Search Results (969)

Deep learning applied to chest X-ray (CXR) images has gained wide attention for its potential to improve diagnostic accuracy and accessibility in resource-limited healthcare settings. This study compares two deep learning strategies for lung disease classification: a Two-Stage approach that first detects abnormalities before classifying specific pathologies and a Direct multiclass classification approach. Using a curated database of CXR images covering diverse lung diseases, including COVID-19, pneumonia, pulmonary fibrosis, and tuberculosis, we evaluate the performance of various convolutional neural network architectures, the impact of lung segmentation, and explainability techniques. Our results show that the Two-Stage framework achieves higher diagnostic performance and fewer false positives than the Direct approach. Additionally, we highlight the limitations of segmentation and data augmentation techniques, emphasizing the need for further advancements in explainability and robust model design to support real-world diagnostic applications. Finally, we conduct a complementary evaluation of bone suppression techniques to assess their potential impact on disease classification performance. Full article

Ensuring the integrity of medical images is essential to securing clinical workflows, telemedicine platforms, and healthcare IoT environments. Existing watermarking and reversible data-hiding approaches often modify pixel intensities, reducing diagnostic fidelity, introducing embedding constraints, or causing instability under compression and format conversion. This work proposes a distortion-free, non-embedding authentication framework that leverages the inherent stability of the most significant bit (MSB) patterns in the Non-Region of Interest (NROI) to construct a secure and tamper-sensitive reference for the diagnostic Region of Interest (ROI). The ROI is partitioned into fixed blocks, each producing a 256-bit SHA-256 signature. Instead of embedding this signature, each hash bit is mapped to an NROI pixel whose MSB matches the corresponding bit value, and only the encrypted coordinates of these pixels are stored externally in a secure database. During verification, hashes are recomputed and compared bit-by-bit with the MSB sequence extracted from the referenced NROI coordinates, enabling precise block-level tamper localization without modifying the image. Extensive experiments conducted on MRI (OASIS), X-ray (ChestX-ray14), and CT (CT-ORG) datasets demonstrate the following: (i) perfect zero-distortion fidelity; (ii) stable and deterministic MSB-class mapping with abundant coordinate diversity; (iii) 100% detection of intentional ROI tampering with no false positives across the six clinically relevant manipulation types; and (iv) robustness to common benign Non-ROI operations. The results show that the proposed scheme offers a practical, secure, and computationally lightweight solution for medical image integrity verification in PACS systems, cloud-based archives, and healthcare IoT applications, while avoiding the limitations of embedding-based methods. Full article

Background: Non-communicable diseases (NCDs) such as cardiovascular diseases, diabetes, obesity, and cancer are the leading cause of mortality globally and in Saudi Arabia, accounting for more than 70% of all deaths. Despite national initiatives offering free preventive services, screening uptake remains low. This study aimed to describe the demographic and clinical characteristics of individuals participating in community-based NCD screening campaigns in the Eastern Province of Saudi Arabia and to evaluate screening uptake, compliance, and diagnostic outcomes. Methods: A retrospective cross-sectional analysis was conducted among 3106 adults screened at volunteer-driven community campaigns held between January 2023 and December 2024. Screening included anthropometric measurements, blood pressure assessment, and glucose testing, followed by eligibility evaluation for osteoporosis and cancer screening. Uptake and compliance were verified using electronic health records. Descriptive and inferential statistical analyses were applied. Results: Participants were 64% male and 36% female, with a mean age of 41.4 ± SD years. Obesity, hypertension, and diabetes were identified in 32%, 31%, and 12% of participants overall. Gender-stratified prevalence showed higher obesity among females at 36% (95% CI 32.3 to 38.1) and higher hypertension and diabetes among males at 36% (95% CI 34.0 to 38.2) and 14% (95% CI 12.1 to 15.2), respectively. Uptake among eligible individuals was 51% for dual-energy X-ray absorptiometry (DEXA), 47% for fecal immunochemical testing (FIT), 43% for Pap smear, and 39% for mammography. Diagnostic findings demonstrated substantial undetected disease burden, including osteoporosis in 41% (95% CI 26.0 to 56.8) of DEXA scans, a FIT positivity rate of 5% (95% CI 1.5 to 10.3), abnormal Pap cytology in 3% (95% CI 1.1 to 7.5), and BI-RADS 0 mammograms in 19% (95% CI 11.9 to 29.5), reflecting incomplete assessments requiring further evaluation. Conclusions: Community-based campaigns can effectively resolve limited engagement in health promotional activities and detect substantial burdens of undiagnosed NCDs. However, improvements in referral tracking, follow-up systems, and culturally tailored health education are essential to enhance screening compliance and early detection outcomes. These results can be utilized to inform public policies by extending screening services to additional areas, increasing investment in preventive health campaigns, and enhancing the capacity of the health system. Full article

