Search

Sarcoidosis staging primarily has relied on the Scadding chest radiographic system, although chest CT imaging is finding increased clinical use. Whether standardized chest CT scan assessment provides additional understanding of lung function beyond Scadding stage and demographics is unknown and the focus of this study. We used National Heart, Lung, and Blood Institute study Genomics Research in Alpha-1 Antitrypsin Deficiency and Sarcoidosis (GRADS) cases of sarcoidosis (n = 351) with Scadding stage and chest CT scans obtained in a standardized manner. One chest radiologist scored all CT scans with a visual scoring system, with a subset read by another chest radiologist. We compared demographic features, Scadding stage and CT scan findings, and the correlation between these measures. Associations between spirometry and diffusing capacity of the lungs for carbon monoxide (D lco) results and CT scan findings and Scadding stage were determined using regression analysis (n = 318). Agreement between readers was evaluated using Cohen's κ value. CT scan features were inconsistent with Scadding stage in approximately 40% of cases. Most CT scan features assessed on visual scoring were associated negatively with lung function. Associations persisted for FEV 1 and D lco when adjusting for Scadding stage, although some CT scan feature associations with FVC became insignificant. Scadding stage was associated primarily with FEV 1 , and inclusion of CT scan features reduced significance in association between Scadding stage and lung function. Multivariable regression modeling to identify radiologic measures explaining lung function included Scadding stage for FEV 1 and FEV 1 to FVC ratio (P <. 05) and marginally for D lco (P <. 15). Combinations of CT scan measures accounted for Scadding stage for FVC. Correlations among Scadding stage and CT scan features were noted. Agreement between readers was poor to moderate for presence or absence of CT scan features and poor for degree and location of abnormality. In this study, CT scan features explained additional variability in lung function beyond Scadding stage, with some CT scan features obviating the associations between lung function and Scadding stage. Whether CT scan features, phenotypes, or endotypes could be useful for treating patients with sarcoidosis needs more study. [ABSTRACT FROM AUTHOR]

Abstract Background Children with atrial septal defect (ASD) and ventricular septal defect (VSD) are frequently examined for respiratory symptoms, even when the underlying disease is not found. Chest radiographs often serve as the primary imaging modality. It is crucial to differentiate between ASD and VSD due to their distinct treatment. Purpose To assess whether deep learning analysis of chest radiographs can more effectively differentiate between ASD and VSD in children. Methods In this retrospective study, chest radiographs and corresponding radiology reports from 1,194 patients were analyzed. The cases were categorized into a training set and a validation set, comprising 480 cases of ASD and 480 cases of VSD, and a test set with 115 cases of ASD and 119 cases of VSD. Four deep learning network models—ResNet-CBAM, InceptionV3, EfficientNet, and ViT—were developed for training, and a fivefold cross-validation method was employed to optimize the models. Receiver operating characteristic (ROC) curve analyses were conducted to assess the performance of each model. The most effective algorithm was compared with the interpretations provided by two radiologists on 234 images from the test group. Results The average accuracy, sensitivity, and specificity of the four deep learning models in the differential diagnosis of VSD and ASD were higher than 70%. The AUC values of ResNet-CBAM, IncepetionV3, EfficientNet, and ViT were 0.87, 0.91, 0.90, and 0.66, respectively. Statistical analysis showed that the differential diagnosis efficiency of InceptionV3 was the highest, reaching 87% classification accuracy. The accuracy of InceptionV3 in the differential diagnosis of VSD and ASD was higher than that of the radiologists. Conclusions Deep learning methods such as IncepetionV3 based on chest radiographs in the study showed good performance for differential diagnosis of congenital VSD and ASD, which may be able to assist radiologists in diagnosis, education, and training, and reduce missed diagnosis and misdiagnosis.

Objective: to evaluate the effectiveness of diagnostics for non-small cell lung cancer (LC) based on chest radiography/fluorography data for LC screening diagnostics during preventive medical examination and check-ups.Material and methods. The work was organized as a retrospective cohort study. The starting point of the study was chest radiography, the final point was the diagnosis of LC based on the results of low-dose computed tomography (LDCT) and tumor morphological examination. The patient sample was composed using inclusion and exclusion criteria and initially included 800 patients, then narrowed down to 788. Patients were divided into groups according to LC stage and depending on whether radiography during preventive measures made it possible to suspect LC verified within 3 months via LDCT for any reasons not related to the suspicion of a tumor process. The diagnostic coefficient and informative value of radiography were calculated for each stage of the established LC diagnosis.Results. The study showed that chest radiography does not allow establishing stage I LC diagnosis (J=0.00; p

The World Health Organization’s end TB strategy promotes the use of symptom and chest radiograph screening for tuberculosis (TB) disease. However, asymptomatic early states of TB beyond latent TB infection and active disease can go unrecognized using current screening criteria. We conducted a longitudinal cohort study enrolling household contacts initially free of TB disease and followed them for the occurrence of incident TB over 1 year. Among 1,747 screened contacts, 27 (52%) of the 52 persons in whom TB subsequently developed during follow-up had a baseline abnormal radiograph. Of contacts without TB symptoms, persons with an abnormal radiograph were at higher risk for subsequent TB than persons with an unremarkable radiograph (adjusted hazard ratio 15.62 [95% CI 7.74–31.54]). In young adults, we found a strong linear relationship between radiograph severity and time to TB diagnosis. Our findings suggest chest radiograph screening can extend to detecting early TB states, thereby enabling timely intervention.

