Search Results (99)

Pneumothorax is a potentially life-threatening condition defined as the collapse of the lung due to air leakage into the chest cavity. Delays in the diagnosis of pneumothorax can lead to severe complications and even mortality. A significant challenge in pneumothorax diagnosis is the shortage of radiologists, resulting in the absence of written reports in plain X-rays and, consequently, impacting patient care. In this paper, we propose an automatic triage system for pneumothorax detection in X-ray images based on deep learning. We address this problem from the perspective of multi-source domain adaptation where different datasets available on the Internet are used for training and testing. In particular, we use datasets which contain chest X-ray images corresponding to different conditions (including pneumothorax). A convolutional neural network (CNN) with an EfficientNet architecture is trained and optimized to identify radiographic signs of pneumothorax using those public datasets. We present the results using cross-dataset validation, demonstrating the robustness and generalization capabilities of our multi-source solution across different datasets. The experimental results demonstrate the model’s potential to assist clinicians in prioritizing and correctly detecting urgent cases of pneumothorax using different integrated deployment strategies. Full article

Background: Influenza B usually causes mild illness in children. Severe and fatal cases can occur when complicated by secondary Staphylococcus aureus (S. aureus) pneumonia, including community-acquired methicillin-resistant Staphylococcus aureus (MRSA). We present a rare, rapidly progressive fatal case in an adolescent with no known medical history to highlight diagnostic and therapeutic pitfalls. Case Presentation: A 16-year-old boy with no known underlying conditions (unvaccinated for influenza) presented critically ill at “Sf. Ioan” Clinical Emergency Pediatric Hospital in Galați after one week of high fever and cough. He was in respiratory failure with septic shock, requiring immediate intubation and vasopressors. Chest X-ray (CXR) showed diffuse bilateral infiltrates (acute respiratory distress syndrome, ARDS). Initial laboratory tests revealed leukopenia, severe thrombocytopenia, disseminated intravascular coagulation (DIC), rhabdomyolysis, and acute kidney injury (AKI). Reverse transcription polymerase chain reaction (RT-PCR) confirmed influenza B, and blood cultures grew MRSA. Despite maximal intensive care, including mechanical ventilation, antibiotics (escalated for MRSA), antiviral therapy, and cytokine hemoadsorption therapy, the patient developed refractory multi-organ failure and died on hospital day 6. Autopsy revealed bilateral necrotizing pneumonia (NP) without radiographic cavitation, underscoring the diagnostic challenge. Discussion: The initial chest radiography showed diffuse bilateral pulmonary infiltrates, predominantly in the lower zones, with an ill-defined, patchy, and confluent appearance. Such appearance, in our case, was more suggestive of rapid progressive NP caused by MRSA rather than the typical pneumococcal one. This is one of the few reported cases of influenza B–MRSA coinfection with fulminant rhabdomyolysis and autopsy-confirmed necrosis. Our fulminant case illustrates the synergistic virulence of influenza and MRSA. Toxin-producing MRSA strains can cause NP and a “cytokine storm,” causing capillary leak, ARDS, shock, and DIC. Once multi-organ failure ensues, the prognosis is grim despite aggressive care. The absence of early radiographic necrosis and delayed anti-MRSA therapy (initiated after culture results) likely contributed to the poor outcome. Conclusions: Influenza B–MRSA co-infection, though rare, demands urgent empiric anti-MRSA therapy in severe influenza cases with leukopenia or shock, even without radiographic necrosis. This fatal outcome underscores the dual imperative of influenza vaccination and early, aggressive dual-pathogen targeting in high-risk presentations. Full article

