations was performed utilizing Spearman’s ρ; comparative evaluations among the groups were conducted employing the Kruskal–Wallis and Mann–Whitney U tests. Results: Placental thickness revealed a moderate positive correlation with weighted extracardiac dysfunctions (ρ = 0.36, p < 0.00001), displayed a comparatively weaker yet statistically significant association with cardiac dysfunctions (ρ = 0.13, p = 0.01). Fetuses identified by increased placental thickness (≥70 mm) exhibited notably higher mean scores for both cardiac and extracardiac dysfunctions. Within the cohort exhibiting thick placentas, 25.8% displayed extracardiac dysfunction scores surpassing 0.3, in contrast to only 7.7% within the cohort with thinner placentas. Conclusions: Augmented placental thickness correlates with an elevated cumulative load of fetal dysfunction, especially in the realms of extracardiac and functional cardiac impairments. The measurement of placental thickness may function as a straightforward, supplementary indicator of fetal distress in the third trimester, particularly when utilized alongside targeted imaging modalities. Full article

This study proposes a deep metric learning-based pavement distress classification method to address critical limitations in conventional approaches, including their dependency on large training datasets and inability to incrementally learn new categories. To resolve high intra-class variance and low inter-class distinction in distress images, we design a CNN head with multi-cluster centroins trained via SoftTriple loss, simultaneously maximizing inter-class separation while establishing multiple intra-class centers. An adaptive weighting strategy combining sample similarity and class priors mitigates data imbalance, while soft-label techniques reduce labeling noise by evaluating similarity against support-set exemplars. Evaluations on the UAV-PDD2023 dataset demonstrate superior performance—3.2% higher macro-recall than supervised learning, and 6.7%/8.5% improvements in macro-F1/weighted-F1 over iCaRL incremental learning—validating the method’s effectiveness for real-world road inspection scenarios with evolving distress types and limited annotation. Full article

Gliomas are incurable, heterogeneous brain tumors, with rare forms often constituting diagnostic and treatment challenges. Molecular diagnostics, mainly implemented through the World Health Organization (WHO) 2021 guidelines, have refined the classification, but highlight difficulties in diagnosing rare gliomas remain. This case series analyzes four patients with rare gliomas treated at the University Hospital, Ulm, between 2002 and 2024. Patients were selected based on unique histopathological features and long-term clinical follow-up. Clinical records, imaging, and histological data were reviewed. Molecular diagnostics followed WHO 2021 guidelines. Quality of life was assessed using standardized tools including the EQ-5D-5L, EQ VAS, the Distress Thermometer, and the Montreal Cognitive Assessment (MoCA). In the first case, a 51-year-old male’s diagnosis evolved from pleomorphic xanthoastrocytoma to a high-grade glioma with pleomorphic and pseudopapillary features, later identified as a neuroepithelial tumor with a PATZ1 fusion over 12 years. Despite multiple recurrences, extensive surgical interventions led to excellent outcomes. The second case involved a young female with long-term survival of astroblastoma, demonstrating significant improvements in both longevity and quality of life through personalized care. The third case involved a patient with oligodendroglioma, later transforming into glioblastoma, emphasizing the importance of continuous diagnostic reevaluation and adaptive treatment strategies, contributing to prolonged survival and quality of life improvements. Remarkably, the patient has achieved over 20 years of survival, including 10 years of being both therapy- and progression-free. The fourth case presents a young woman with neurofibromatosis type 1, initially misdiagnosed with glioblastoma based on histopathological findings. Subsequent molecular diagnostics revealed a subependymal giant cell astrocytoma-like astrocytoma, highlighting the critical role of early advanced diagnostic techniques. These cases underscore the importance of precise molecular diagnostics, individualized treatments, and ongoing diagnostic reevaluation to optimize outcomes. They also address the psychological impact of evolving diagnoses, stressing the need for comprehensive patient support. Even in complex cases, extensive surgical interventions can yield favorable results, reinforcing the value of adaptive, multidisciplinary strategies based on evolving tumor characteristics. Full article

