Search Results (264)

Background: Chest X-ray (CXR) is widely used for the assessment of thoracic diseases, yet automated multi-label interpretation remains challenging due to subtle visual patterns, overlapping anatomical structures, and frequent co-occurrence of abnormalities. While recent deep learning models have shown strong performance, limitations in interpretability, anatomical awareness, and robustness continue to hinder their clinical adoption. Methods: The proposed framework employs a hybrid ConvNeXtV2–Vision Transformer (ViT) architecture that combines convolutional feature extraction for capturing fine-grained local patterns with transformer-based global reasoning to model long-range contextual dependencies. The model is trained exclusively using image-level annotations. In addition to classification, three complementary post hoc components are integrated to enhance model trust and interpretability. A segmentation-aware Gradient-weighted class activation mapping (Grad-CAM) module leverages CheXmask lung and heart segmentations to highlight anatomically relevant regions and quantify predictive evidence inside and outside the lungs. An ontology-driven neuro-symbolic reasoning layer translates Grad-CAM activations into structured, rule-based explanations aligned with clinical concepts such as “basal effusion” and “enlarged cardiac silhouette”. Furthermore, a lightweight out-of-distribution (OOD) detection module based on confidence scores, energy scores, and Mahalanobis distance scores is employed to identify inputs that deviate from the training distribution. Results: On the VinBigData test set, the model achieved a macro-AUROC of 0.9525 and a Micro AUROC of 0.9777 when trained solely with image-level annotations. External evaluation further demonstrated strong generalisation, yielding macro-AUROC scores of 0.9106 on NIH ChestXray14 and 0.8487 on CheXpert (frontal views). Both Grad-CAM visualisations and ontology-based reasoning remained coherent on unseen data, while the OOD module successfully flagged non-thoracic images. Conclusions: Overall, the proposed approach demonstrates that hybrid convolutional neural network (CNN)–vision transformer (ViT) architectures, combined with anatomy-aware explainability and symbolic reasoning, can support automated chest X-ray diagnosis in a manner that is accurate, transparent, and safety-aware. Full article

Background/Objective: Pulmonary impairments have been identified as some of the most complex and debilitating post-acute sequelae of SARS-CoV-2 infection (PASC) or long COVID. This study identified and characterised the specific forms of pulmonary impairments detected using pulmonary function tests (PFT), chest X-rays (CXR), and computed tomography (CT) scans in patients with long COVID symptoms. Methods: We conducted a single-centre retrospective study to evaluate 60 patients with long COVID who underwent PFT, CXR, and CT scans. Pulmonary function in long COVID patients was assessed using defined thresholds for key test parameters, enabling categorisation into normal, restrictive, obstructive, and mixed lung-function patterns. We applied exact binomial (Clopper–Pearson) 95% confidence intervals to calculate the proportions of patients falling below the defined thresholds. We also assessed the relationships among spirometric indices, lung volumes, and diffusion capacity (DLCO) using scatter plots and corresponding linear regressions. The findings from the CXRs and CT scans were categorised, and their prevalence was calculated. Results: A total of 60 patients with long COVID symptoms (mean age 60 ± 13 years; 57% female) were evaluated. The cohort was ethnically diverse and predominantly non-smokers, with a mean BMI of 32.4 ± 6.3 kg/m². PFT revealed that most patients had preserved spirometry, with mean Forced Expiratory Volume in 1 Second (FEV1) and Forced Vital Capacity (FVC) above 90% predicted. However, a significant proportion exhibited reductions in lung volumes, with total lung capacity (TLC) decreasing in 35%, and diffusion capacity (DLCO/TLCO) decreasing in 75%. Lung function pattern analysis showed 88% of patients had normal function, while 12% displayed a restrictive pattern; no obstructive or mixed patterns were observed. Radiographic assessment revealed that 58% of chest X-rays were normal, whereas CT scans showed ground-glass opacities (GGO) in 65% of patients and fibrotic changes in 55%, along with findings such as atelectasis, air trapping, and bronchial wall thickening. Conclusions: Spirometry alone is insufficient to detect impairment of gas exchange or underlying histopathological changes in patients with long COVID. Our findings show that, despite normal spirometry results, many patients exhibit significant diffusion impairment, fibrotic alterations, and ground-glass opacities, indicating persistent lung and microvascular damage. These results underscore the importance of comprehensive assessment using multiple diagnostic tools to identify and manage chronic pulmonary dysfunction in long COVID. Full article