Deep learning has brought substantial progress to medical imaging, which has resulted in continuous improvements in diagnostic procedures. Through deep learning architecture implementations, radiology professionals achieve automated pathological condition detection, segmentation, and classification with improved accuracy. The research tackles a rarely studied clinical medical imaging issue that involves bullet identification and positioning within X-ray images. The purpose is to construct a sturdy deep learning system that will identify and classify ballistic trauma in images. Our research examined various deep learning models that functioned either as classifiers or as object detectors to develop effective solutions for ballistic trauma detection in X-ray images. Research data was developed by replicating controlled bullet damage in chest X-rays while expanding to a wider range of anatomical areas that include the legs, abdomen, and head. Special deep learning algorithms went through a process of optimization before researchers improved their ability to detect and place objects. Multiple computational systems were used to verify the results, which showcased the effectiveness of the proposed solution. This research provides new perspectives on understanding forensic radiology trauma assessment by developing the first deep learning system that detects and classifies gun-related radiographic injuries automatically. The first system for forensic radiology designed with automated deep learning to classify gunshot wounds in radiographs is introduced by this research. This approach offers new ways to look at trauma which is helpful for work in clinics as well as in law enforcement. Full article

Pneumothorax is a critical condition that requires rapid and accurate diagnosis from standard chest radiographs. Identifying and segmenting the location of the pneumothorax are essential for developing an effective treatment plan. nnUNet is a self-configuring, deep learning-based framework for medical image segmentation. Despite adjusting its parameters automatically through data-driven optimization strategies and offering robust feature extraction and segmentation capabilities across diverse datasets, our initial experiments revealed that nnUNet alone struggled to achieve consistently accurate segmentation for pneumothorax, particularly in challenging scenarios where subtle intensity variations and anatomical noise obscure the target regions. This study aims to enhance the accuracy and robustness of pneumothorax segmentation in low-contrast chest radiographs by integrating spatial prior information and attention mechanism into the nnUNet framework. In this study, we introduce the spatial prior contrast adapter (SPCA)-enhanced nnUNet by implementing two modules. First, we integrate an SPCA utilizing the MedSAM foundation model to incorporate spatial prior information of the lung region, effectively guiding the segmentation network to focus on anatomically relevant areas. In the meantime, a probabilistic atlas, which shows the probability of an area prone to pneumothorax, is generated based on the ground truth masks. Both the lung segmentation results and the probabilistic atlas are used as attention maps in nnUNet. Second, we combine the two attention maps as additional input into nnUNet and integrate an attention mechanism into standard nnUNet by using a convolutional block attention module (CBAM). We validate our method by experimenting on the dataset CANDID-PTX, a benchmark dataset representing 19,237 chest radiographs. By introducing spatial awareness and intensity adjustments, the model reduces false positives and improves the precision of boundary delineations, ultimately overcoming many of the limitations associated with low-contrast radiographs. Compared with standard nnUNet, SPCA-enhanced nnUNet achieves an average Dice coefficient of 0.81, which indicates an improvement of standard nnUNet by 15%. This study provides a novel approach toward enhancing the segmentation performance of pneumothorax with low contrast in chest X-ray radiographs. Full article

X-ray imaging protocols in radiology departments often exhibit variability in exposure parameters and geometric setups, leading to inconsistencies in image quality and potential variations in patient dose. Objectives: This study aimed to harmonise and optimise chest and pelvis X-ray imaging protocols by standardising exposure parameters and geometric setups across departmental systems, minimising radiation dose while ensuring adequate image quality for accurate diagnosis. Methods: The image quality of five pelvic and three chest protocols across different radiographic systems was evaluated both quantitatively and visually. Visual image quality for both chest and pelvis protocols was assessed by radiologists and radiographers using the Visual Grading Analysis (VGA) method. Additionally, the quantitative image quality figure inverse (IQF_inv) metric for all protocols was determined using the CDRAD image quality phantom. Moreover, the patient radiation dose for both chest and pelvis protocols was evaluated using dose area product (DAP) values measured by the systems’ built-in DAP metres. Results: Different quantitative image quality and radiation dose to patients were achieved in various protocol settings for both chest and pelvis examinations, but the visual image quality assessment showed satisfactory image quality for all observers in both the pelvis and chest protocols. The selected protocols for harmonising chest radiography across all imaging systems result in reduced radiation exposure for patients while maintaining adequate image quality compared to the previously used system-specific protocol. Conclusions: The clinical protocol for chest and pelvis radiography has been standardised and optimised in accordance with patient radiation exposure and image quality. This approach aligns with the ALARA (As Low As Reasonably Achievable) principle, ensuring optimal diagnostic information while minimising the radiation risks. Full article