Background/Objectives: Radiography is an essential and low-cost diagnostic method in pulmonary medicine that is used for the early detection and monitoring of lung diseases. An adequate and consistent image quality (IQ) is crucial to ensure accurate diagnosis and effective patient management. This pilot study evaluates the feasibility and effectiveness of the International Atomic Energy Agency (IAEA)'s remote and automated quality control (QC) methodology, which has been tested in multiple imaging centers. Methods: The data, collected between April and December 2022, included 47 longitudinal data sets from 22 digital radiographic units. Participants submitted metadata on the radiography setup, exposure parameters, and imaging modes. The database comprised 968 exposures, each representing multiple image quality parameters and metadata of image acquisition parameters. Python scripts were developed to collate, analyze, and visualize image quality data. Results: The pilot survey identified several critical issues affecting the future implementation of the IAEA method, as follows: (1) difficulty in accessing raw images due to manufacturer restrictions, (2) variability in IQ parameters even among identical X-ray systems and image acquisitions, (3) inconsistencies in phantom construction affecting IQ values, (4) vendor-dependent DICOM tag reporting, and (5) large variability in SNR values compared to other IQ metrics, making SNR less reliable for image quality assessment. Conclusions: Cross-comparisons among radiography systems must be taken with cautious because of the dependence on phantom construction and acquisition mode variations. Awareness of these factors will generate reliable and standardized quality control programs, which are crucial for accurate and fair evaluations, especially in high-frequency chest imaging. [ABSTRACT FROM AUTHOR]

Objective: To evaluate the utility of ordering chest x‐rays after pediatric tracheostomy tube placement in identifying acute, post‐operative complications and how it impacts clinical decision‐making. Methods: In this retrospective cohort study, we identified tracheostomies performed in 139 pediatric patients through CPT codes over a 5‐year period from 2013 to 2018. Manual chart review was performed for demographic and clinical characteristics, pre‐procedure and post‐procedure chest x‐ray interpretations, and the presence of complications. Each complication was reviewed to see if action was taken due to post‐procedure chest x‐ray findings. Multivariable logistic regression was performed to determine associations with changes in pre‐procedure versus post‐procedure chest x‐rays. Results: In a cohort of 139 pediatric patients with pre‐procedure and post‐procedure chest x‐rays, 40 (28.8%) of patients had new significant post‐procedure chest x‐ray findings compared to pre‐procedure chest x‐ray findings. Of these 40 instances of changes in pre‐procedure versus post‐procedure chest x‐ray findings, only eight resulted in action being taken due to the observed findings. Among these eight instances of action being taken, only one instance involved in invasive action being taken with a bronchoscopy. With multivariable regression analysis, patient age, race, gender, and the presences of genetic syndromes, were not found to be significant risk factors in predicting changes in pre‐procedure versus post‐procedure chest x‐ray. Conclusion: In our study, post‐procedure chest x‐ray after tracheostomy tube placement did not significantly impact clinical decision making. It may be worth reconsidering the value in routine chest x‐rays after tracheostomy tube placement in pediatric patients. [ABSTRACT FROM AUTHOR]

Background and Objectives: This study aims to analyze survival in peritoneal and hemodialysis patients using chest radiography and biochemical parameters, determine common dialysis etiologies and causes of death, reveal prognostic factors, and contribute to clinical practice. Materials and Methods: A retrospective cross-sectional study was conducted with data from 33 peritoneal dialysis and 37 hemodialysis patients collected between October 2018 and February 2020. Survival and mortality were retrospectively tracked over 70 months (October 2018–June 2024). Chest X-ray measurements (cardiothoracic index, pulmonary vascular pedicle width, right pulmonary artery diameter, diaphragmatic height) and biochemical parameters (urea, albumin, creatinine, parathormone, ferritin, hemoglobin, arterial blood gas, potassium) were analyzed for their impact on survival. Statistical analyses included descriptive statistics, chi-square test, Fisher's exact test, Bayesian analysis, McNemar test, Kaplan–Meier survival analysis, Cox regression, Bayesian correlation test, linear regression analysis (scatter plot), and ROC analysis. SPSS 20.0 was used for data analysis, with p < 0.05 considered statistically significant. Results: Hypertension, type 2 diabetes, and urogenital disorders were the main dialysis etiologies. Peritonitis (38.5%) and cardiovascular diseases (47.4%) were the leading causes of death in peritoneal and hemodialysis patients, respectively. Significant chest X-ray differences included pulmonary vascular pedicle width and pulmonary artery diameter in hemodialysis and diaphragm height in peritoneal dialysis. Kaplan–Meier showed no survival difference between methods. Cox regression identified age, intact parathormone levels, iPTH/PVPW ratio, and clinical status as survival and mortality factors. The iPTH/PVPW ratio cut-off for mortality prediction was ≤6.8. Conclusions: Age, intact parathormone levels, pulmonary vascular pedicle width, and clinical status significantly impact survival in dialysis patients. Management of hypertension and diabetes, management and follow-up of urogenital disorders, infection control, patient education, and regular cardiovascular check-ups may improve survival rates. Additionally, the iPTH/PVPW ratio can predict mortality risk. [ABSTRACT FROM AUTHOR]

Chest radiographs (CXRs) are still of crucial importance in primary diagnostics, but their interpretation poses difficulties at times. Can a convolutional neural network-based artificial intelligence (AI) system that interprets CXRs add value in an emergency unit setting? A total of 563 CXRs acquired in the emergency unit of a major university hospital were retrospectively assessed twice by three board-certified radiologists, three radiology residents, and three emergency unit-experienced nonradiology residents (NRRs). They used a two-step reading process: (1) without AI support; and (2) with AI support providing additional images with AI overlays. Suspicion of four suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, and nodules) was reported on a five-point confidence scale. Confidence scores of the board-certified radiologists were converted into four binary reference standards of different sensitivities. Performance by radiology residents and NRRs without AI support/with AI support were statistically compared by using receiver-operating characteristics (ROCs), Youden statistics, and operating point metrics derived from fitted ROC curves. NRRs could significantly improve performance, sensitivity, and accuracy with AI support in all four pathologies tested. In the most sensitive reference standard (reference standard IV), NRR consensus improved the area under the ROC curve (mean, 95% CI) in the detection of the time-critical pathology pneumothorax from 0.846 (0.785-0.907) without AI support to 0.974 (0.947-1.000) with AI support (P <.001), which represented a gain of 30% in sensitivity and 2% in accuracy (while maintaining an optimized specificity). The most pronounced effect was observed in nodule detection, with NRR with AI support improving sensitivity by 53% and accuracy by 7% (area under the ROC curve without AI support, 0.723 [0.661-0.785]; with AI support, 0.890 [0.848-0.931]; P <.001). Radiology residents had smaller, mostly nonsignificant gains in performance, sensitivity, and accuracy with AI support. We found that in an emergency unit setting without 24/7 radiology coverage, the presented AI solution features an excellent clinical support tool to nonradiologists, similar to a second reader, and allows for a more accurate primary diagnosis and thus earlier therapy initiation. [ABSTRACT FROM AUTHOR]