Accurate segmentation of pavement cracks from high-resolution remote sensing imagery plays a crucial role in automated road condition assessment and infrastructure maintenance. However, crack structures often exhibit asymmetry, irregular morphology, and multi-scale variations, posing significant challenges to conventional CNN-based methods in real-world environments. Specifically, the proposed ETAFHrNet focuses on two predominant pavement-distress morphologies—linear cracks (transverse and longitudinal) and alligator cracks—and has been empirically validated on their intersections and branching patterns over both asphalt and concrete road surfaces. In this work, we present ETAFHrNet, a novel attention-guided segmentation network designed to address the limitations of traditional architectures in detecting fine-grained and asymmetric patterns. ETAFHrNet integrates Transformer-based global attention and multi-scale hybrid feature fusion, enhancing both contextual perception and detail sensitivity. The network introduces two key modules: the Efficient Hybrid Attention Transformer (EHAT), which captures long-range dependencies, and the Cross-Scale Hybrid Attention Module (CSHAM), which adaptively fuses features across spatial resolutions. To support model training and benchmarking, we also propose QD-Crack, a high-resolution, pixel-level annotated dataset collected from real-world road inspection scenarios. Experimental results show that ETAFHrNet significantly outperforms existing methods—including U-Net, DeepLabv3+, and HRNet—in both segmentation accuracy and generalization ability. These findings demonstrate the effectiveness of interpretable, multi-scale attention architectures in complex object detection and image classification tasks, making our approach relevant for broader applications, such as autonomous driving, remote sensing, and smart infrastructure systems. Full article

Perineal injuries are a common complication of vaginal delivery, affecting 75–85% of women. This review examines current knowledge on risk factors, classification, treatment, and quality of life impacts. Risk factors are divided into maternal, foetal, and labour-related categories. Treatment depends on injury severity. First-degree tears can be managed conservatively, with skin glue or suturing—preferably with synthetic absorbable sutures to reduce pain and infection risk. Second-degree tears and episiotomies respond best to continuous non-locking sutures, improving healing, and minimizing postpartum pain. Severe third- and fourth-degree tears require specialised surgical techniques, such as the overlay method for anal sphincter repair, which improves faecal continence. Proper preoperative care, including antibiotics and anaesthesia, enhances outcomes. Episiotomy is controversial; selective use based on clinical indications is recommended over routine practice. Research shows no significant long-term benefits compared to spontaneous tears, and links episiotomy to psychological distress and negative body image. Preventative strategies, like perineal massage and warm compresses during labour, may reduce the risk of severe trauma, particularly in first-time mothers. Perineal trauma can have lasting physical and psychological effects, impacting sexual function, continence, and mental health. Proper diagnosis, treatment, and postpartum care are essential. Future studies should aim to standardise care protocols and explore long-term outcomes to enhance patient quality of life. Full article

Roads are critical infrastructure in multi-sectoral development. Any country that aims to expand and stabilize its activities must have a network of paved roads in good condition. However, that is not the case in many countries. The usual methods of recording and classifying pavement distress on the roads require a lot of equipment, technicians, and time to obtain the nature and indices of the damage to estimate the roadway’s quality level. This study proposes the use of pavement distress detection and classification models based on Convolutional Neural Networks, starting from videos taken of any asphalt road. To carry out this work, various routes were filmed to list the degradations concerned. Images were extracted from these videos and then resized and annotated. Then, these images were used to constitute several databases of road damage, such as longitudinal cracks, alligator cracks, small potholes, and patching. Within an appropriate development environment, three Convolutional Neural Networks were developed and trained on the databases. The accuracy achieved by the different models varies from 94.6% to 97.3%. This accuracy is promising compared to the literature models. This method would make it possible to considerably reduce the financial resources used for each road data campaign. Full article

