Search Results (1,304)

This paper aims to leverage artificial intelligence (AI) to assist physicians in utilizing advanced deep learning techniques integrated into developed models within electronic health records (EHRs) in medical information systems (MISes), which have been in use for over 15 years in health centers across the Republic of Serbia. This paper presents a human-centered AI approach that emphasizes physician decision-making supported by AI models. This study presents two developed and implemented deep neural network (DNN) models in the EHR. Both models were based on data that were collected during the COVID-19 outbreak. The models were evaluated using five-fold cross-validation. The convolutional neural network (CNN), based on the pre-trained VGG19 architecture for classifying chest X-ray images, was trained on a publicly available smaller dataset containing 196 entries, and achieved an average classification accuracy of 91.83 ± 2.82%. The DNN model for optimizing patient appointment scheduling was trained on a large dataset (341,569 entries) and a rich feature design extracted from the MIS, which is daily used in Serbia, achieving an average classification accuracy of 77.51 ± 0.70%. Both models have consistent performance and good generalization. The architecture of a realized MIS, incorporating the positioning of developed AI tools that encompass both developed models, is also presented in this study. Full article

This paper showcases current developments in the use of carbon nanotube (CNT) and nanoparticle-based materials for electromagnetic radiation shielding. Electromagnetic radiation involves different types of radiation covering a wide spectrum of frequencies. Due to their good electrical conductivity, small diameter, and light weight, individual CNTs are good candidates for shielding radio and microwaves. CNTs can be organized into macroscale forms by dispersing them in polymers or by wrapping CNT strands into fabrics or yarn. Magnetic nanoparticles can also be incorporated into the CNT fabric to provide excellent shielding of electromagnetic waves. However, for shielding higher-frequency X-ray and gamma ray radiation, the situation is reversed. Carbon’s low atomic number means that CNTs alone are less effective than metals. Thus, different nanoparticles such as tungsten are added to the CNT materials to provide improved shielding of photons. The goal is to achieve a desired combination of light weight, flexibility, safety, and multifunctionality for use in shielding spacecraft, satellites, nuclear reactors, and medical garments and to support lunar colonization. Future research should investigate the effect of the size, shape, and configuration of nanoparticles on radiation shielding. Developing large-scale low-cost methods for the continuous manufacturing of lightweight multifunctional nanoparticle-based materials is also needed. Full article

Background/Objective: The COVID-19 pandemic profoundly transformed social life worldwide, indiscriminately affecting individuals across all age groups. Children have not been exempted from the risk of severe illness and death caused by COVID-19. Objective: This paper sought to describe the clinical findings, laboratory and imaging results, and hospital care provided for severe and critical cases of COVID-19 in unvaccinated children, with or without severe asthma, hospitalized in a public referral service for COVID-19 treatment in the Brazilian state of Pernambuco. Methods: This was a case series study of severe and critical COVID-19 in hospitalized, unvaccinated children, with or without severe asthma, conducted in a public referral hospital between March 2020 and June 2021. Results: The case series included 80 children, aged from 1 month to 11 years, with the highest frequency among those under 2 years old (58.8%) and a predominance of males (65%). Respiratory diseases, including severe asthma, were present in 73.8% of the cases. Pediatric multisystem inflammatory syndrome occurred in 15% of the children, some of whom presented with cardiac involvement. Oxygen therapy was required in 65% of the cases, mechanical ventilation in 15%, and 33.7% of the children required intensive care in a pediatric intensive care unit. Pulmonary infiltrates and ground-glass opacities were common findings on chest X-rays and CT scans; inflammatory markers were elevated, and the most commonly used medications were antibiotics, bronchodilators, and corticosteroids. Conclusions: This case series has identified key characteristics of children with severe and critical COVID-19 during a period when vaccines were not yet available in Brazil for the study age group. However, the persistence of low vaccination coverage, largely due to parental vaccine hesitancy, continues to leave children vulnerable to potentially severe illness from COVID-19. These findings may inform the development of public health emergency contingency plans, as well as clinical protocols and care pathways, which can guide decision-making in pediatric care and ensure appropriate clinical management, ultimately improving the quality of care provided. Full article