Issues in patient positioning during chest X-ray (CXR) acquisition impair diagnostic quality and potentially increase radiation dose. Automated quality assessment was proposed to address this. Our objective is to determine thresholds on some quality control metrics following international guidelines, that represent expert knowledge and can be applied in a comprehensible and explainable AI approach for such an automatic quality assessment. An AI-method estimating collimation distance to the ribcage, balancing between both clavicle heads, and number of ribs above the diaphragm as metrics for collimation, rotation, and inhalation quality was applied on 64,315 posteroanterior CXR images from a public dataset (ChestX-ray8). From this set 920 CXR images were sampled and manually annotated to gain additional trusted reference metrics. Seven readers from different institutions then classified the acquisition quality of these images independently into okay, inadequate, or unacceptable following the criteria of international guidelines. Optimal thresholds on the metrics were determined to reproduce these classes using the metrics only. A fair to moderate agreement between the experts was found. When disregarding all inadequate rates a classification on the metrics was able to separate okay rated cases from unacceptable cases for collimation (AUC > 0.97), rotation (AUC = 0.93) and inhalation (AUC = 0.97). Suitable thresholds were determined to reproduce expert opinions in the assessment of the most important quality criteria in CXR acquisition. These thresholds were finally applied on the AI-method's estimates to automatically classify image acquisition quality comprehensibly and according to the guidelines. [ABSTRACT FROM AUTHOR]

The objective of this study was to demonstrate the performance characteristics and potential utility of a novel tomosynthesis device as applied to imaging the chest, specifically relating to lung nodules. The imaging characteristics and quality of a novel digital tomosynthesis prototype system was assessed by scanning, a healthy volunteer, and an andromorphic lung phantom with different configurations of simulated pulmonary nodules. The adequacy of nodule detection on the phantoms was rated by chest radiologists using a standardized scale. Results from using this tomosynthesis device demonstrate in plane resolution of 16lp/cm, with estimated effective radiation doses of 90% less than low dose CT. Nodule detection was adequate across various anatomic locations on a phantom. These proof-of-concept tests showed this novel tomosynthesis device can detect lung nodules with low radiation dose to the patient. This technique has potential as an alternative to low dose chest CT for lung nodule screening and tracking. [ABSTRACT FROM AUTHOR]

Scimitar Syndrome is part of a complex spectrum of congenital cardiovascular anomalies related to anomalous pulmonary venous return. Depending on the extent of involvement, treatment can be either expectant or surgical. Prognosis and survival have been controversial, with some results supporting early surgical management. This research aims to disclose the outcomes and describe the management, clinical and imaging characteristics of patients diagnosed with Scimitar Syndrome treated in a tertiary referral healthcare center. Longitudinal descriptive observational study. The study included all patients diagnosed with scimitar syndrome in our institution between January/2011 and December/2022. A description of the sociodemographic and clinical characteristics, diagnostic tools used, treatment features, and patient outcomes is provided. Eleven patients were included, with a mean age at diagnosis of five years (CI 0–17), six of which were female (54.55%). Nine (81.82%) patients had evidence of a scimitar vein on the chest radiograph, six (54.55%) cardiac dextroposition, six (54.55%) pulmonary hypoplasia, five (45.45%) right pulmonary artery hypoplasia, and three (27.27%) had aortopulmonary collaterals. Four (36.36%) patients had horseshoe lungs, and four (36.36%) had bronchopulmonary sequestration. In the associations, two (18.18%) patients were found to have an atrial septal defect, three (27.27%) ventricular septal defect, and one (9%) had Tetralogy of Fallot. Pulmonary hypertension was demonstrated in two (18.18%) patients. Seven (63.64%) required surgical management to correct the scimitar vein, and two patients died due to unrelated complications. Scimitar syndrome presents diagnostic and treatment challenges, necessitating a multidisciplinary approach for timely care. Chest radiography and CT scans are primary diagnostic tools, with surgical intervention often warranted alongside other heart defects or significant hemodynamic repercussions. Medical management is effective for mild to moderate cases. Long-term patient outcomes remain uncertain due to study limitations, but improved life expectancy is anticipated with ongoing care. [ABSTRACT FROM AUTHOR]

The objective is to evaluate the performance of blood test results, radiomics, and a combination of the two data types on the prediction of the 24-h oxygenation support need for the Coronavirus disease 2019 (COVID-19) patients. In this retrospective cohort study, COVID-19 patients with confirmed real-time reverse transcription-polymerase chain reaction assay (RT-PCR) test results between February 2020 and August 2021 were investigated. Initial blood cell counts, chest radiograph, and the status of oxygenation support used within 24 h were collected (n = 290; mean age, 45 ± 19 years; 125 men). Radiomics features from six lung zones were extracted. Logistic regression and random forest models were developed using the clinical-only, radiomics-only, and combined data. Ten repeats of fivefold cross-validation with bootstrapping were used to identify the input features and models with the highest area under the receiver operating characteristic curve (AUC). Higher AUCs were achieved when using only radiomics features compared to using only clinical features (0.94 ± 0.03 vs. 0.88 ± 0.04). The best combined model using both radiomics and clinical features achieved highest in the cross-validation (0.95 ± 0.02) and test sets (0.96 ± 0.02). In comparison, the best clinical-only model yielded AUCs of 0.88 ± 0.04 in cross-validation and 0.89 ± 0.03 in test set. Both radiomics and clinical data can be used to predict 24-h oxygenation support need for COVID-19 patients with AUC > 0.88. Moreover, the combination of both data types further improved the performance. [ABSTRACT FROM AUTHOR]

