Search Results (119)

Artificial intelligence (AI) is increasingly used to support tuberculosis (TB) screening and diagnosis, particularly through computer-aided detection (CAD) applied to chest radiography (CXR). However, the programmatic value of AI depends not only on diagnostic accuracy but also on implementation context, threshold calibration, and integration into diagnostic pathways. We conducted a narrative, state-of-the-art review of AI applications across the TB diagnosis pathway. Evidence was synthesized from World Health Organization policy documents, independent validation initiatives, and peer-reviewed studies published between 2010 and 2026, with a structured selection process aligned with PRISMA principles. CAD for CXR is the most mature AI application and is recommended by WHO for TB screening and triage among individuals aged ≥15 years in specific contexts. Across studies, CAD-CXR demonstrates sensitivity comparable to human readers, although performance varies by product, population, and imaging conditions, necessitating local threshold calibration. Evidence from implementation studies suggests improvements in screening efficiency and potential cost-effectiveness in high-burden settings. Other AI modalities, including computed tomography (CT)-based imaging analysis, point-of-care ultrasound interpretation, cough or stethoscope sound analysis, clinical risk models, and genomic resistance prediction show promising but heterogeneous results, with most requiring further independent validation and prospective evaluation. AI has the potential to strengthen TB screening and diagnostic pathways, but its impact depends on integration into health systems and evaluated using patient- and program-level outcomes rather than accuracy alone. A differentiated approach is needed, with responsible scale-up of policy-endorsed tools alongside rigorous evaluation of emerging technologies to support effective and equitable TB care. Full article

Objectives: This scoping review synthesized the available evidence on bedside ultrasonography used to confirm short-term nasogastric tube (NGT) placement in adults. Methods: The review followed JBI Collaboration methodology. Searches were conducted in CINAHL, Embase, LILACS, PubMed, and Scopus, as well as in gray literature sources (Google Scholar and ProQuest Dissertation & Thesis Global). Primary studies and clinical guidelines addressing bedside ultrasonography for short-term NGT placement in adults (≥18 years) were eligible, with no limits on language or publication year. Data were extracted and narratively summarized with the I-AIM framework (Indication, Acquisition, Interpretation, and Decision-Making). Results: Twenty-nine studies met the inclusion criteria. Most were single-center observational studies performed in intensive care units or emergency departments. Ultrasound was primarily used for confirmation prior to enteral nutrition initiation, while gastric decompression was less frequently reported. Acquisition protocols varied, although supine positioning, convex abdominal probes, and linear cervical probes were most commonly described. The gastric antrum and esophagus were the principal anatomical landmarks, with interpretation based on direct tube visualization and dynamic fogging; color Doppler was occasionally used. Radiography remained the reference standard in most studies, and only a minority initiated feeding based solely on ultrasound findings. Reported facilitators included bedside feasibility, absence of radiation exposure, and timeliness. Barriers included operator dependency, limited visualization in patients with obesity or gas interposition, protocol heterogeneity, and the limited methodological robustness of available studies. Conclusions: Current evidence suggests that ultrasonography may represent a feasible, radiation-free bedside approach for confirmation of NGT placement. Evidence from selected studies suggests that, with structured training, healthcare professionals may achieve diagnostic accuracy in specific clinical settings, although further robust multicenter investigations are needed to confirm these findings. Full article

Background/Objectives: Radiological assessment has become indispensable for modern clinical decision-making. Image quality plays a critical role in the reliability of radiological interpretation. Unlike most previous studies, this study investigated the effect of monitor type on diagnostic accuracy and ease of diagnosis under physical conditions outside the radiology unit. Methods: Three image sets were prepared for the study, consisting of emergency radiological images, each containing 50 computed tomography, magnetic resonance imaging, and digital radiography images. The image sets were examined by five emergency specialists, who were blinded to each other’s work, under emergency service conditions on a standard monitor (SM), medical monitor (MM), and advanced monitor (AM). The accuracy and ease of diagnosis were analyzed statistically according to the type of monitor used. Results: Overall diagnostic accuracy rates were 98.7% for SM, 100% for AM, and 100% for MM. Cochran’s Q test demonstrated a statistically significant difference between monitor types (p = 0.002), with significant pairwise differences for SM–AM and SM–MM comparisons. The absolute risk difference between SM and AM/MM was 1.3%, corresponding to a relative risk of 1.013 and a number needed to benefit (NNB) of 77. Ease of diagnosis scores increased progressively across monitor types (SM: 7.6 [IQR 7–8], AM: 9.4 [IQR 9–9.8], MM: 9.8 [IQR 9.6–10]; p < 0.001), with a large overall effect size (Kendall’s W = 0.81). Multilevel modeling confirmed that these associations persisted after adjustment for clustering effects. Conclusions: In situations where medical monitors cannot be used due to cost and operational constraints, opting for advanced monitors instead of standard monitors may modestly improve diagnostic accuracy while substantially enhancing perceived ease of diagnosis. Full article