Background/Objectives: Traditional medical image analysis methods often suffer from locality bias, limiting their ability to model long-range contextual relationships between spatially distributed anatomical structures. To overcome this challenge, this study proposes SPX-GNN (Superpixel Explainable Graph Neural Network). This novel method reformulates image analysis as a structural graph learning problem, capturing both local anomalies and global topological patterns in a holistic manner. Methods: The proposed framework decomposes images into semantically coherent superpixel regions, converting them into graph nodes that preserve topological relationships. Each node is enriched with a comprehensive feature vector encoding complementary diagnostic clues, including colour (CIELAB), texture (LBP and Haralick), shape (Hu moments), and spatial location. A Graph Neural Network is then employed to learn the relational dependencies between these enriched nodes. The method was rigorously evaluated using 5-fold stratified cross-validation on a public dataset comprising 4200 chest X-ray images. Results: SPX-GNN demonstrated exceptional performance in tuberculosis classification, achieving a mean accuracy of 99.82%, an F1-score of 99.45%, and a ROC-AUC of 100.00%. Furthermore, an integrated Explainable Artificial Intelligence module addresses the black box problem by generating semantic importance maps, which illuminate the decision mechanism and enhance clinical reliability. Conclusions: SPX-GNN offers a novel approach that successfully combines high diagnostic accuracy with methodological transparency. By providing a robust and interpretable workflow, this study presents a promising solution for medical imaging tasks where structural information is critical, paving the way for more reliable clinical decision support systems. Full article

This study is part of a broader conservation and restoration project of the 17th-century statue “Santissimo Salvatore” attributed to the Bolognese sculptor Gabriele Brunelli (1615–1682). This sculpture was traditionally classified as a marble statue, i.e., primarily composed of calcium carbonate. However, the careful diagnostic analyses conducted during the present work of restoration revealed that, instead, the sculpture is made of gypsum alabaster, a material predominantly composed of calcium sulphate hydrate (CaSO₄·2H₂O). In the present research, a multi-analytical investigation was carried out using X-Ray Powder Diffraction (XRPD), Field Emission Environmental Scanning Electron Microscopy (FE-ESEM) with Energy-Dispersive X-ray Spectroscopy (EDS), and confocal Raman microspectrometry. Here, we report detailed and updated analytical data of the material constituting the “Santissimo Salvatore” statue by Gabriele Brunelli. These data were found extremely useful to plan and accomplish the restoration work in detail: (i) the suitable conservation project of the artwork, (ii) the reassessment of the knowledge on the artist’s sculptural production, and (iii) gaining more information about the material used in the 17th-century Bolognese sculptural context. Full article

In this study, a structured and methodological evaluation approach for eXplainable Artificial Intelligence (XAI) methods in medical image classification is proposed and implemented using LIME and SHAP explanations for chest X-ray interpretations. The evaluation framework integrates two critical perspectives: predictive model-centered and human-centered evaluations. Predictive model-centered evaluations examine the explanations’ ability to reflect changes in input and output data and the internal model structure. Human-centered evaluations, conducted with 97 medical experts, assess trust, confidence, and agreements with AI’s indicative and contra-indicative reasoning as well as their changes before and after provision of explainability. Key findings of our study include explanation of sensitivity of LIME and SHAP to model changes, their effectiveness in identifying critical features, and SHAP’s significant impact on diagnosis changes. Our results show that both LIME and SHAP negatively affected contra-indicative agreement. Case-based analysis revealed AI explanations reinforce trust and agreement when participant’s initial diagnoses are correct. In these cases, SHAP effectively facilitated correct diagnostic changes. This study establishes a benchmark for future research in XAI for medical image analysis, providing a robust foundation for evaluating and comparing different XAI methods. Full article