Background: Chest radiography remains a cornerstone of thoracic imaging; however, the influence of patient demographics and technical factors on radiologic findings is not yet fully understood. This study investigates how gender, age, and radiographic projection affect the prevalence of three common findings: atelectasis, pleural effusion, and pulmonary nodules. Methods: We analyzed 112,120 frontal chest radiographs from the publicly available NIH ChestX-ray8 dataset. Gender-specific prevalence rates were compared using chi-square tests and unadjusted odds ratios (ORs). Multivariable logistic regression was performed to assess the independent effects of gender, age, and projection (posteroanterior [PA] vs. anteroposterior [AP]), including interaction terms. Results: Atelectasis and nodules were more prevalent in male patients, with unadjusted rates of 10.9% and 5.8% versus 9.5% and 5.4% in females. While the difference in nodules’ prevalence was not statistically significant (OR = 0.96, p = 0.16), multivariable analysis showed a significant association (adjusted OR = 1.378, 95% CI 1.157–1.641; p = 0.0003). Pleural effusion showed no significant gender difference (11.7% vs. 12.1%; OR 0.97, p = 0.10). Increasing age was consistently associated with higher odds of all findings (ORs per year: 1.016–1.012; all p < 0.0001). The PA view reduced the odds of atelectasis (OR 0.59) and effusion (OR 0.60), but increased the odds of detecting nodules (OR 1.31). Interaction terms showed minor but statistically significant gender-related differences in age effects. Conclusions: Gender, age, and radiographic projection substantially affect the radiographic detection of frequently observed thoracic abnormalities. These findings are directly relevant for improving clinical diagnostic accuracy and for reducing demographic and technical biases in AI-based radiograph interpretation, particularly in critical care and screening settings. Full article

Objective: Reliable reading and annotation of chest X-ray (CXR) images are essential for both clinical decision-making and AI model development. While most of the literature emphasizes pulmonary findings, this study evaluates the consistency and reliability of annotations for extrapulmonary findings, using a labelling scheme. Methods: Six clinicians with varying experience levels (novice, intermediate, and experienced) annotated 100 CXR images using a diagnostic labelling scheme, in two rounds, separated by a three-week washout period. Annotation consistency was assessed using Randolph’s free-marginal kappa (RK), prevalence- and bias-adjusted kappa (PABAK), proportion positive agreement (PPA), and proportion negative agreement (PNA). Pairwise comparisons and the McNemar’s test were conducted to assess inter-reader and intra-reader agreement. Results: PABAK values indicated high overall grouped labelling agreement (novice: 0.86, intermediate: 0.90, experienced: 0.91). PNA values demonstrated strong agreement on negative findings, while PPA values showed moderate-to-low consistency in positive findings. Significant differences in specific agreement emerged between novice and experienced clinicians for eight labels, but there were no significant variations in RK across experience levels. The McNemar’s test confirmed annotation stability between rounds. Conclusions: This study demonstrates that clinician annotations of extrapulmonary findings in CXR are consistent and reliable across different experience levels using a pre-defined diagnostic labelling scheme. These insights aid in optimizing training strategies for both clinicians and AI models. Full article

The term “overkilling” in forensic medicine is not clearly defined and is used to refer to homicides involving unusually massive injuries, far exceeding those necessary to kill the victim. This is the clinical case of a dog found in February 2023 in a town near Naples, with a rope around its neck and the metacarpal region of its forelimbs. The dog was taken to the Istituto Zooprofilattico Sperimentale del Mezzogiorno (IZSM, Portici, Southern Italy), where it underwent a total body radiographic study performed using the “Philosophy HF400” X-ray device (Pan Vet, Kildare Town, Ireland). Subsequently, a full autopsy was performed, and samples of the injured organs were analyzed by accredited in-house laboratories for microbiological, histological and toxicological analyses. The autopsy revealed anatomopathological lesions compatible with strangulation, which were confirmed by histological examination. The autopsy also reported serosanguineous chest effusion, food material mixed with blackish microgranules and harmful substances in the stomach and, finally, uncoagulated blood in the atrioventricular chambers of the heart. These findings raised the suspicion of poisoning, which was confirmed by the positive outcome of toxicological tests. Full article