Objectives: Computer-aided detection (CAD) software packages quantify tuberculosis (TB)-compatible chest X-ray (CXR) abnormality as continuous scores. In practice, a threshold value is selected for binary CXR classification. We assessed the diagnostic accuracy of an alternative approach to applying CAD for TB triage: incorporating CAD scores in multivariable modeling. Methods: We pooled individual patient data from four studies. Separately, for two commercial CAD, we used logistic regression to model microbiologically confirmed TB. Models included CAD score, study site, age, sex, human immunodeficiency virus status, and prior TB. We compared specificity at target sensitivities ≥90% between the multivariable model and the current threshold-based approach for CAD use. Results: We included 4,733/5,640 (84%) participants with complete covariate data (median age 36 years; 45% female; 22% with prior TB; 22% people living with human immunodeficiency virus). A total of 805 (17%) had TB. Multivariable models demonstrated excellent performance (areas under the receiver operating characteristic curve [95% confidence interval]: software A, 0.91 [0.90-0.93]; software B, 0.92 [0.91-0.93]). Compared with threshold scores, multivariable models increased specificity (e.g., at 90% sensitivity, threshold vs model specificity [95% confidence interval]: software A, 71% [68-74%] vs 75% [74-77%]; software B, 69% [63-75%] vs 75% [74-77%]). Conclusion: Using CAD scores in multivariable models outperformed the current practice of CAD-threshold-based CXR classification for TB diagnosis.

IntroductionDeep learning (DL) has significantly advanced medical image classification. However, it often relies on transfer learning (TL) from models pretrained on large, generic non-medical image datasets like ImageNet. Conversely, medical images possess unique visual characteristics that such general models may not adequately capture.MethodsThis study examines the effectiveness of modality-specific pretext learning strengthened by image denoising and deblurring in enhancing the classification of pediatric chest X-ray (CXR) images into those exhibiting no findings, i.e., normal lungs, or with cardiopulmonary disease manifestations. Specifically, we use a VGG-16-Sharp-U-Net architecture and leverage its encoder in conjunction with a classification head to distinguish normal from abnormal pediatric CXR findings. We benchmark this performance against the traditional TL approach, viz., the VGG-16 model pretrained only on ImageNet. Measures used for performance evaluation are balanced accuracy, sensitivity, specificity, F-score, Matthew’s Correlation Coefficient (MCC), Kappa statistic, and Youden’s index.ResultsOur findings reveal that models developed from CXR modality-specific pretext encoders substantially outperform the ImageNet-only pretrained model, viz., Baseline, and achieve significantly higher sensitivity (p

Pediatric patients are generally uncooperative during radiology examinations. Radiographic images can become blurry due to movement. This will cause to repeat examinations, thereby significantly increasing radiation exposure, and it can pose significant risks to children, patient families, and radiation workers. The research aims to create and test the effectiveness of a fixation device equipped with Audio-Visual elements for pediatric chest radiography examinations in Anteroposterior and Lateral projections. The experimental method involves developing the fixation device in the Radiodiagnostic Department Laboratory of Poltekkes Kemenkes Jakarta II. The effectiveness of the fixation device is assessed through surveys and interviews involving 66 respondents at hospitals in Jakarta from January to July 2023 during pediatric chest examinations. The average results indicate that the device can be used in hospitals (3.27±0.63), it’s safe to use (3.00±0.74), and highly effective (3.17±0.67). The overall average value of 3.16±0.68, suggests that the fixation device is suitable for use in pediatric chest examinations. The obtained images from the Anteroposterior and Lateral projections optimally describe of lung organs, the heart, and blood vessels within the thoracic cavity. Suggestions for further development of the safe device include the addition of leg supports, pediatric chair can be moved forward/backward and patient restraints to prevent falling or movement

Abstract Aim Pleural effusion (PE) is a common chest radiography (CXR) finding in patients with advanced cardiac disease. The pathophysiology and clinical value of PE in this setting are incompletely defined. We aimed to assess the haemodynamic correlates and prognostic impact of PE in patients with severe aortic stenosis (AS). Methods and results We studied 471 patients (mean age 74 ± 10 years) with severe AS (indexed aortic valve area 0.42 ± 0.12 cm2/m2, left ventricular ejection fraction 58 ± 12%) undergoing right heart catheterization and upright CXR prior to aortic valve replacement (AVR). Two radiologist independently evaluated all CXR for the presence of bilateral PE, unilateral, or no PE, blinded to any other data. There were 49 (10%) patients with bilateral PE, 32 (7%) patients with unilateral PE, and 390 (83%) patients with no PE. Patients with bilateral PE had the highest mean right atrial pressure, mean pulmonary artery wedge pressure (mPAWP), and pulmonary vascular resistance, and had the lowest stroke volume index while those with unilateral PE had intermediate values. In the multivariate analysis, mPAWP was an independent predictor of any PE and bilateral PE. After a median (interquartile range) post‐AVR follow‐up of 1361 (957–1878) days mortality was highest in patients with bilateral PE (2.7 times higher than in patients without PE), whereas patients with unilateral PE had similar mortality as those without PE. Conclusions In severe AS patients, the presence of PE, particularly bilateral PE, is a marker of a poor haemodynamic constellation. Bilateral PE is associated with a substantially increased post‐AVR mortality.