CT scanners are essential tools in modern medical imaging. Sudden failures of their X-ray tubes can lead to equipment downtime, affecting healthcare services and patient diagnosis. However, existing prediction methods based on a single model struggle to adapt to the multi-stage variation characteristics of tube lifespan and have limited modeling capabilities for temporal features. To address these issues, this paper proposes an intelligent prediction architecture for CT tubes’ remaining useful life based on a dual-branch neural network. This architecture consists of two specialized branches: a residual self-attention BiLSTM (RSA-BiLSTM) and a multi-layer dilation temporal convolutional network (D-TCN). The RSA-BiLSTM branch extracts multi-scale features and also enhances the long-term dependency modeling capability for temporal data. The D-TCN branch captures multi-scale temporal features through multi-layer dilated convolutions, effectively handling non-linear changes in the degradation phase. Furthermore, a dynamic phase detector is applied to integrate the prediction results from both branches. In terms of optimization strategy, a dynamically weighted triplet mixed loss function is designed to adjust the weight ratios of different prediction tasks, effectively solving the problems of sample imbalance and uneven prediction accuracy. Experimental results using leave-one-out cross-validation (LOOCV) on six different CT tube datasets show that the proposed method achieved significant advantages over five comparison models, with an average MSE of 2.92, MAE of 0.46, and R² of 0.77. The LOOCV strategy ensures robust evaluation by testing each tube dataset independently while training on the remaining five, providing reliable generalization assessment across different CT equipment. Ablation experiments further confirmed that the collaborative design of multiple components is significant for improving the accuracy of X-ray tubes remaining life prediction. Full article

The detection of trace chemicals at low and ultra-low concentrations is critical for applications in environmental monitoring, medical diagnostics, food safety and other fields. Conventional detection techniques often lack the required sensitivity, specificity, or cost-effectiveness, making real-time, in situ analysis challenging. Surface-enhanced Raman spectroscopy (SERS) is a powerful analytical tool, offering improved sensitivity through the enhancement of Raman scattering by plasmonic nanostructures. While noble metals such as Ag and Au are currently the reference choices for SERS substrates, fabrication methods should balance enhancement efficiency, reproducibility and scalability. In this study, we propose a novel approach for SERS substrate fabrication using reactive Aerosol Jet Printing (r-AJP) as an innovative additive manufacturing technique. The r-AJP process enables in-flight Ag seed reduction and nucleation of Ag nanoparticles (NPs) by mixing silver nitrate and ascorbic acid aerosols before deposition, as suggested by computational fluid dynamics (CFD) simulations. The resulting coatings were characterized by X-ray diffraction (XRD) and scanning electron microscopy (SEM) analyses, revealing the formation of nanoporous crystalline Ag agglomerates partially covered by residual matter. The as-prepared SERS substrates exhibited remarkable SERS activity, demonstrating a high enhancement factor (10⁶) for rhodamine (R6G) detection. Our findings highlight the potential of r-AJP as a scalable and cost-effective fabrication strategy for next-generation SERS sensors, paving the way for the development of a new additive manufacturing tool for noble metal material deposition. Full article

Background/Objectives: Magnetic nanoparticles, particularly iron oxide-based materials, such as magnetite (Fe₃O₄), have gained significant attention as contrast agents in medical imaging This study aimsto syntheze and characterize Fe₃O₄-based core–shell nanostructures, including Fe₃O₄@TiO₂ and Fe₃O₄@SiO₂, and to evaluate their potential as tunable contrast agents for diagnostic imaging. Methods: Fe₃O₄, Fe₃O₄@TiO₂, and Fe₃O₄@SiO₂ nanoparticles were synthesized via co-precipitation at varying temperatures from iron salt precursors. Fourier transform infrared spectroscopy (FTIR) was used to confirm the presence of Fe–O bonds, while X-ray diffraction (XRD) was employed to determine the crystalline phases and estimate average crystallite sizes. Morphological analysis and particle size distribution were assessed by scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDX) and transmission electron microscopy (TEM). Magnetic properties were investigated using vibrating sample magnetometry (VSM). Results: FTIR spectra exhibited characteristic Fe–O vibrations at 543 cm⁻¹ and 555 cm⁻¹, indicating the formation of magnetite. XRD patterns confirmed a dominant cubic magnetite phase, with the presence of rutile TiO₂ and stishovite SiO₂ in the coated samples. The average crystallite sizes ranged from 24 to 95 nm. SEM and TEM analyses revealed particle sizes between 5 and 150 nm with well-defined core–shell morphologies. VSM measurements showed saturation magnetization (Ms) values ranging from 40 to 70 emu/g, depending on the synthesis temperature and shell composition. The highest Ms value was obtained for uncoated Fe₃O₄ synthesized at 94 °C. Conclusions: The synthesized Fe₃O₄-based core–shell nanomaterials exhibit desirable structural, morphological, and magnetic properties for use as contrast agents. Their tunable magnetic response and nanoscale dimensions make them promising candidates for advanced diagnostic imaging applications. Full article