Background: Pneumonia-associated sepsis constitutes a significant portion of all sepsis cases and is a leading cause of sepsis-related morbidity and mortality. The clinical burden is especially pronounced in general ward settings, where delayed recognition can hinder timely intervention. This underscores the necessity for advanced tools that facilitate early detection. Methods: This retrospective, single-center study assessed an AI-driven deep learning model designed to predict in-hospital sepsis up to four hours in advance. We analyzed 7715 pneumonia cases identified through chest radiography or CT. The model’s performance was evaluated using AUROC, sensitivity, specificity, and lead time to sepsis onset and was compared against established scoring systems: NEWS, MEWS, SOFA, and qSOFA. Sepsis was defined according to the CDC Adult Sepsis Event criteria in alignment with Sepsis-3 guidelines. Results: The AI model exhibited strong performance in the early detection of sepsis among pneumonia patients, achieving an AUROC of 0.870, with a sensitivity of 76.7% and specificity of 84.1%. It significantly surpassed conventional scoring systems: NEWS (0.697), MEWS (0.661), SOFA (0.649), and qSOFA (0.678). Importantly, the model identified sepsis a median of 183 min earlier than recognition based on the operational definition. This lead-time advantage was consistent in the pneumonia cohort, where 18.3% of patients developed sepsis. Conclusions: The AI model demonstrated strong predictive capabilities for pneumonia-associated sepsis, facilitating earlier clinical decision-making. Integrating this model into EMR systems could be an effective strategy to enhance sepsis outcomes in general ward settings. Further prospective studies are needed to validate its effectiveness in real-time clinical applications. Full article

Inhalation of foreign material is an uncommon condition that occurs more often in dogs than cats. The main aim of this study was to describe signalment, diagnostic investigation, management and outcomes of dogs and cats with tracheobronchial foreign bodies (TBFBs) in four UK referral centres. Ninety-two dogs and 14 cats with a diagnosis of intraluminal TBFBs between January 2012 and July 2019 were included. Labrador retriever was the most commonly represented canine breed (22/92). Cough was the most common presenting complaint, occurring in 89/92 dogs and 9/14 cats. Summer seasonality was recorded in 74/88 dogs, but no feline seasonality was observed. Radiographic suspected TBFB location agreed with definitive location in 15/22 dogs and 2/2 cats. CT-suspected TBFB location and definitive location agreed in 45/46 dogs and 4/5 cats. Most common TBFB location was right caudal lobe bronchus in dogs (35/97) and trachea in cats (6/14). One of 100 canine TBFBs and nine of 14 feline TBFBs were non-vegetal. Single-attempt bronchoscopic retrieval was successful in 88/92 dogs and 13/14 cats. Surgical retrieval was performed in 4/92 dogs. All patients survived to discharge. This study suggests a pattern of canine TBFB seasonality in the UK. Imaging was useful to guide localisation, and CT appeared more accurate at predicting TBFB location than radiography in dogs. Bronchoscopic TBFB removal was commonly successful, with excellent survival rates. Presenting signs, patterns of seasonality, imaging findings, and management outcomes are useful to help clinical reasoning and decision management in the practical setting. Full article

Pneumonia is one of the main reasons for child mortality, with chest radiography (CXR) being essential for its diagnosis. However, the low radiation exposure in pediatric analysis complicates the accurate detection of pneumonia, making traditional examination ineffective. Progress in medical imaging with convolutional neural networks (CNN) has considerably improved performance, gaining widespread recognition for its effectiveness. This paper proposes an accurate pneumonia detection method based on different deep CNN architectures that combine optimal feature fusion. Enhanced VGG-19, ResNet-50, and MobileNet-V2 are trained on the most widely used pneumonia dataset, applying appropriate transfer learning and fine-tuning strategies. To create an effective feature input, the Chi-Square technique removes inappropriate features from every enhanced CNN. The resulting subsets are subsequently fused horizontally, to generate more diverse and robust feature representation for binary classification. By combining 1000 best features from VGG-19 and MobileNet-V2 models, the suggested approach records the best accuracy (97.59%), Recall (98.33%), and F1-score (98.19%) on the test set based on the supervised support vector machines (SVM) classifier. The achieved results demonstrated that our approach provides a significant enhancement in performance compared to previous studies using various ensemble fusion techniques while ensuring computational efficiency. We project this fused-feature system to significantly aid timely detection of childhood pneumonia, especially within constrained healthcare systems. Full article