Abstract Introduction Differences in patient size often provide challenges for radiographers, particularly when choosing the optimum acquisition parameters to obtain radiographs with acceptable image quality (IQ) for diagnosis. This study aimed to assess the effect of body part thickness on IQ in terms of low‐contrast detail (LCD) detection and radiation dose when undertaking adult chest radiography (CXR). Methods This investigation made use of a contrast detail (CD) phantom. Polymethyl methacrylate (PMMA) was utilised to approximate varied body part thicknesses (9, 11, 15 and 17 cm) simulating underweight, standard, overweight and obese patients, respectively. Different tube potentials were tested against a fixed 180 cm source to image distance (SID) and automatic exposure control (AEC). IQ was analysed using bespoke software thus providing an image quality figure inverse (IQFinv) value which represents LCD detectability. Dose area product (DAP) was utilised to represent the radiation dose. Results IQFinv values decreased statistically (P = 0.0001) with increasing phantom size across all tube potentials studied. The highest IQFinv values were obtained at 80 kVp for all phantom thicknesses (2.29, 2.02, 1.8 and 1.65, respectively). Radiation dose increased statistically (P = 0.0001) again with increasing phantom thicknesses. Conclusion Our findings demonstrate that lower tube potentials provide the highest IQFinv scores for various body part thicknesses. This is not consistent with professional practice because radiographers frequently raise the tube potential with increased part thickness. Higher tube potentials did result in radiation dose reductions. Establishing a balance between dose and IQ, which must be acceptable for diagnosis, can prevent the patient from receiving unnecessary additional radiation dose.

Aim: Pleural effusion (PE) is a common chest radiography (CXR) finding in patients with advanced cardiac disease. The pathophysiology and clinical value of PE in this setting are incompletely defined. We aimed to assess the haemodynamic correlates and prognostic impact of PE in patients with severe aortic stenosis (AS). Methods and results: We studied 471 patients (mean age 74 ± 10 years) with severe AS (indexed aortic valve area 0.42 ± 0.12 cm2/m2, left ventricular ejection fraction 58 ± 12%) undergoing right heart catheterization and upright CXR prior to aortic valve replacement (AVR). Two radiologist independently evaluated all CXR for the presence of bilateral PE, unilateral, or no PE, blinded to any other data. There were 49 (10%) patients with bilateral PE, 32 (7%) patients with unilateral PE, and 390 (83%) patients with no PE. Patients with bilateral PE had the highest mean right atrial pressure, mean pulmonary artery wedge pressure (mPAWP), and pulmonary vascular resistance, and had the lowest stroke volume index while those with unilateral PE had intermediate values. In the multivariate analysis, mPAWP was an independent predictor of any PE and bilateral PE. After a median (interquartile range) post‐AVR follow‐up of 1361 (957–1878) days mortality was highest in patients with bilateral PE (2.7 times higher than in patients without PE), whereas patients with unilateral PE had similar mortality as those without PE. Conclusions: In severe AS patients, the presence of PE, particularly bilateral PE, is a marker of a poor haemodynamic constellation. Bilateral PE is associated with a substantially increased post‐AVR mortality. [ABSTRACT FROM AUTHOR]

Summary: We developed a new model for predicting bone mineral density on chest radiographs and externally validated it using images captured at facilities other than the development environment. The model performed well and showed potential for clinical use. Purpose: In this study, we performed external validation (EV) of a developed deep learning model for predicting bone mineral density (BMD) of femoral neck on chest radiographs to verify the usefulness of this model in clinical practice. Methods: This study included patients who visited any of the collaborating facilities from 2010 to 2020 and underwent chest radiography and dual-energy X-ray absorptiometry (DXA) at the femoral neck in the year before and after their visit. A total of 50,114 chest radiographs were obtained, and BMD was measured using DXA. We developed the model with 47,150 images from 17 facilities and performed EV with 2914 images from three other facilities (EV dataset). We trained the deep learning model via ensemble learning based on chest radiographs, age, and sex to predict BMD using regression. The outcomes were the correlation of the predicted BMD and measured BMD with diagnoses of osteoporosis and osteopenia using the T-score estimated from the predicted BMD. Results: The mean BMD was 0.64±0.14 g/cm2 in the EV dataset. The BMD predicted by the model averaged 0.61±0.08 g/cm2, with a correlation coefficient of 0.68 (p<0.01) when compared with the BMD measured using DXA. The accuracy, sensitivity, and specificity of the model were 79.0%, 96.6%, and 34.1% for T-score < -1 and 79.7%, 77.1%, and 80.4% for T-score ≤ -2.5, respectively. Conclusion: Our model, which was externally validated using data obtained at facilities other than the development environment, predicted BMD of femoral neck on chest radiographs. The model performed well and showed potential for clinical use. [ABSTRACT FROM AUTHOR]

Recently, the COVID-19 disease has significantly impacted global economies and healthcare systems. Swift and accurate detection of COVID-19 is crucial for effectively mitigating the spread of this pandemic. Chest X-ray images (CXR) and CT scans have emerged as valuable diagnostic tools for COVID-19 patients. However, existing deep learning (DL) methods for COVID-19 detection are often computationally expensive and require substantial memory resources. Therefore, there is a pressing need for a lightweight and computationally efficient solution to facilitate COVID-19 detection. In response to these challenges, we propose an innovative and efficient lightweight stacked ensemble model, known as LWSE. Our approach combines the MobileNet model with a lightweight convolutional neural network (CNN) to enhance the detection performance of various chest infectious diseases, including COVID-19. The integration of these models not only improves the learning capability but also significantly reduces the computational complexity. The stacked ensemble technique is employed to aggregate predictions from the MobileNet and lightweight CNN, leading to enhanced detection accuracy. Subsequently, these predictions are fused into a multilayer perceptron (MLP) for classification, yielding superior results compared to using a single model. To evaluate the effectiveness of our LWSE model, we have developed a novel COVID-19 dataset comprising 900 CXR images of Pakistani patients collected from local hospitals. Additionally, we conducted experiments on publicly available datasets. Our comprehensive evaluation benchmarks the LWSE model against four pre-trained models in terms of computational cost and detection performance. Notably, our LWSE model achieves highly promising results with an accuracy of 96.40% and 97.89% on the CXR dataset, and an outstanding accuracy of 98.83% on the CT dataset. The superior performance of our LWSE model, coupled with its low computational cost, enables faster image classification compared to pre-trained and state-of-the-art models. Consequently, our proposed LWSE model presents a more viable solution for rapid diagnosis of patients with chest infections. [ABSTRACT FROM AUTHOR]