Malignant mediastinal tumors are a group representing some of the most demanding oncological challenges for early, multi-level, and successful management. The timely identification of any suspicious clinical symptomatology is urgent in achieving an accurate, staged histological diagnosis, in order to follow up with an equally detailed medical therapeutic plan (interventional or not) and determine the principal goals regarding efficient overall treatment in these patients. We report a case of a 24-year-old male patient with an incident-free prior medical history. An initial chest X-ray was performed after the patient reported short-term, consistent moderate chest pain symptomatology, early work fatigue, and shortness of breath. The following imaging procedures (chest CT, PET-CT) indicated the presence of an anterior mediastinal mass (meas. ~11 cm × 10 cm × 13 cm, SUV: 8.7), applying additional pressure upon both right heart chambers. The Alpha-Fetoprotein (aFP) blood levels had exceeded at least 50 times their normal range. Two consecutive diagnostic attempts with non-specific histological results, a negative-for-malignancy fine-needle aspiration biopsy (FNA-biopsy), and an additional tumor biopsy, performed via mini anterior (R) thoracotomy with “suspicious” cellular gatherings, were performed elsewhere. After admission to our department, an (R) Video-Assisted Thoracic Surgery (VATS) was performed, along with multiple tumor biopsies and moderate pleural effusion drainage. The tumor’s measurements had increased to DMax: 16 cm × 9 cm × 13 cm, with a severe degree of atelectasis of the Right Lower Lobe parenchyma (RLL) and a pressure-displacement effect upon the Superior Vena Cava (SVC) and the (R) heart sinus, based on data from the preoperative chest MRA. The histological report indicated elements of a combined, non-seminomatous germ-cell mediastinal tumor, posthuberal-type teratoma, and embryonal carcinoma. The imminent chemotherapeutic plan included a “BEP” (Bleomycin^®/Cisplatin^®/Etoposide^®) scheme, which needed to be modified to a “VIP” (Cisplatin^®/Etoposide^®/Ifosfamide^®) scheme, due to an acute pulmonary embolism incident. While the aFP blood levels declined, even reaching normal measurements, the tumor’s size continued to increase significantly (DMax: 28 cm × 25 cm × 13 cm), with severe localized pressure effects, rapid weight loss, and a progressively worsening clinical status. Thus, an emergency surgical intervention took place via median sternotomy, extended with a complementary “T-Shaped” mini anterior (R) thoracotomy. A large, approx. 4 Kg mediastinal tumor was extracted, with additional RML and RUL “en-bloc” segmentectomy and partial mediastinal pleura decortication. The following histological results, apart from verifying the already-known posthuberal-type teratoma, indicated additional scattered small lesions of combined high-grade rabdomyosarcoma, chondrosarcoma, and osteosarcoma, as well as numerous high-grade glioblastoma cellular gatherings. No visible findings of the previously discovered non-seminomatous germ-cell and embryonal carcinoma elements were found. The patient’s postoperative status progressively improved, allowing therapeutic management to continue with six “TIP” (Cisplatin^®/Paclitaxel^®/Ifosfamide^®) sessions, currently under his regular “follow-up” from the oncological team. This report underlines the importance of early, accurate histological identification, combined with any necessary surgical intervention, diagnostic or therapeutic, as well as the appliance of any subsequent multimodality management plan. The diversity of mediastinal tumors, especially for young patients, leaves no place for complacency. Such rare examples may manifest, with equivalent, unpredictable evolution, obliging clinical physicians to stay constantly alert and not take anything for granted. Full article

Medical image registration is an indispensable preprocessing step to align medical images to a common coordinate system before in-depth analysis. The registration precision is critical to the following analysis. In addition to representative image features, the initial pose settings and multiple poses in images will significantly affect the registration precision, which is largely neglected in state-of-the-art works. To address this, the paper proposes a dual-pose medical image registration algorithm based on improved differential evolution. More specifically, the proposed algorithm defines a composite similarity measurement based on contour points and utilizes this measurement to calculate the similarity between frontal–lateral positional DRR (Digitally Reconstructed Radiograph) images and X-ray images. In order to ensure the accuracy of the registration algorithm in particular dimensions, the algorithm implements a dual-pose registration strategy. A PDE (Phased Differential Evolution) algorithm is proposed for iterative optimization, enhancing the optimization algorithm’s ability to globally search in low-dimensional space, aiding in the discovery of global optimal solutions. Extensive experimental results demonstrate that the proposed algorithm provides more accurate similarity metrics compared to conventional registration algorithms; the dual-pose registration strategy largely reduces errors in specific dimensions, resulting in reductions of 67.04% and 71.84%, respectively, in rotation and translation errors. Additionally, the algorithm is more suitable for clinical applications due to its lower complexity. Full article