Sepsis is a systemic inflammatory response syndrome of suspected or confirmed infectious origin, which frequently culminates in multiorgan failure, including cardiac involvement. Septic cardiomyopathy (SCM) remains a poorly defined clinical entity, lacking a formal or consensus definition and representing a significant knowledge gap in critical care medicine. It is an often-underdiagnosed complication of sepsis. The only widely accepted aspect of its definition is that SCM is a transient myocardial dysfunction occurring in patients with sepsis, which cannot be attributed to ischemia or pre-existing cardiac disease. The pathogenesis of SCM appears to be multifactorial, involving inflammatory cytokines, overproduction of nitric oxide, mitochondrial dysfunction, calcium homeostasis dysregulation, autonomic imbalance, and myocardial edema. Diagnosis primarily relies on echocardiography, with advanced tools such as tissue Doppler imaging (TDI) and global longitudinal strain (GLS) providing greater sensitivity for detecting subclinical dysfunction and guiding therapeutic decisions. Traditional echocardiographic findings, such as left ventricular ejection fraction measured by 2D echocardiography, often reflect systemic vasoplegia rather than intrinsic myocardial dysfunction, complicating accurate diagnosis. Right ventricular (RV) dysfunction, identified as a critical component of SCM in many studies, has multifactorial pathophysiology. Factors including septic cardiomyopathy itself, mechanical ventilation, hypoxemia, and hypercapnia—particularly in cases complicated by acute respiratory distress syndrome (ARDS)—increase RV afterload and exacerbate RV dysfunction. The prognostic value of cardiac biomarkers, such as troponins and natriuretic peptides, remains uncertain, as these markers primarily reflect illness severity rather than being specific to SCM. Treatment focuses on the early recognition of sepsis, hemodynamic optimization, and etiological interventions, as no targeted therapies currently exist. Emerging therapies, such as levosimendan and VA-ECMO, show potential in severe SCM cases, though further validation is needed. The lack of standardized diagnostic criteria, combined with the heterogeneity of sepsis presentations, poses significant challenges to the effective management of SCM. Future research should focus on developing cluster-based classification systems for septic shock patients by integrating biomarkers, echocardiographic findings, and clinical parameters. These advancements could clarify the underlying pathophysiology and enable tailored therapeutic strategies to improve outcomes for SCM patients. Full article

In the rapid development of urbanization, the sustained and healthy development of transportation infrastructure has become a widely discussed topic. The inspection and maintenance of asphalt pavements not only concern road safety and efficiency but also directly impact the rational allocation of resources and environmental sustainability. To address the challenges of modern transportation infrastructure management, this study innovatively proposes a hybrid learning model that integrates deep convolutional neural networks (DCNNs) and support vector machines (SVMs). Specifically, the model initially employs a ShuffleNet architecture to autonomously extract abstract features from various defect categories. Subsequently, the Maximum Relevance Minimum Redundancy (MRMR) method is utilized to select the top 25% of features with the highest relevance and minimal redundancy. After that, SVMs equipped with diverse kernel functions are deployed to perform training and prediction based on the selected features. The experimental results reveal that the model attains a high classification accuracy of 94.62% on a self-constructed asphalt pavement image dataset. This technology not only significantly improves the accuracy and efficiency of pavement inspection but also effectively reduces traffic congestion and incremental carbon emissions caused by pavement distress, thereby alleviating environmental burdens. It is of great significance for enhancing pavement maintenance efficiency, conserving resource consumption, mitigating environmental pollution, and promoting sustainable socio-economic development. Full article