Introduction: Differences in patient size often provide challenges for radiographers, particularly when choosing the optimum acquisition parameters to obtain radiographs with acceptable image quality (IQ) for diagnosis. This study aimed to assess the effect of body part thickness on IQ in terms of low‐contrast detail (LCD) detection and radiation dose when undertaking adult chest radiography (CXR). Methods: This investigation made use of a contrast detail (CD) phantom. Polymethyl methacrylate (PMMA) was utilised to approximate varied body part thicknesses (9, 11, 15 and 17 cm) simulating underweight, standard, overweight and obese patients, respectively. Different tube potentials were tested against a fixed 180 cm source to image distance (SID) and automatic exposure control (AEC). IQ was analysed using bespoke software thus providing an image quality figure inverse (IQFinv) value which represents LCD detectability. Dose area product (DAP) was utilised to represent the radiation dose. Results: IQFinv values decreased statistically (P = 0.0001) with increasing phantom size across all tube potentials studied. The highest IQFinv values were obtained at 80 kVp for all phantom thicknesses (2.29, 2.02, 1.8 and 1.65, respectively). Radiation dose increased statistically (P = 0.0001) again with increasing phantom thicknesses. Conclusion: Our findings demonstrate that lower tube potentials provide the highest IQFinv scores for various body part thicknesses. This is not consistent with professional practice because radiographers frequently raise the tube potential with increased part thickness. Higher tube potentials did result in radiation dose reductions. Establishing a balance between dose and IQ, which must be acceptable for diagnosis, can prevent the patient from receiving unnecessary additional radiation dose. [ABSTRACT FROM AUTHOR]

Abstract Objective To evaluate the utility of ordering chest x‐rays after pediatric tracheostomy tube placement in identifying acute, post‐operative complications and how it impacts clinical decision‐making. Methods In this retrospective cohort study, we identified tracheostomies performed in 139 pediatric patients through CPT codes over a 5‐year period from 2013 to 2018. Manual chart review was performed for demographic and clinical characteristics, pre‐procedure and post‐procedure chest x‐ray interpretations, and the presence of complications. Each complication was reviewed to see if action was taken due to post‐procedure chest x‐ray findings. Multivariable logistic regression was performed to determine associations with changes in pre‐procedure versus post‐procedure chest x‐rays. Results In a cohort of 139 pediatric patients with pre‐procedure and post‐procedure chest x‐rays, 40 (28.8%) of patients had new significant post‐procedure chest x‐ray findings compared to pre‐procedure chest x‐ray findings. Of these 40 instances of changes in pre‐procedure versus post‐procedure chest x‐ray findings, only eight resulted in action being taken due to the observed findings. Among these eight instances of action being taken, only one instance involved in invasive action being taken with a bronchoscopy. With multivariable regression analysis, patient age, race, gender, and the presences of genetic syndromes, were not found to be significant risk factors in predicting changes in pre‐procedure versus post‐procedure chest x‐ray. Conclusion In our study, post‐procedure chest x‐ray after tracheostomy tube placement did not significantly impact clinical decision making. It may be worth reconsidering the value in routine chest x‐rays after tracheostomy tube placement in pediatric patients.

Barotrauma occurs in a significant number of patients with COVID-19 interstitial pneumonia undergoing mechanical ventilation. The aim of the current study was to investigate whether the Brixia score (BS) calculated on chest-X-rays acquired at the Emergency Room was associated with barotrauma. We retrospectively evaluated 117 SARS-CoV-2 patients presented to the Emergency Department (ED) and then admitted to the intensive care unit (ICU) for mechanical ventilation between February and April 2020. Subjects were divided into two groups according to the occurrence of barotrauma during their hospitalization. CXRs performed at ED admittance were assessed using the Brixia score. Distribution of barotrauma (pneumomediastinum, pneumothorax, subcutaneous emphysema) was identified in chest CT scans. Thirty-eight subjects (32.5%) developed barotrauma (25 pneumomediastinum, 24 pneumothorax, 24 subcutaneous emphysema). In the barotrauma group we observed higher Brixia score values compared to the non-barotrauma group (mean value 12.18 vs. 9.28), and logistic regression analysis confirmed that Brixia score is associated with the risk of barotrauma. In this work, we also evaluated the relationship between barotrauma and clinical and ventilatory parameters: SOFA score calculated at ICU admittance and number of days of non-invasive ventilation (NIV) prior to intubation emerged as other potential predictors of barotrauma.