Background/Objectives: To compare the image quality of chest radiography with a dual-energy X-ray imaging system using AI technology (DE-AI) to that of conventional chest radiography with a standard protocol. Methods: In this prospective study, 52 healthy volunteers underwent dual-energy chest radiography. Images were obtained using two exposures at 60 kVp and 120 kVp, separated by a 150 ms interval. Four images were generated for each participant: a conventional image, an enhanced standard image, a soft-tissue-selective image, and a bone-selective image. A machine learning model optimized the cancellation parameters for generating soft-tissue and bone-selective images. To enhance image quality, motion artifacts were minimized using Laplacian pyramid diffeomorphic registration, while a wavelet directional cycle-consistent adversarial network (WavCycleGAN) reduced image noise. Four radiologists independently evaluated the visibility of thirteen anatomical regions (eight soft-tissue regions and five bone regions) and the overall image with a five-point scale of preference. Pooled mean values were calculated for each anatomic region through meta-analysis using a random-effects model. Results: Radiologists preferred DE-AI images to conventional chest radiographs in various anatomic regions. The enhanced standard image showed superior quality in 9 of 13 anatomic regions. Preference for the soft-tissue-selective image was statistically significant for three of eight anatomic regions. Preference for the bone-selective image was statistically significant for four of five anatomic regions. Conclusions: Images produced by DE-AI provide better visualization of thoracic structures. Full article

The purpose of this study is to determine the typical diagnostic reference levels (DRLs) of radiation exposure values for chest radiographs in neonates (<1 kg) in mobile imaging at a University Hospital in Greece and compare these values with the existing DRL values from the literature. Patient and dosimetry data, including age, sex, weight, tube voltage (kV), tube current (mA), exposure time (s), exposure index of a digital detector (S), and dose area product (DAP) were obtained from a total of 80 chest radiography examinations performed on neonates (<1 kg and <30 days old). All examinations were performed in a single X-ray system, and all data (demographic and dosimetry data) were collected from the PACS of the hospital. Typical radiation exposure values were determined as the median value of DAP and ESD distribution. Afterward, these typical values were compared with DRL values from other countries. Three radiologists reviewed the images to evaluate image quality for dose optimization in neonatal chest radiography. From all examinations, the mean value and standard deviation of DAP was 0.13 ± 0.11 dGy·cm² (range: 0.01–0.46 dGy·cm²), and ESD was measured at 11.55 ± 4.96 μGy (range: 4.01–30.4 μGy). The typical values in terms of DAP and ESD were estimated to be 0.08 dGy·cm² and 9.87 μGy, respectively. The results show that the DAP value decreases as the exposure index increases. This study’s typical values were lower than the DRLs reported in the literature because our population had lower weight and age. From the subjective evaluation of image quality, it was revealed that the vast majority of radiographs (over 80%) met the criteria for being diagnostic as they received an excellent rating in terms of noise levels, contrast, and sharpness. This study contributes to the recording of typical dose values in a sensitive and rare category of patients (neonates weighing <1 kg) as well as information on the image quality of chest X-rays that were performed in this group. Full article

Background: Chest X-rays are among the most frequently used imaging tests in medical practice. We aimed to assess the prognostic value of the cardio–thoracic ratio (CTR) and transverse cardiac diameter (TCD) and compare them with novel chest X-ray parameters used in screening for cardiac enlargement. Methods: CTR, TCD, and five other non-standard new radiographic indexes, including basic spherical index (BSI), assessing changes in cardiac silhouette in chest radiographs in posterior–anterior projection were related to increased left ventricular end-diastolic volume (LVEDV) and left ventricular hypertrophy (LVH) assessed in cardiac magnetic resonance imaging (CMR). Results: TCD, CTR, and BSI were the best predictors of both LVH and increased LVEDV diagnosed in CMR. The best sensitivity, along with good specificity in LVH prediction, defined as left ventricular mass/body surface area (BSA) > 72 g/m² in men or >55 g/m² in women, was observed when TCD and BSI parameters were used jointly (69.2%, 95% confidence interval [CI]: 52.4–83.0% and 80.0%, 95% CI: 51.9–95.7%, respectively). In the prediction of cardiac enlargement defined as LVEDV/BSA > 117 mL/m² in men or >101 mL/m² in women, BSI > 137.5 had the best sensitivity and specificity (85.0%, 95% CI: 62.1–96.8% and 82.4%, 95% CI: 65.5–93.2%, respectively). Conclusions: TCD may be valuable in the assessment of patients suspected of having cardiac enlargement. CTR and BSI serve as complementary tools for a more precise approach. TCD appears particularly useful for the prediction of LVH, while BSI demonstrates greater utility as an indicator of increased LVEDV. Full article