Background: The aim of this review is to highlight the new advance of predictive and explainable artificial intelligence for neuroimaging applications. Methods: Data came from 30 original studies in PubMed with the following search terms: “neuroimaging” (title) together with “machine learning” (title) or ”deep learning” (title). The 30 original studies were eligible according to the following criteria: the participants with the dependent variable of brain image or associated disease; the interventions/comparisons of artificial intelligence; the outcomes of accuracy, the area under the curve (AUC), and/or variable importance; the publication year of 2019 or later; and the publication language of English. Results: The performance outcomes reported were within 58–96 for accuracy (%), 66–97 for sensitivity (%), 76–98 for specificity (%), and 70–98 for the AUC (%). The support vector machine and the convolutional neural network registered the best performance (AUC 98%) for the classifications of low- vs. high-grade glioma and brain conditions, respectively. Likewise, the random forest delivered the best performance (root mean square error 1) for the regression of brain conditions. The following factors were discovered to be major predictors of brain image or associated disease: (demographic) age, education, sex; (health-related) alpha desynchronization, Alzheimer’s disease stage, CD4, depression, distress, mild behavioral impairment, RNA sequencing; (neuroimaging) abnormal amyloid-β, amplitude of low-frequency fluctuation, cortical thickness, functional connectivity, fractal dimension measure, gray matter volume, left amygdala activity, left hippocampal volume, plasma neurofilament light, right cerebellum, regional homogeneity, right middle occipital gyrus, surface area, sub-cortical volume. Conclusion: Predictive and explainable artificial intelligence provide an effective, non-invasive decision support system for neuroimaging applications. Full article

In this study, the extent of concrete building distress is used to determine whether a building needs to be demolished and maintained, and the study focuses on accurately identifying target distress in different complex contexts and accurately distinguishing between their categories. To solve the problem of insufficient feature extraction of small targets in bridge disease images under complex backgrounds and noise, we propose the YOLOv8 Dynamic Plus model. First, we enhanced attention on multi-scale disease features by implementing structural reparameterization with parallel small-kernel expansion convolution. Next, we reconstructed the relationship between localization and classification tasks in the detection head and implemented dynamic selection of interactive features using a feature extractor to improve the accuracy of classification and recognition. Finally, to address problems of missed detection, such as inadequate extraction of small targets, we extended the original YOLOv8 architecture by adding a layer in the feature extraction phase dedicated to small-target detection. This modification integrated the neck part more effectively with the shallow features of the original three-layer YOLOv8 feature extraction stage. The improved YOLOv8 Dynamic Plus model demonstrated a 7.4 percentage-point increase in performance compared to the original model, validating the feasibility of our approach and enhancing its capability for building disease detection. In practice, this improvement has led to more accurate maintenance and safety assessments of concrete buildings and earlier detection of potential structural problems, resulting in lower maintenance costs and longer building life. This not only improves the safety of buildings but also brings significant economic benefits and social value to the industries involved. Full article

Alopecia is a common adverse effect of neoadjuvant or adjuvant chemotherapy in patients with early breast cancer. While hair typically regrows over time, more than 40% of patients continue to suffer from permanent partial alopecia, significantly affecting body image, psychological well-being, and quality of life. This concern is a recognized reason why some breast cancer patients decline life-saving chemotherapy. It is critical for healthcare professionals to consider the impact of this distressing side effect and adopt supportive measures to mitigate it. Among the various strategies investigated to reduce chemotherapy-induced alopecia (CIA), scalp cooling has emerged as the most effective. This article reviews the pathophysiology of CIA and examines the efficacy of different scalp cooling methods. Scalp cooling has been shown to reduce the incidence of CIA, defined as less than 50% hair loss, by 50% in patients receiving chemotherapy. It is associated with high patient satisfaction and does not significantly increase the risk of scalp metastasis or compromise overall survival. Promising new scalp cooling technologies, such as cryogenic nitrogen oxide cryotherapy, offer the potential to achieve and maintain lower scalp temperatures, potentially enhancing therapeutic effects. Further investigation into these approaches is warranted. Research on CIA is hindered by significant heterogeneity and the lack of standardised methods for assessing hair loss. To advance the field, further interdisciplinary research is crucial to develop preclinical models of CIA, establish a uniform, internationally accepted and standardised classification system, and establish an objective, personalised prognosis monitoring system. Full article