Purpose: To validate the predictive value of the aortic knob index for identifying new-onset postoperative atrial fibrillation (POAF) after off-pump coronary artery bypass grafting (OPCAB). Methods: Among 156 patients who underwent isolated OPCAB, 138 consecutive patients without a history of atrial fibrillation were enrolled in this retrospective observational cohort study. The patients were divided into two groups based on the development of POAF. We compared the baseline clinical characteristics; preoperative radiographic characteristics of the aorta, including aortic knob measurements; and perioperative data, between the groups. Logistic regression analysis was performed to identify the predictors of new-onset POAF. Results: New-onset POAF developed in 35 (25.4%) patients. Multivariate logistic regression analysis revealed that the aortic knob index was an independent predictor of POAF and yielded that the risk of POAF increased by 1.85 times when the aortic knob index increased by 0.1 (odds ratio, 1.853; confidence interval, 1.326–2.588; P < 0.001). Receiver operating characteristic analysis revealed that an aortic knob index of 1.364 constituted a cutoff value for new-onset POAF with 80.0% sensitivity and 65.0% specificity. Conclusions: The aortic knob index on preoperative chest radiography was a significant and independent predictor of new-onset POAF following OPCAB. [ABSTRACT FROM AUTHOR]

Our goal was to analyze radiology report text for chest radiographs (CXRs) to identify imaging findings that have the most impact on report length and complexity. Identifying these imaging findings can highlight opportunities for designing CXR AI systems which increase radiologist efficiency. We retrospectively analyzed text from 210,025 MIMIC-CXR reports and 168,949 reports from our local institution collected from 2019 to 2022. Fifty-nine categories of imaging finding keywords were extracted from reports using natural language processing (NLP), and their impact on report length was assessed using linear regression with and without LASSO regularization. Regression was also used to assess the impact of additional factors contributing to report length, such as the signing radiologist and use of terms of perception. For modeling CXR report word counts with regression, mean coefficient of determination, R2, was 0.469 ± 0.001 for local reports and 0.354 ± 0.002 for MIMIC-CXR when considering only imaging finding keyword features. Mean R2 was significantly less at 0.067 ± 0.001 for local reports and 0.086 ± 0.002 for MIMIC-CXR, when only considering use of terms of perception. For a combined model for the local report data accounting for the signing radiologist, imaging finding keywords, and terms of perception, the mean R2 was 0.570 ± 0.002. With LASSO, highest value coefficients pertained to endotracheal tubes and pleural drains for local data and masses, nodules, and cavitary and cystic lesions for MIMIC-CXR. Natural language processing and regression analysis of radiology report textual data can highlight imaging targets for AI models which offer opportunities to bolster radiologist efficiency. [ABSTRACT FROM AUTHOR]

Purpose: Data comparing lung ultrasound (LUS) and chest X-rays (CXRs) have increased over the past years. However, there still is a lack of knowledge as to how these modalities compare with one another in the critical care setting, and several factors, including artificial study conditions, limit the generalizability of most published studies. Our study aimed to analyze the performance of LUS in comparison with CXRs in real-world critical care practice. Materials and Methods: This study presents new data from the prospective FASP-ICU trial. A total of 209 corresponding datasets of LUS and CXR results from 111 consecutive surgical ICU patients were subanalyzed, and categorial findings were compared. Statistical analysis was performed on the rates of agreement between the different imaging modalities. Results: A total of 1162 lung abnormalities were detected by LUS in ICU patients compared with 1228 detected by CXR, a non-significant difference (p = 0.276; 95% CI −0.886 to 0.254). However, the agreement rates varied between the observed abnormalities: the rate of agreement for the presence of interstitial syndrome ranged from 0 to 15%, consolidation from 0 to 56%, basal atelectasis from 33.9 to 49.34%, pleural effusion from 40.65 to 50%, and compression atelectasis from 14.29 to 19.3%. The rate of agreement was 0% for pneumothorax and 20.95% for hypervolemia. Conclusions: LUS does not detect more lung abnormalities in real-world critical care practice than CXRs, although a higher sensitivity of LUS has been reported in previous studies. Overall, low agreement rates between LUS and CXRs suggest that these diagnostic techniques are not equivalent but instead are complementary and should be used alongside each other. [ABSTRACT FROM AUTHOR]

To determine the tip position of the central venous catheter (CVC) in patients with dialysis, the guidelines recommend that it be determined using chest radiography (CXR) after catheterization, without fluoroscopy. However, some researchers have proposed that transthoracic echocardiography (TTE) can replace CXR, but this has not been widely adopted. This study aimed to determine which of the two aforementioned methods is more suitable for locating the tip position of the CVC. This prospective study included 160 patients who underwent hemodialysis at our hospital from March 2021 to December 2022. After inserting the CVC through the internal jugular vein, we used transthoracic echocardiography and CXR to determine the tip of the CVC and compared the results with those of computed tomography (CT). In the comparison between TTE and CXR for locating the CVC tip, we obtained three main findings. (1) TTE was associated with fewer misdiagnosed cases than CXR. (2) TTE provided higher sensitivity (similar sensitivity in position 2), specificity, positive/negative predictive values, and accuracy than CXR. (3) When comparing the receiver operating characteristic curves of TTE and CXR, the area under the curve (95% confidence interval) for the former was larger. Additionally, we made anatomical discoveries: the "hyperechoic triangle" recognized by TTE was equivalent to the entrance of the superior vena cava into the right atrium shown by transesophageal transthoracic echocardiography. TTE is more suitable than CXR as the first examination for CVC tip localization, as it improves diagnostic accuracy and reduces X-ray radiation damage. [ABSTRACT FROM AUTHOR]

Sarcoidosis is a chronic granulomatous disease characterized by non-caseating granuloma. The conventional chest X-ray (CXR) has important role in the diagnosis, staging and follow-up of disease. Computed tomography (CT) is a second-line imaging method used to determine the extent, complications and differential diagnosis of sarcoidosis. To determine the role of CXR in the early diagnosis and staging of sarcoidosis and to compare with CT imaging. One hundred and nine sarcoidosis patients followed at a single center were included in the study. Demographic, radiological, and clinical data of 81 patients were obtained from a total of 109 patients, and the record data of these 81 patients were evaluated. Patients who could not be reached for all tests were excluded from the study. CXR and CT imaging taken at diagnosis were evaluated retrospectively independently from two radiologists and one rheumatologist. Among 109 patients, eighty-one patients CXR and CT imaging taken at the same center has been reached. Among 81 sarcoidosis patients 23 (28.4%) were male, 58 (71.6%) were female. The mean patients age was 46.4 years and the mean disease duration was 3.8 years. CXR is regarded as normal at diagnosis in 30 patients (37%), while all of these patients had findings consistent with sarcoidosis on CT imaging. CT imaging are more superior than CXR in the early diagnosis and staging of sarcoidosis (p = 0.001). Also CT imaging is more superior for detection of disease extent and complications. In this study, we observed that CT imaging outperforms CXR in terms of early detection and staging of sarcoidosis. The use of CT imaging is important for early diagnosis and staging of sarcoidosis. The low performance of CXR is a condition that requires the discussion of this method. Multicenter prospective study is needed in this regard. [ABSTRACT FROM AUTHOR]