Dynamic digital radiography (DDR) is a recent imaging technique that allows for real-time visualization of thoracic and pulmonary movement in synchronization with the breathing cycle, providing useful clinical information. A 46-year-old male, a former smoker, was evaluated for unexplained dyspnea and reduced exercise tolerance. His medical history included a SARS-CoV-2 infection in 2021. On physical examination, decreased breath sounds were noted at the right-lung base. Spirometry showed results below predicted values. A standard chest radiograph revealed an elevated right hemidiaphragm, a finding not present in a previous CT scan performed during his SARS-CoV-2 infection. To better assess the diaphragmatic function, a posteroanterior DDR study was performed in the standing position with X-ray equipment (AeroDR TX, Konica Minolta Inc., Tokyo, Japan) during forced breath, with the following acquisition parameters: tube voltage, 100 kV; tube current, 50 mA; pulse duration of pulsed X-ray, 1.6 ms; source-to-image distance, 2 m; additional filter, 0.5 mm Al + 0.1 mm Cu. The exposure time was 12 s. The pixel size was 388 × 388 μm, the matrix size was 1024 × 768, and the overall image area was 40 × 30 cm. The dynamic imaging, captured at 15 frames/s, was then assessed on a dedicated workstation (Konica Minolta Inc., Tokyo, Japan). The dynamic acquisition showed a markedly reduced motion of the right diaphragm. The diagnosis of diaphragm dysfunction can be challenging due to its range of symptoms, which can vary from mild to severe dyspnea. The standard chest X-ray is usually the first exam to detect an elevated hemidiaphragm, which may suggest motion impairment or paralysis but fails to predict diaphragm function. Ultrasound (US) allows for the direct visualization of the diaphragm and its motion. Still, its effectiveness depends highly on the operator’s experience and could be limited by gas and abdominal fat. Moreover, ultrasound offers limited information regarding the lung parenchyma. On the other hand, high-resolution CT can be useful in identifying causes of diaphragmatic dysfunction, such as atrophy or eventration. However, it does not allow for the quantitative assessment of diaphragmatic movement and the differentiation between paralysis and dysfunction, especially in bilateral dysfunction, which is often overlooked due to the elevation of both hemidiaphragms. Dynamic Digital Radiography (DDR) has emerged as a valuable and innovative imaging technique due to its unique ability to evaluate diaphragm movement in real time, integrating dynamic functional information with static anatomical data. DDR provides both visual and quantitative analysis of the diaphragm’s motion, including excursion and speed, which leads to a definitive diagnosis. Additionally, DDR offers a range of post-processing techniques that provide information on lung movement and pulmonary ventilation. Based on these findings, the patient was referred to a thoracic surgeon and deemed a candidate for surgical plication of the right diaphragm. Full article