The growing demand for accurate and efficient Chest X-Ray (CXR) interpretation has prompted the development of AI-driven systems to alleviate radiologist workload and reduce diagnostic variability. This paper introduces the Intelligent Humanized Radiology Analysis System (IHRAS), a modular framework that automates the end-to-end process of CXR analysis and report generation. IHRAS integrates four core components: (i) deep convolutional neural networks for multi-label classification of 14 thoracic conditions; (ii) Grad-CAM for spatial visualization of pathologies; (iii) SAR-Net for anatomical segmentation; and (iv) a large language model (DeepSeek-R1) guided by the CRISPE prompt engineering framework to generate structured diagnostic reports using SNOMED CT terminology. Evaluated on the NIH ChestX-ray dataset, IHRAS demonstrates consistent diagnostic performance across diverse demographic and clinical subgroups, and produces high-fidelity, clinically relevant radiological reports with strong faithfulness, relevancy, and alignment scores. The system offers a transparent and scalable solution to support radiological workflows while highlighting the importance of interpretability and standardization in clinical Artificial Intelligence applications. Full article

Accurate classification of chest X-ray (CXR) images is crucial for diagnosing lung diseases in medical imaging. Existing deep learning models for CXR image classification face challenges in distinguishing non-lung features. In this work, we propose a new segmentation-assisted fusion-based classification method. The method involves two stages: first, we use a lightweight segmentation model, Partial Convolutional Segmentation Network (PCSNet) designed based on an encoder–decoder architecture, to accurately obtain lung masks from CXR images. Then, a fusion of the masked CXR image with the original image enables classification using the improved lightweight ShuffleNetV2 model. The proposed method is trained and evaluated on segmentation datasets including the Montgomery County Dataset (MC) and Shenzhen Hospital Dataset (SH), and classification datasets such as Chest X-Ray Images for Pneumonia (CXIP) and COVIDx. Compared with seven segmentation models (U-Net, Attention-Net, SegNet, FPNNet, DANet, DMNet, and SETR), five classification models (ResNet34, ResNet50, DenseNet121, Swin-Transforms, and ShuffleNetV2), and state-of-the-art methods, our PCSNet model achieved high segmentation performance on CXR images. Compared to the state-of-the-art Attention-Net model, the accuracy of PCSNet increased by 0.19% (98.94% vs. 98.75%), and the boundary accuracy improved by 0.3% (97.86% vs. 97.56%), while requiring 62% fewer parameters. For pneumonia classification using the CXIP dataset, the proposed strategy outperforms the current best model by 0.14% in accuracy (98.55% vs. 98.41%). For COVID-19 classification with the COVIDx dataset, the model reached an accuracy of 97.50%, the absolute improvement in accuracy compared to CovXNet was 0.1%, and clinical metrics demonstrate more significant gains: specificity increased from 94.7% to 99.5%. These results highlight the model’s effectiveness in medical image analysis, demonstrating clinically meaningful improvements over state-of-the-art approaches. Full article

Interpreting diagnostic imaging and identifying clinically relevant features remain challenging tasks, particularly for novice radiologists who often lack structured guidance and expert feedback. To bridge this gap, we propose an Eye-Gaze Guided Multimodal Fusion framework that leverages expert eye-tracking data to enhance learning and decision-making in medical image interpretation. By integrating chest X-ray (CXR) images with expert fixation maps, our approach captures radiologists’ visual attention patterns and highlights regions of interest (ROIs) critical for accurate diagnosis. The fusion model utilizes a shared backbone architecture to jointly process image and gaze modalities, thereby minimizing the impact of noise in fixation data. We validate the system’s interpretability using Gradient-weighted Class Activation Mapping (Grad-CAM) and assess both classification performance and explanation alignment with expert annotations. Comprehensive evaluations, including robustness under gaze noise and expert clinical review, demonstrate the framework’s effectiveness in improving model reliability and interpretability. This work offers a promising pathway toward intelligent, human-centered AI systems that support both diagnostic accuracy and medical training. Full article