Chest X-ray radiology report generation is a challenging task that involves techniques from medical natural language processing and computer vision. This paper provides a comprehensive overview of recent progress. The annotation protocols, structure, linguistic characteristics, and size of the main public datasets are presented and compared. Understanding their properties is necessary for benchmarking and generalization. Both clinically oriented and natural language generation metrics are included in the model evaluation strategies to assess their performance. Their respective strengths and limitations are discussed in the context of radiology applications. Recent deep learning approaches for report generation and their different architectures are also reviewed. Common trends such as instruction tuning and the integration of clinical knowledge are also considered. Recent works show that current models still have limited factual accuracy, with a score of 72% reported with expert evaluations, and poor performance on rare pathologies and lateral views. The most important challenges are the limited dataset diversity, weak cross-institution generalization, and the lack of clinically validated benchmarks for evaluating factual reliability. Finally, we discuss open challenges related to data quality, clinical factuality, and interpretability. This review aims to support researchers by synthesizing the current literature and identifying key directions for developing more clinically reliable report generation systems. Full article

Early and accurate diagnosis of lung diseases is essential for effective treatment and patient management. Conventional diagnostic models trained on a single data type often miss important clinical information. This study explored a multimodal deep learning framework that integrates cough sounds, chest radiograph (X-rays), and computed tomography (CT) scans to enhance disease classification performance. Two fusion strategies, early and intermediate fusion, were implemented and evaluated against three single-modality baselines. The dataset was collected from different sources. Each dataset underwent preprocessing steps, including noise removal, grayscale conversion, image cropping, and class balancing, to ensure data quality. Convolutional neural network (CNN) and Extreme Inception (Xception) architectures were used for feature extraction and classification. The results show that multimodal learning achieves superior performance compared with single models. The intermediate fusion model achieved 98% accuracy, while the early fusion model reached 97%. In contrast, single CXR and CT models achieved 94%, and the cough sound model achieved 79%. These results confirm that multimodal integration, particularly intermediate fusion, offers a more reliable framework for automated lung disease diagnosis. Full article

Objectives: The purpose of this study was to evaluate the trends and changes in the time to medical imaging in the emergency department (ED) for patients with cardiopulmonary symptoms during the coronavirus disease 2019 (COVID-19) pandemic. Methods: The retrospective observational study was conducted from the clinical database of a tertiary academic teaching hospital. Patients with cardiopulmonary symptoms (chest pain, dyspnea, palpitation and syncope) who visited an adult ED between January 2018 and December 2021 were included. The primary outcome was the time to medical imaging, including chest X-ray (CXR), chest computed tomography (CT), and focused cardiac ultrasound (FOCUS). The primary exposure was the date of the ED visit during the COVID-19 pandemic (from 1 March 2020 to 31 December 2021). Results: Among the 28,213 patients, 17,260 (61.2%) were in the pre-COVID-19 group, and 10,953 (38.8%) were in the COVID-19 group. The time to medical imaging was delayed in the COVID-19 group compared with the pre-COVID-19 group: the time to FOCUS was 9 min, the time to CXR was 6 min, and the time to chest CT was 115 min. Conclusions: We found that the time to medical imaging for patients with cardiopulmonary symptoms who visited the ED was significantly delayed during the COVID-19 pandemic. Full article

Background: Chest X-ray (CXR) imaging is crucial for diagnosing thoracic abnormalities; however, the rising demand burdens radiologists, particularly in resource-limited settings. Method: We used large-scale, diverse public CXR datasets with noisy labels to train general-purpose deep learning models (ResNet, DenseNet, EfficientNet, and DLAD-10) for multi-label classification of thoracic conditions. Uncertainty quantification was incorporated to assess model reliability. Performance was evaluated on both internal and external validation sets, with analyses of data scale, diversity, and fine-tuning effects. Result: EfficientNet achieved the highest overall area under the receiver operating characteristic curve (0.8944) with improved sensitivity and F1-score. Moreover, as training data volume increased—particularly using multi-source datasets—both diagnostic performance and generalizability were enhanced. Although larger datasets reduced predictive uncertainty, conditions such as tuberculosis remained challenging due to limited high-quality samples. Conclusions: General-purpose deep learning models can achieve robust CXR diagnostic performance when trained on large-scale, diverse public datasets despite noisy labels. However, further targeted strategies are needed for underrepresented conditions. Full article