Background/Objectives: Chest disease identification for Tuberculosis and Pneumonia diseases presents diagnostic challenges due to overlapping radiographic features and the limited availability of expert radiologists, especially in developing countries. The present study aims to address these challenges by developing a Computer-Aided Diagnosis (CAD) system to provide consistent and objective analyses of chest X-ray images, thereby reducing potential human error. By leveraging the complementary strengths of convolutional neural networks (CNNs) and vision transformers (ViTs), we propose a hybrid model for the accurate detection of Tuberculosis and for distinguishing between Tuberculosis and Pneumonia. Methods: We designed a two-step hybrid model that integrates the ResNet-50 CNN with the ViT-b16 architecture. It uses the transfer learning on datasets from Guangzhou Women’s and Children’s Medical Center for Pneumonia cases and datasets from Qatar and Dhaka (Bangladesh) universities for Tuberculosis cases. CNNs capture hierarchical structures in images, while ViTs, with their self-attention mechanisms, excel at identifying relationships between features. Combining these approaches enhances the model’s performance on binary and multi-class classification tasks. Results: Our hybrid CNN-ViT model achieved a binary classification accuracy of 98.97% for Tuberculosis detection. For multi-class classification, distinguishing between Tuberculosis, viral Pneumonia, and bacterial Pneumonia, the model achieved an accuracy of 96.18%. These results underscore the model’s potential in improving diagnostic accuracy and reliability for chest disease classification based on X-ray images. Conclusions: The proposed hybrid CNN-ViT model demonstrates substantial potential in advancing the accuracy and robustness of CAD systems for chest disease diagnosis. By integrating CNN and ViT architectures, our approach enhances the diagnostic precision, which may help to alleviate the burden on healthcare systems in resource-limited settings and improve patient outcomes in chest disease diagnosis. Full article

Background/Objectives: In contrast to traditional biometric modalities, such as facial recognition, fingerprints, and iris scans or even DNA, the research orientation towards chest X-ray recognition has been spurred by its remarkable recognition rates. Capturing the intricate anatomical nuances of an individual’s skeletal structure, the ribcage of the chest, lungs, and heart, chest X-rays have emerged as a focal point for identification and verification, especially in the forensic field, even in scenarios where the human body damaged or disfigured. Discriminative feature embedding is essential for large-scale image verification, especially in applying chest X-ray radiographs for identity identification and verification. This study introduced a self-residual attention-based convolutional neural network (SRAN) aimed at effective feature embedding, capturing long-range dependencies and emphasizing critical spatial features in chest X-rays. This method offers a novel approach to person identification and verification through chest X-ray categorization, relevant for biometric applications and patient care, particularly when traditional biometric modalities are ineffective. Method: The SRAN architecture integrated a self-channel and self-spatial attention module to minimize channel redundancy and enhance significant spatial elements. The attention modules worked by dynamically aggregating feature maps across channel and spatial dimensions to enhance feature differentiation. For the network backbone, a self-residual attention block (SRAB) was implemented within a ResNet50 framework, forming a Siamese network trained with triplet loss to improve feature embedding for identity identification and verification. Results: By leveraging the NIH ChestX-ray14 and CheXpert datasets, our method demonstrated notable improvements in accuracy for identity verification and identification based on chest X-ray images. This approach effectively captured the detailed anatomical characteristics of individuals, including skeletal structure, ribcage, lungs, and heart, highlighting chest X-rays as a viable biometric tool even in cases of body damage or disfigurement. Conclusions: The proposed SRAN with self-residual attention provided a promising solution for biometric identification through chest X-ray imaging, showcasing its potential for accurate and reliable identity verification where traditional biometric approaches may fall short, especially in postmortem cases or forensic investigations. This methodology could play a transformative role in both biometric security and healthcare applications, offering a robust alternative modality for identity verification. Full article

Objective: This systematic review aims to assess the effectiveness of respiratory physiotherapy techniques in oxygenation, chest X-ray findings, and lung auscultation in paediatric patients aged 0 to 18 years diagnosed with atelectasis. Methods: A comprehensive search was conducted in the PubMed, PEDro, Web of Science, and Cochrane Library databases. Results: Eight randomised clinical trials were included, involving 430 children ranging from 35 weeks of gestational age to 14 years. These trials evaluated various respiratory physiotherapy techniques and their effects on oxygenation and chest radiograph outcomes. The methodological quality of the studies ranged from acceptable to good, according to the PEDro scale. Conclusions: Recent evidence indicates that respiratory physiotherapy is effective and safe in the paediatric population with atelectasis. Both manual and instrumental techniques demonstrated efficacy, with instrumental techniques showing superior outcomes in many cases. Full article