Background: Dental disorders, such as cavities, periodontal disease, and periapical infections, remain major global health issues, often resulting in pain, tooth loss, and systemic complications if not identified early. Traditional diagnostic methods rely heavily on visual inspection and manual interpretation of panoramic X-ray images by dental professionals, making them time-consuming, subjective, and less accessible in resource-limited settings. Objectives: Accurate and timely diagnosis is vital for effective treatment and prevention of disease progression, reducing healthcare costs and patient discomfort. Recent advances in deep learning (DL) have demonstrated remarkable potential to automate and improve the precision of dental diagnostics by objectively analyzing panoramic, periapical, and bitewing X-rays. Methods: In this research, a hybrid feature-fusion framework is proposed. It integrates handcrafted Histogram of Oriented Gradients (HOG) features with deep representations from DenseNet-201 and the Shifted Window (Swin) Transformer models. Sequential dependencies among the fused features were learned utilizing the Long Short-Term Memory (LSTM) classifier. The framework was evaluated on the Dental Radiography Analysis and Diagnosis (DRAD) dataset following preprocessing steps, including resizing, normalization, Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement, and image cropping. Results: The proposed LSTM-based hybrid model achieved 96.47% accuracy, 91.76% specificity, 94.92% precision, 91.76% recall, and 93.14% F1-score. Conclusions: The proposed framework offers flexibility, interpretability, and strong empirical performance, making it suitable for various image-based recognition applications and serving as a reproducible framework for future research on hybrid feature fusion and sequence-based classification. Full article

Background/Objectives: Vertical root fractures (VRFs) present significant diagnostic challenges due to their subtle radiographic features and variability across imaging modalities. Artificial intelligence (AI) offers potential to improve detection accuracy, yet evidence regarding its performance across different imaging systems remains fragmented. To critically evaluate current evidence on AI-assisted detection of VRFs across periapical radiography, panoramic radiography, and cone-beam computed tomography (CBCT) and to compare diagnostic performance, methodological strengths, and limitations. Methods: A systematic review of literature up to January 2025 was carried out using databases such as PubMed, Scopus, Web of Science, and the Cochrane Library. The studies included in this review utilized AI-based techniques for detecting VRF through periapical, panoramic, or CBCT imaging. Extracted data encompassed study design, AI models, dataset sizes, preprocessing methods, imaging parameters, validation techniques, and diagnostic metrics. The risk of bias in these studies was evaluated using the QUADAS-2 tool. Results: Ten studies met inclusion criteria; CNN-based models predominated, with performance highly dependent on imaging modality. CBCT-based AI systems achieved the highest diagnostic accuracy (91.4–97.8%) and specificity (90.7–100%), followed by periapical radiography models with accuracies up to 95.7% in controlled settings. Panoramic radiography models demonstrated lower sensitivity (0.45–0.75) but maintained high precision (0.93) in certain contexts. Most studies reported improvements over human performance, yet limitations included small datasets, heterogeneous methodologies, and risk of overfitting. Conclusions: AI-assisted VRF detection shows promising accuracy, particularly with CBCT imaging, but current evidence is constrained by methodological variability and limited clinical validation. Full article

Background: Intraoral radiography remains highly operator-dependent, with small deviations in beam angulation or receptor placement leading to geometric distortions, diagnostic inaccuracies, and repeated exposures. This pilot study introduces and evaluates a gyroscopic-guided, laser-assisted radiographic device designed to standardize cone positioning and improve the geometric reliability of bisecting-angle intraoral radiographs. Methods: Eighteen dental graduates and practitioners performed periapical radiographs on phantom models using a charge-coupled device (CCD) sensor over six months. Each participant obtained six standardized projections with and without the device, yielding 200 analysable radiographs. Radiographic linear measurements included tooth height (occluso–apical dimension) and tooth width (mesio-distal diameter), which were compared with reference values obtained using the paralleling technique. Radiographic errors—including cone cut, elongation, proximal overlap, sliding occlusal plane deviation, and apical cut—were recorded and compared between groups. Results: Use of the gyroscopic-guided device significantly enhanced geometric accuracy. Height measurements showed a strong correlation with reference values in the device group (r = 0.942; R² = 0.887) compared with the non-device technique (r = 0.767; R² = 0.589; p < 0.0001). Width measurements demonstrated similar improvement (device: r = 0.878; R² = 0.770; non-device: r = 0.748; R² = 0.560; p < 0.0001). Overall, the device reduced technical radiographic errors by approximately 62.5%, with significant reductions in cone cut, elongation, proximal overlap, sliding occlusal plane errors, and tooth-centering deviations. Conclusions: Integrating gyroscopic stabilization with laser trajectory guidance substantially improves the geometric fidelity, reproducibility, and diagnostic quality of intraoral radiographs. By minimizing operator-dependent variability, this innovation has the potential to reduce repeat exposures and enhance clinical diagnostics. Further clinical trials are recommended to validate performance in patient-based settings. Full article