Automated radiology report generation from chest X-rays presents a critical challenge in medical imaging. Traditional image-captioning models struggle with clinical specificity and rare pathologies. Recently, contrastive vision language learning has emerged as a robust alternative that learns joint visual–textual representations. However, applying contrastive learning (CL) to radiology remains challenging due to severe data scarcity. Prior work has employed input space augmentation, but these approaches incur computational overhead and risk distorting diagnostic features. This work presents CL with feature space interpolation for retrieval (CLFIR), a novel CL framework operating on learned embeddings. The method generates interpolated pairs in the feature embedding space by mixing original and shuffled embeddings in batches using a mixing coefficient $\lambda \sim U(0.85,0.99)$. This approach increases batch diversity via synthetic samples, addressing the limitations of CL on medical data while preserving diagnostic integrity. Extensive experiments demonstrate state-of-the-art performance across critical clinical validation tasks. For report generation, CLFIR achieves BLEU-1/ROUGE/METEOR scores of 0.51/0.40/0.26 (Indiana university [IU] X-ray) and 0.45/0.34/0.22 (MIMIC-CXR). Moreover, CLFIR excels at image-to-text retrieval with R@1 scores of 4.14% (IU X-ray) and 24.3% (MIMIC-CXR) and achieves 0.65 accuracy in zero-shot classification on the CheXpert5×200 dataset, surpassing the established vision-language models. Full article

This study presents a controlled benchmarking analysis of min–max scaling, Z-score normalization, and an adaptive preprocessing pipeline that combines percentile-based ROI cropping with histogram standardization. The evaluation was conducted across four public chest X-ray (CXR) datasets and three convolutional neural network architectures under controlled experimental settings. The adaptive pipeline generally improved accuracy, F1-score, and training stability on datasets with relatively stable contrast characteristics while yielding limited gains on MIMIC-CXR due to strong acquisition heterogeneity. Ablation experiments showed that histogram standardization provided the primary performance contribution, with ROI cropping offering complementary benefits, and the full pipeline achieving the best overall performance. The computational overhead of the adaptive preprocessing was minimal (+6.3% training-time cost; 5.2 ms per batch). Friedman–Nemenyi and Wilcoxon signed-rank tests confirmed that the observed improvements were statistically significant across most dataset–model configurations. Overall, adaptive normalization is positioned not as a novel algorithmic contribution, but as a practical preprocessing design choice that can enhance cross-dataset robustness and reliability in chest X-ray classification workflows. Full article

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

This study proposes a unified deep-learning framework for the concurrent classification of Chronic Obstructive Pulmonary Disease (COPD) severity and regression of the FEV1/FVC ratio from chest X-ray (CXR) images. We integrated a ConvNeXt-Large backbone with a Slot Attention mechanism to effectively disentangle and refine disease-relevant features for multi-task learning. Evaluation on a clinical dataset demonstrated that the proposed model with a 5-slot configuration achieved superior performance compared to standard CNN and Vision Transformer baselines. On the independent test set, the model attained an Accuracy of 0.9107, Sensitivity of 0.8603, and Specificity of 0.9324 for three-class severity stratification. Simultaneously, it achieved a Mean Absolute Error (MAE) of 8.2649 and a Mean Squared Error (MSE) of 151.4704, and an ${\mathrm{R}}^2$ of 0.7591 for FEV1/FVC ratio estimation. Qualitative analysis using saliency maps also suggested that the slot-based approach contributes to attention patterns that are more constrained to clinically relevant pulmonary structures. These results suggest that our slot-attention-based multi-task model offers a robust solution for automated COPD assessment from standard radiographs. 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: Silicosis, a fibrotic lung disease, is re-emerging globally, driven by an aggressive form linked to engineered stone processing that rapidly progresses to progressive massive fibrosis (PMF). The standard diagnostic approach, chest X-ray (CXR), is subject to considerable inter-observer variability, making the distinction between simple silicosis (SS) and PMF particularly challenging. The purpose of this study was to develop and validate an automated multimodal framework for silicosis staging by integrating artificial intelligence (AI), CXR images, and routine blood biomarkers. Methods: We developed three fusion architectures, early, late, and hybrid, connecting blood biomarker analysis with CXR analysis. Deep learning and conventional (shallow) machine learning models were combined. The models were trained and validated on a cohort of 94 patients with engineered stone silicosis, providing 341 paired CXR and biomarker samples. A patient-aware 5-fold cross-validation was used to ensure the model’s generalizability and prevent patient data leakage between folds. Results: The hybrid and late fusion models achieved the best performance for disease staging, yielding an area under the receiver operating characteristic (ROC) curve (AUC) of 0.85. This multimodal approach outperformed both the unimodal CXR-based model (AUC = 0.83) and the biomarker-based model (AUC = 0.70). Conclusions: This study reveals that AI-based techniques that utilize a multimodal fusion approach have the potential to outperform single-modality methods have the potential to serve as an objective decision support tool for clinicians, leading to more consistent staging and improved patient management. Full article