Background: Vision-language models show promise in medical image interpretation, but their performance in musculoskeletal tumor diagnostics remains underexplored. Objective: To evaluate the diagnostic accuracy of six large language models on orthopedic radiographs for tumor detection, classification, anatomical localization, and X-ray view interpretation, and to assess the impact of demographic context and self-reported certainty. Methods: We retrospectively evaluated six VLMs on 3746 expert-annotated orthopedic radiographs from the Bone Tumor X-ray Radiograph dataset. Each image was analyzed by all models with and without patient age and sex using a standardized prompting scheme across four predefined tasks. Results: Over 48,000 predictions were analyzed. Tumor detection accuracy ranged from 59.9–73.5%, with the Gemini Ensemble achieving the highest F1 score (0.723) and recall (0.822). Benign/malignant classification reached up to 85.2% accuracy; tumor type identification 24.6–55.7%; body region identification 97.4%; and view classification 82.8%. Demographic data improved tumor detection accuracy (+1.8%, p < 0.001) but had no significant effect on other tasks. Certainty scores were weakly correlated with correctness, with Gemini Pro highest (r = 0.089). Conclusion: VLMs show strong potential for basic musculoskeletal radiograph interpretation without task-specific training but remain less accurate than specialized deep learning models for complex classification. Limited calibration, interpretability, and contextual reasoning must be addressed before clinical use. This is the first systematic assessment of image-based diagnosis and self-assessment in LLMs using a real-world radiology dataset. Full article

Apatite is a key indicator mineral whose chemical signature can reveal the genesis and evolution of ore-forming systems. However, correctly interpreting these signatures requires a robust discrimination between apatite types formed by different geological processes, such as metamorphism and hydrothermal activity. This study aims to chemically characterize and genetically classify apatite samples from the Slyudyanka deposit (Siberia, Russia) to establish discriminative geochemical fingerprints for metamorphic and hydrothermal apatite types. We analyzed 80 samples of apatite using total reflection X-ray fluorescence (TXRF) and inductively coupled plasma mass spectrometry (ICP-MS). The geochemical data were processed using principal component analysis (PCA) and k-means cluster analysis to objectively discriminate the apatite types. Our analysis reveals three distinct geochemical groups. Metamorphic veinlet apatite is defined by high U and Pb, low REE, Sr, and Th, and suprachondritic Y/Ho ratios. Massive metamorphic apatite from silicate–carbonate rocks shows extreme REE enrichment and chondritic Y/Ho ratios. Hydrothermal–metasomatic apatite features high Sr, Th, and As, with intermediate REE concentrations and chondritic Y/Ho ratios. Furthermore, we validated the critical and anomalous Y concentrations in the metamorphic veinlet apatite by cross-referencing TXRF and ICP-MS data, confirming the reliability of our measurements for this monoisotopic element. We successfully established diagnostic geochemical fingerprints that distinguish apatite formed in different geological environments at Slyudyanka. The anomalous Y/Ho ratio in metamorphic veinlet apatite serves as a key discriminant and provides insight into specific fractionation processes that occurred during the formation of phosphorites in oceanic environments, which later transformed to apatites during high-grade metamorphism without a change in the Y/Ho ratio. This work underscores the importance of multi-method analytical validation for accurate geochemical classification. Full article

This paper provides a comprehensive overview of the application of various radiological modalities, with a critical comparison between human and veterinary medicine. The modalities discussed include conventional radiography, dual-energy X-ray absorptiometry (DXA), computed tomography (CT), magnetic resonance imaging (MRI), ultrasound (US), quantitative ultrasound (QUS), positron emission tomography-computed tomography (PET-CT) and micro and nano computed tomography (micro-CT, nano-CT) in clinical practice and basic research of skeletal system. Radiological imaging plays a crucial role in the diagnosis, monitoring and research of skeletal system disorders in both human and veterinary medicine. In preclinical research, advanced diagnostic imaging modalities such as micro-CT and nano-CT allow for 3D quantification of trabecular and cortical bone microarchitecture for studies in bone biology, regenerative medicine and pharmacological research. Furthermore, the integration of artificial intelligence is advancing image interpretation, precision diagnostics and disease tracking. Despite their broad utility, imaging modalities must be selected based on clinical indication, species, age and anatomical region with consideration of radiation dose, cost and availability, especially in remote regions. For this reason, clinicians and radiologists remain an irreplaceable part of diagnostic imaging. Full article