Stability assessments of drug substances and the detection of crystalline forms are critical for ensuring drug quality and medication safety. Atorvastatin calcium drug substance samples were characterized using powder X-ray diffraction (PXRD) and differential scanning calorimetry (DSC). DSC results demonstrated a precise discrimination of the stability of samples. An analysis of PXRD characteristic peaks and DSC melting data suggested that instability likely stems from the presence of the amorphous phase. To validate this hypothesis, blended samples containing controlled ratios of amorphous phase and crystalline Form I were prepared. Quantitative models based on PXRD, DSC, and near-infrared spectroscopy (NIRS) data were developed to predict amorphous content, and classification accuracy was evaluated. Experimental results confirmed that all three models achieved classification accuracy values exceeding 70% in the stability prediction of the two groups of samples, which included “stable” and “unstable” samples, substantiating the hypothesis. Among them, the modeling method based on NIRS data was not only non-destructive and rapid but also demonstrates a superior discrimination accuracy value reaching 100% (n = 11), showing potential for promotion and application in industrial sample detection. The quantitative correlation between amorphous content and stability was successfully established in this study, offering a novel method for a quality stability assessment of atorvastatin calcium drug substances. Full article

The rapid spread of COVID-19 increased the need for speedy diagnostic tools, which led scientists to conduct extensive research on deep learning (DL) applications that use chest imaging, such as chest X-ray (CXR) and computed tomography (CT). This review examines the development and performance of DL architectures, notably convolutional neural networks (CNNs) and emerging vision transformers (ViTs), in identifying COVID-19-related lung abnormalities. Individual ResNet architectures, along with CNN models, demonstrate strong diagnostic performance through the transfer protocol; however, ViTs provide better performance, with improved readability and reduced data requirements. Multimodal diagnostic systems now incorporate alternative methods, in addition to imaging, which use lung ultrasounds, clinical data, and cough sound evaluation. Information fusion techniques, which operate at the data, feature, and decision levels, enhance diagnostic performance. However, progress in COVID-19 detection is hindered by ongoing issues stemming from restricted and non-uniform datasets, as well as domain differences in image standards and complications with both diagnostic overfitting and poor generalization capabilities. Recent developments in COVID-19 diagnosis involve constructing expansive multi-noise information sets while creating clinical process-oriented AI algorithms and implementing distributed learning protocols for securing information security and system stability. While deep learning-based COVID-19 detection systems show strong potential for clinical application, broader validation, regulatory approvals, and continuous adaptation remain essential for their successful deployment and for preparing future pandemic response strategies. Full article

Accurate detection of fractures in X-ray images is important to initiate appropriate medical treatment in time—in this study, an advanced combined attention CNN model with multiple attention mechanisms was developed to improve fracture detection by deeply representing features. Specifically, our model incorporates squeeze blocks and convolutional block attention module (CBAM) blocks to improve the model’s ability to focus on relevant features in X-ray images. Using computed tomography X-ray images, this study assesses the diagnostic efficacy of the artificial intelligence (AI) model before and after optimization and compares its performance in detecting fractures or not. The training and evaluation dataset consists of fractured and non-fractured X-rays from various anatomical locations, including the hips, knees, lumbar region, lower limb, and upper limb. This gives an extremely high training accuracy of 99.98 and a validation accuracy 96.72. The attention-based CNN thus showcases its role in medical image analysis. This aspect further complements a point we highlighted through our research to establish the role of attention in CNN architecture-based models to achieve the desired score for fracture in a medical image, allowing the model to generalize. This study represents the first steps to improve fracture detection automatically. It also brings solid support to doctors addressing the continued time to examination, which also increases accuracy in diagnosing fractures, improving patients’ outcomes significantly. Full article

Background/Objectives: Extracting meaningful medical information from chest X-ray images and transcribing it into text is a complex task that requires a high level of expertise and directly affects clinical decision-making processes. Automatic reporting systems for this field in Turkish represent an important gap in scientific research, as they have not been sufficiently addressed in the existing literature. Methods: A deep learning-based approach called Model-SEY was developed with the aim of automatically generating Turkish medical reports from chest X-ray images. The Swin Transformer structure was used in the encoder part of the model to extract image features, while the text generation process was carried out using the cosmosGPT architecture, which was adapted specifically for the Turkish language. Results: With the permission of the ethics committee, a new dataset was created using image–report pairs obtained from Elazıg Fethi Sekin City Hospital and Indiana University Chest X-Ray dataset and experiments were conducted on this new dataset. In the tests conducted within the scope of the study, scores of 0.6412, 0.5335, 0.4395, 0.4395, 0.3716, and 0.2240 were obtained in BLEU-1, BLEU-2, BLEU-3, BLEU-4, and ROUGE word overlap evaluation metrics, respectively. Conclusions: Quantitative and qualitative analyses of medical reports autonomously generated by the proposed model have shown that they are meaningful and consistent. The proposed model is one of the first studies in the field of autonomous reporting using deep learning architectures specific to the Turkish language, representing an important step forward in this field. It will also reduce potential human errors during diagnosis by supporting doctors in their decision-making. Full article