Chest radiography remains one of the most frequently performed imaging examinations, highlighting the need for optimization of acquisition parameters to balance image quality and radiation dose. This study presents a phantom-based quantitative evaluation of chest radiography acquisition settings using a digital radiography system (AGFA DR 600). Measurements were performed at three tube voltage levels across simulated patient-equivalent thicknesses generated using PMMA slabs, with a Leeds TOR 15FG image quality phantom positioned centrally in the imaging setup. Image quality was quantitatively assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), which were calculated from mean pixel values obtained from repeated acquisitions. Radiation exposure was evaluated through estimation of entrance surface dose (ESD). The analysis demonstrated that dose-normalized performance metrics favored intermediate tube voltages for slim and average patient-equivalent thicknesses, while higher voltages were required to maintain image quality in obese-equivalent conditions. Overall, image quality and dose were found to be strongly dependent on the combined selection of tube voltage and phantom thickness. These findings indicate that modest adjustments to tube voltage selection may improve the balance between image quality and radiation dose in chest radiography. Nevertheless, as the present work is based on phantom measurements, further validation using clinical images and observer-based studies is required before any modification of routine radiographic practice. Full article

Background/Objectives: Chest radiography is the primary first-line imaging tool for diagnosing pneumothorax in pediatric emergency settings. However, interpretation under clinical pressures such as high patient volume may lead to delayed or missed diagnosis, particularly for subtle cases. This study aimed to evaluate the diagnostic performance of ChatGPT-5, a multimodal large language model, in detecting and localizing pneumothorax on pediatric chest radiographs using multiple prompting strategies. Methods: In this retrospective study, 380 pediatric chest radiographs (190 pneumothorax cases and 190 matched controls) from a tertiary hospital were interpreted using ChatGPT-5 with three prompting strategies: instructional, role-based, and clinical-context. Performance metrics, including accuracy, sensitivity, specificity, and conditional side accuracy, were evaluated against an expert-adjudicated reference standard. Results: ChatGPT-5 achieved an overall accuracy of 0.77–0.79 and consistently high specificity (0.96–0.98) across all prompts, with stable reproducibility. However, sensitivity was limited (0.57–0.61) and substantially lower for small pneumothoraces (American College of Chest Physicians [ACCP]: 0.18–0.22; British Thoracic Society [BTS]: 0.41–0.46) than for large pneumothoraces (ACCP: 0.75–0.79; BTS: 0.85–0.88). The conditional side accuracy exceeded 0.96 when pneumothorax was correctly detected. No significant differences were observed among prompting strategies. Conclusions: ChatGPT-5 showed consistent but limited diagnostic performance for pediatric pneumothorax. Although the high specificity and reproducible detection of larger pneumothoraces reflect favorable performance characteristics, the unacceptably low sensitivity for subtle pneumothoraces precludes it from independent clinical interpretation and underscores the necessity of oversight by emergency clinicians. Full article

Background/Objectives: diabetic foot osteomyelitis (DFO) is a serious complication characterized by bone infection that can involve cortical structures, bone marrow, and surrounding soft tissues. Its prevalence ranges from 20% in moderate diabetic foot infections to over 50% in severe cases, making accurate diagnosis essential in guiding timely and effective management. in this study, we aimed to evaluate the diagnostic accuracy achieved by combining the probe-to-bone (PTB) test, plain radiography, and blood biomarkers—including the erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP)—in the diagnosis of DFO. Methods: we conducted a diagnostic accuracy study involving 128 patients with diabetic foot ulcers and clinical suspicion of DFO. The sensitivity, specificity, positive predictive value, and negative predictive value were calculated for individual tests and for their diagnostic combinations. Results: the combination of PTB and biomarkers yielded a sensitivity of 75%, a specificity of 24%, a positive predictive value of 69%, and a negative predictive value of 29%. Similarly, the combination of PTB and plain radiography showed a sensitivity of 76%, a specificity of 23%, a positive predictive value of 62%, and a negative predictive value of 38%. When the three diagnostic modalities were analyzed together, the sensitivity reached 75%, and the specificity reached 23%. Conclusions: the combination of PTB and inflammatory biomarkers demonstrated moderate effectiveness and diagnostic performance comparable to PTB combined with radiography. These findings suggest that biomarkers may serve as a practical and accessible diagnostic adjunct in settings where imaging availability is limited or radiographic interpretation is challenging. Full article