Radiotherapy is a fundamental component in the management of head and neck malignancies, but its non-selective effects on surrounding normal tissues can result in significant oral complications. The oral cavity and oropharynx contain several radiosensitive structures, including mucosa, salivary glands, and alveolar bone, which are susceptible to both acute and late toxicities resulting in mucositis, xerostomia, and osteoradionecrosis. Although dentomaxillofacial diagnostic imaging, such as intraoral radiography, panoramic imaging and cone-beam computed tomography (CBCT), delivers radiation doses several orders of magnitude lower than therapeutic exposures, its biological impact on previously irradiated tissues remains underexplored. Even low-dose X-rays may act as secondary stressors, reactivating oxidative and inflammatory pathways in tissues with compromised repair capacity. In this review, we examine the radiobiological and dosimetric implications of using diagnostic ionizing imaging in patients undergoing or recently having completed head and neck radiotherapy. We summarize current evidence on potential additive effects of low-dose imaging, emphasizing the importance of justification, timing, and protocol optimization. Finally, we discuss radioprotective strategies (e.g., dose modulation, field limitation, and integration of modern low-dose imaging technologies) designed to reduce unnecessary exposure, thus enhancing tissue preservation and ensuring diagnostic safety in this vulnerable patient population Full article

This research deals with a multi-analytical approach to characterise three polychrome wooden crucifixes attributed to Fra’ Umile da Petralia or, in one case, close to his style. The analysed wooden sculptures belong to (1) the Sanctuary of Saint Umile from Bisignano (Cosenza, Italy); (2) the Santissimo Crocifisso Church at Cutro (Crotone, Italy); (3) the Saint Salvatore Church at Gangi (Palermo, Italy). Fra’ Umile (Giovanni Francesco Pintorno) was born in Petralia Soprana (Palermo, Sicily) between 1600 and 1601, died on 9 February 1639, and belonged to the Order of Friars Minor. Systematic research of the materials and constructive techniques of wooden sculptures is still not very wide, although diagnostic analyses could represent a useful tool for art historians and restorers for these typologies of works of art. The wooden sculptures were subjected to both non-invasive and micro-invasive investigations. Digital direct X-ray radiography, SEM-EDX, and X-ray fluorescence analyses have been carried out, revealing for the three analysed sculptures a similar construction technique and similar pictorial materials. The provided diagnostic evidence supports the coincident chronology and the same attribution to Fra’ Umile da Petralia or his workshop, confirming the proposals based on the stylistic comparative analyses and archival historical documents. The results of this first multi-analytical investigation, documenting the artistic technique and construction system, represent a starting point for future systematic study on the artistic production of this prolific artist and sculptor never studied from a technical–scientific point of view to date. Full article

Background: Aorto-esophageal fistula (AEF) is a rare but life-threatening condition in children following foreign body (FB) ingestion, with button batteries (BB) being the most dangerous. These batteries involve severe tissue necrosis due to chemical and electrical reactions, often leading to fistula formation and catastrophic hemorrhage. Appropriate treatment for AEF is still undefined. Method: This report presents a novel case of AEF closure using a covered stent in a 4-year-old boy, complemented by a narrative review of 36 reported pediatric AEF cases from 1988 to 2024. Results: The review revealed that BB ingestion accounted for 67% of AEF cases, with a high mortality rate of 43%, underscoring the critical nature of this condition. Early symptoms are often nonspecific, leading to delayed diagnoses, which worsen outcomes. Computed tomography (CT) is the key imaging modality for detecting vascular complications such as AEF, while X-ray may help identify the foreign body, but is often insufficient to assess associated injuries. While surgical repair remains the mainstay of treatment, minimally invasive techniques, such as endovascular approaches, are emerging as viable options. Conclusions: This study highlights the need for heightened public awareness, safer battery designs, and prompt, multidisciplinary interventions to improve patient outcomes. Future research should focus on refining diagnostic protocols, evaluating innovative management strategies, and establishing comprehensive registries to inform evidence-based guidelines and optimize care. Full article