Background: The incidence of iatrogenic pneumothorax (IPTX) following transbronchial lung cryobiopsy (TBLCB) ranges from 1.4% to 20.2%. While chest X-ray (CXR) is the standard imaging modality to exclude IPTX, thoracic ultrasound (TUS) has demonstrated superior accuracy in detecting pneumothorax across various contexts. This study evaluates TUS as a reliable alternative to routine CXR for ruling out IPTX after TBLCB. Methods: A retrospective observational study included 51 patients undergoing ambulatory TBLCB. Pre- and post-TBLCB TUS were performed. CXR was reserved for cases where TUS findings were inconclusive (absence of sliding lung [SL] and seashore sign [SS] in any lung zones) or if patients exhibited symptoms or signs of IPTX. Results: TUS findings were concordant in 44 (86.1%) patients, of whom 42 (95.5%) did not require CXR. Two patients (4.5%) with symptomatic IPTX were identified and managed. Among the seven patients (13.7%) requiring CXR due to inconclusive TUS or symptoms, five (71.4%) were negative for IPTX, and two (28.6%) had asymptomatic IPTX. Conclusion: Our TUS protocol effectively ruled out clinically significant IPTX, eliminating routine CXR in 95.5% of patients. TUS is a safe alternative to CXR post-TBLCB, with CXR reserved for inconclusive TUS findings or symptomatic cases. Full article

Background: Routine chest X-rays (CXR) are not recommended by the American Academy of Pediatrics in bronchiolitis, yet remain a mainstay in diagnostics. We aimed to understand the impact of obtaining CXRs in patients with critical bronchiolitis, assessing intensive care unit length of stay (ICU-LOS) and intensive care unit level of respiratory support (ICU-LRS). Methods/Design: This single-center retrospective cohort study assessed children less than three years of age admitted to the PICU, pediatric step-down ICU, and pediatric cardiac ICU. Two groups were used for analysis: patients with CXR and no-CXR. The primary outcome was the difference in ICU-LOS and ICU-LRS between the groups. The critical bronchiolitis score (CBS) was used to calculate a predicted ICU-LOS and ICU-LRS. The secondary outcome was the difference between actual and predicted ICU-LOS and ICU-LRS, comparing the groups. Results: Of the 107 patients included, 65 patients (61%) received a CXR. Patients who received a CXR had significantly longer ICU-LOS (p = 0.01) and ICU-LRS (p = 0.02), despite no difference in predicted illness severity (ICU-LOS, p = 0.4; ICU-LRS, p = 0.3). The difference between actual and predicted ICU-LOS was greater in the no-CXR group (–1.4 days) compared to the CXR group (–0.8 days; p = 0.04). A similar trend was observed in ICU-LRS (–0.1 vs. –0.6 days; p = 0.1), though not statistically significant. Conclusions: Routine CXRs are common in critically ill bronchiolitis patients and may be associated with longer ICU-LOS and ICU-LRS, despite similar illness severity. Full article

Lung ultrasound (LUS) has emerged as a valuable diagnostic modality for the evaluation of respiratory disorders in neonates, infants and children. LUS has high diagnostic accuracy for identification of lung lesions in neonates, infants and children, where most lung lesions abut the pleura. Furthermore, LUS has the advantage of rapid execution and ease of use, and does not require ionizing radiation. Its sensitivity, cost-effectiveness, and clinical efficiency make it an important tool for supporting clinical decision-making and improving patient management. Moreover, LUS may represent a reliable alternative to chest radiography for the assessment of pediatric lung conditions and, in selected cases, could potentially replace routine chest X-rays (CXRs). Because LUS is a user-friendly technique that enables real-time imaging without radiation, it has increasingly been used in clinical practice in recent years. Here, we discuss the diagnostic role of LUS for the accurate identification of pulmonary lesions in pediatric patients. In addition, we present LUS sonographic findings associated with common pediatric lung diseases, including signs and artifacts that can be used during diagnosis and evaluation of pediatric patients. Full article