Many automatic classification methods published can identify the main hidden distress types of highways, but they cannot meet the precise needs of operation and maintenance. The classification of interlayer distresses based on ground penetrating radar (GPR) images is very important to improve maintenance efficiency and reduce cost. However, among models of different complexities, which models are suitable for the interlayer distress data needs further verification. Firstly, to cover enough of the variable range of distress samples, the interlayer distress dataset collected containing 32,038 samples was subcategorized into three types: interlayer debonding, interlayer water seepage, and interlayer loosening. Secondly, residual networks (ResNets) that render easier to build shallower or deeper networks (ResNet-4, ResNet-6, ResNet-8, ResNet-10, ResNet-14, ResNet-18, ResNet-34, and ResNet-50) and five classical network models (DenseNet-121, EfficientNet B0, SqueezeNet1_0, MobileNet V2, and VGG-19) were evaluated by training and validation loss, test accuracy, and model complexity. The experimental results show that all models have high test accuracy with little difference, but ResNet-4, ResNet-6, SqueezeNet1_0, and ResNet-8 exhibit no overfitting which means they have good generalization performance. Full article

Interstitial lung disease (ILD) comprises a group of respiratory diseases affecting the interstitium of the lungs, which occur when a lung injury triggers an abnormal healing response, and an inflammatory process leads to altered diffusion and restrictive respiratory dysfunction. The term “interstitial” may be misleading, as other components of the lungs are usually also involved (epithelium, airways, endothelium, and so on). Pediatric conditions (childhood interstitial lung disease, chILD) are different from adult forms, as growing and developing lungs are affected and more diverse and less prevalent diseases are seen in childhood. Diffuse parenchymal lung disease (DPLD) and diffuse lung disease (DLD) can be used interchangeably with ILD. Known etiologies of chILD include chronic infections, bronchopulmonary dysplasia, aspiration, genetic mutations leading to surfactant dysfunction, and hypersensitivity pneumonitis due to drugs or environmental exposures. Many forms are seen in disorders with pulmonary involvement (connective tissue disorders, storage diseases, malignancies, and so on), but several conditions have unknown origins (desquamative pneumonitis, pulmonary interstitial glycogenosis, neuroendocrine cell hyperplasia in infancy, and so on). Currently, there is no consensus on pediatric classification; however, age grouping is proposed as some specific forms are more prevalent in infancy (developmental and growth abnormalities, surfactant dysfunction mutations, etc.) and others are usually seen in older cohorts (disorders in normal or immunocompromised hosts, systemic diseases, etc.). Clinical manifestations vary from mild nonspecific symptoms (recurrent respiratory infections, exercise intolerance, failure to thrive, dry cough, etc.) to a severe clinical picture (respiratory distress) and presentation related to the child’s age. The diagnostic approach relies on imaging techniques (CT), but further investigations including genetic tests, BAL, and lung biopsy (VATS) are needed in uncertain cases. Pharmacological treatment is mostly empiric and based on anti-inflammatory and immunomodulatory drugs. Lung transplantation for selected cases in a pediatric transplantation center could be an option; however, limited data and evidence are available regarding long-term survival. International collaboration is warranted to understand chILD entities better and improve the outcomes of these patients. Full article

Despite the considerable advancements in automated identification methods of highway hidden distress with ground-penetrating radar (GPR) images, there still exist challenges in realizing automated identification of highway hidden distress owing to the quantity, variability, and reliability of the distress samples and diversity of classification models. Firstly, the dataset collected contains 31,640 samples categorized into four categories: interlayer debonding, interlayer loosening, interlayer water seepage, and structural loosening from 1500 km highway, for obtaining larger enough samples and covering the variable range of distress samples. Secondly, the distresses were labeled by experienced experts, and the labels were verified with drilled cores to ensure their reliability. Lastly, 18 exemplary convolutional neural network (CNN) models from 8 different architectures were evaluated using evaluation metrics such as precision, recall, and f1-score. Further, confusion matrix and Grad-CAM techniques were utilized to analyze these models. The experimental results show that VGG13 performed most prominently and stably, while the lightweight network SqueezeNet1_1 performed particularly well with a batch size of 64. Furthermore, this study indicates that models with fewer layers can achieve comparable or better performance than deeper models. Full article