Background/Objectives: Acute dyspnea is a common and urgent presentation in the emergency department, with acute heart failure (AHF) as one of its leading causes. Rapid differentiation between AHF and other etiologies is essential. Methods: This study aimed to evaluate the diagnostic accuracy of lung ultrasound (LUS) and compare it to chest X-ray (CXR) and NT-proBNP accuracy in patients with acute dyspnea, and to assess the potential of LUS for fast bedside diagnosis. This prospective study included 242 adult patients presenting with acute dyspnea of ≤3 days’ duration. All underwent NT-proBNP testing, CXR, and LUS according to a standardized protocol. The final diagnosis was established by experienced clinicians using all available clinical, laboratory, and imaging data, blinded to the LUS results. Diagnostic performance measures of LUS, CXR, and NT-proBNP were evaluated, and examination times of LUS and CXR were compared. Results: LUS achieved the highest sensitivity (95.3%) and negative predictive value (90.8%) for AHF, outperforming NT-proBNP (87.5%, 74.2%) and CXR (84.4%, 79.0%). CXR showed the highest specificity (65.8%) and positive predictive value (73.5%), while LUS specificity was moderate (51.8%). The LUS results were available significantly faster (median 10.0 min) than CXR (median 62.5 min). Conclusions: LUS demonstrated diagnostic accuracy comparable to CXR and NT-proBNP, with superior sensitivity, negative predictive value, and shorter time to results. These findings support its use as a rapid, non-invasive, first-line tool for excluding AHF in acute dyspnea patients. Full article

Background/Objectives: Colonic diverticulosis is a common condition in the elderly population and may affect bowel habits and reduce quality of life. Intestinal peristalsis is regulated by bioamines, which can influence bowel transit time. Methods: This prospective, comparative study included 23 patients. All participants were examined with colonoscopy with colonic mucosal biopsy and a bowel transit time test using SITZMARKS^® markers. The following bioamines were assessed in the colonic mucosa: 3-methoxy-4-hydroxyphenylglycol (MHPG), norepinephrine (NA), dopamine (DA), homovanillic acid (HVA), 5-hydroxytryptamine (5-HT, serotonin), and 5-hydroxyindoleacetic acid (5-HIAA). Results: Among study participants, 14 had colonic diverticulosis and 9 were controls. There were no differences in age, sex, body mass, or weight between the groups. All patients with diverticulosis had left-sided diverticula and a DICA score of 1. None of the patients met the diagnostic criteria outlined in the ROME IV classification of functional gastrointestinal disorders. After 48 h, patients with diverticulosis tended to retain less SITZMARKS^® markers (mean of 1.14 vs. 6.78, p < 0.027), compared to the control group. Fewer patients with diverticulosis tended to have SITZMARKS^® markers visible in the X-ray image at 48 h (2 out of 14 versus 4 out of 9 patients, p < 0.262), compared to the control group. There were no differences in colonic mucosal concentrations of bioamines (5-HT, 5-HIAA, MHPG, NA, DA, HVA) between cases and controls. Conclusions: Bowel transit time in patients with colonic diverticulosis may be accelerated compared with controls, and this appears unrelated to bioamine metabolism. Full article

Artificial Intelligence (AI) plays an important role in driving innovation in smart healthcare by providing accurate, scalable, and privacy-preserving diagnostic options. Pneumonia is still a major global health issue, and early detection is key to improving patient outcomes. This study proposes a federated deep learning (FL) approach for automatic pneumonia detection using chest X-ray images, considering both diagnostic efficacy and data privacy. Two models were developed and tested: a custom-developed convolutional neural network and a VGG16 transfer learning architecture. The framework evaluates diagnostic efficacy in both centralized and federated scenarios, taking into account heterogeneous client distributions and class imbalance. F1-score and accuracy values for the federated models indicate competitive levels, with F1-scores greater than 0.90 for pneumonia, being robust even when the data is not independent and identically distributed. Results confirm that FL could be tested as a privacy-preserving way to manage medical imaging and intelligence across distributed healthcare. This study provides a potential proof of concept of how to incorporate federated AI into smart healthcare and gives direction toward clinically tested and real-world applications. Full article