The hospital-at-home (HaH) model delivers hospital-level care to patients in their homes, with point-of-care ultrasonography (PoCUS) serving as a cornerstone diagnostic tool for respiratory illnesses such as pneumonia. This review—the third in a series—addresses the prognostic, synchronous, and potential overdiagnostic concerns of lung ultrasound (LUS) in managing pneumonia within HaH settings. LUS offers advantages of safety and repeatability, allowing clinicians to identify “red flag” sonographic findings that signal complicated or severe disease, including pleural line abnormalities, fluid bronchograms, absent Doppler perfusion, or poor diaphragmatic motion. Serial LUS examinations correlate closely with clinical recovery, showing progressive resolution of consolidations, B-lines, and pleural effusions, and thus provide a non-invasive method for monitoring therapeutic response. Compared with chest radiography, LUS demonstrates superior sensitivity in detecting pneumonia, pleural effusion, and interstitial syndromes across pediatric and adult populations. However, specificity may decline in tuberculosis-endemic or obese populations due to technical limitations and overlapping imaging patterns. Overdiagnosis remains a concern, as highly sensitive ultrasonography may identify minor or clinically irrelevant lesions, potentially leading to overtreatment. To mitigate this, PoCUS should be applied in parallel with conventional diagnostics and integrated into comprehensive clinical assessment. Standardized training, multi-zone scanning protocols, and structured image acquisition are recommended to improve reproducibility and inter-operator consistency. Full article

Automatic radiology report generation (ARRG) has emerged as a promising application of deep learning (DL) with the potential to alleviate reporting workload and improve diagnostic consistency. However, despite rapid methodological advances, the field remains technically fragmented and not yet mature for routine clinical adoption. This scoping review maps the current ARRG research landscape by examining DL architectures, multimodal integration strategies, and evaluation practices from 2015 to April 2025. Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, a comprehensive literature search identified 89 eligible studies, revealing a marked predominance of chest radiography datasets (87.6%), primarily driven by their public availability and the accelerated development of automated tools during the COVID-19 pandemic. Most models employed hybrid architectures (73%), particularly CNN–Transformer pairings, reflecting a shift toward systems that combine local feature extraction with global contextual reasoning. Although these approaches have achieved measurable gains in textual and semantic coherence, several challenges persist, including limited anatomical diversity, weak alignment with radiological rationale, and evaluation metrics that insufficiently reflect diagnostic adequacy or clinical impact. Overall, the findings indicate a rapidly evolving but clinically immature field, underscoring the need for validation frameworks that more closely reflect radiological practice and support future deployment in real-world settings. Full article

Diagnosing fractures in hummingbirds is challenging because of their small size. This study evaluated the diagnostic performance and inter-reviewer agreement of four imaging modalities—conventional radiography, dental radiography, micro-computed tomography (micro-CT), and three-dimensional (3D)-reconstructed images from micro-CT scans—for identifying fractures in 16 ruby-throated hummingbirds (Archilochus colubris) admitted to a wildlife hospital. Six independent reviewers, with or in training for a specialty in veterinary radiology or wildlife medicine, assessed randomized image sets. Gross dissection of the carcasses using dermestid beetle larvae established the gold standard. Diagnostic performance metrics—sensitivity, specificity, predictive values, and likelihood ratios—were calculated for each modality. Inter-reviewer agreement was assessed using Fleiss’ kappa. Our results demonstrated that advanced imaging techniques improved diagnostic performance and inter-reviewer agreement compared to traditional radiography. While specificity (>88%) was comparable to other small animal studies, the sensitivity did not exceed 50% across all modalities. This low sensitivity reflects the challenges posed by minimal fracture displacement and hummingbirds’ extremely small size. Only 3D images achieved high positive likelihood ratios and superior inter-reviewer agreement, highlighting the unique value of 3D visualization in complex anatomical evaluations. Overall, the minute structures of hummingbirds present inherent diagnostic limitations, underscoring that negative radiographic results must be interpreted cautiously, and the possibility of false negatives should prompt consideration of advanced or follow-up imaging when clinical suspicion persists. Full article