Barotrauma occurs in a significant number of patients with COVID-19 interstitial pneumonia undergoing mechanical ventilation. The aim of the current study was to investigate whether the Brixia score (BS) calculated on chest-X-rays acquired at the Emergency Room was associated with barotrauma. We retrospectively evaluated 117 SARS-CoV-2 patients presented to the Emergency Department (ED) and then admitted to the intensive care unit (ICU) for mechanical ventilation between February and April 2020. Subjects were divided into two groups according to the occurrence of barotrauma during their hospitalization. CXRs performed at ED admittance were assessed using the Brixia score. Distribution of barotrauma (pneumomediastinum, pneumothorax, subcutaneous emphysema) was identified in chest CT scans. Thirty-eight subjects (32.5%) developed barotrauma (25 pneumomediastinum, 24 pneumothorax, 24 subcutaneous emphysema). In the barotrauma group we observed higher Brixia score values compared to the non-barotrauma group (mean value 12.18 vs. 9.28), and logistic regression analysis confirmed that Brixia score is associated with the risk of barotrauma. In this work, we also evaluated the relationship between barotrauma and clinical and ventilatory parameters: SOFA score calculated at ICU admittance and number of days of non-invasive ventilation (NIV) prior to intubation emerged as other potential predictors of barotrauma. [ABSTRACT FROM AUTHOR]

Key message Despite embolization being now considered the preferred treatment for PAVM, surgical intervention may be considered if the malformation involves large vessels.

IntroductionPhysical measurements of expiratory flow volume and speed can be obtained using spirometry. These measurements have been used for the diagnosis and risk assessment of chronic obstructive pulmonary disease and play a crucial role in delivering early care. However, spirometry is not performed frequently in routine clinical practice, thereby hindering the early detection of pulmonary function impairment. Chest radiographs (CXRs), though acquired frequently, are not used to measure pulmonary functional information. This study aimed to evaluate whether spirometry parameters can be estimated accurately from single frontal CXR without image findings using deep learning.MethodsForced vital capacity (FVC), forced expiratory volume in 1 s (FEV1), and FEV1/FVC as spirometry measurements as well as the corresponding chest radiographs of 11,837 participants were used in this study. The data were randomly allocated to the training, validation, and evaluation datasets at an 8:1:1 ratio. A deep learning network was pretrained using ImageNet. The input and output information were CXRs and spirometry test values, respectively. The training and evaluation of the deep learning network were performed separately for each parameter. The mean absolute error rate (MAPE) and Pearson’s correlation coefficient (r) were used as the evaluation indices.ResultsThe MAPEs between the spirometry measurements and AI estimates for FVC, FEV1 and FEV1/FVC were 7.59% (r = 0.910), 9.06% (r = 0.879) and 5.21% (r = 0.522), respectively. A strong positive correlation was observed between the measured and predicted indices of FVC and FEV1. The average accuracy of >90% was obtained in each estimation of spirometry indices. Bland–Altman analysis revealed good agreement between the estimated and measured values for FVC and FEV1.DiscussionFrontal CXRs contain information related to pulmonary function, and AI estimation performed using frontal CXRs without image findings could accurately estimate spirometry values. The network proposed for estimating pulmonary function in this study could serve as a recommendation for performing spirometry or as an alternative method, suggesting its utility.

Abstract Background Chest x-ray is commonly used for pulmonary abnormality screening. However, since the image characteristics of x-rays highly depend on the machine specifications, an artificial intelligence (AI) model developed for specific equipment usually fails when clinically applied to various machines. To overcome this problem, we propose an image manipulation pipeline. Methods A total of 15,010 chest x-rays from systems with different generators/detectors were retrospectively collected from five institutions from May 2020 to February 2021. We developed an AI model to classify pulmonary abnormalities using x-rays from a single system. Then, we externally tested its performance on chest x-rays from various machine specifications. We compared the area under the receiver operating characteristics curve (AUC) of AI models developed using conventional image processing pipelines (histogram equalization [HE], contrast-limited histogram equalization [CLAHE], and unsharp masking [UM] with common data augmentations) with that of the proposed manipulation pipeline (XM-pipeline). Results The XM-pipeline model showed the highest performance for all the datasets of different machine specifications, such as chest x-rays acquired from a computed radiography system (n = 356, AUC 0.944 for XM-pipeline versus 0.917 for HE, 0.705 for CLAHE, 0.544 for UM, p $$\le$$ ≤ 0.001, for all) and from a mobile x-ray generator (n = 204, AUC 0.949 for XM-pipeline versus 0.933 for HE, p = 0.042, 0.932 for CLAHE (p = 0.009), 0.925 for UM (p = 0.001). Conclusions Applying the XM-pipeline to AI training increased the diagnostic performance of the AI model on the chest x-rays of different machine configurations. Relevance statement The proposed training pipeline would successfully promote a wide application of the AI model for abnormality screening when chest x-rays are acquired using various x-ray machines. Key points • AI models developed using x-rays of a specific machine suffer from generalization. • We proposed a new image processing pipeline to address the generalization problem. • AI models were tested using multicenter external x-ray datasets of various machines. • AI with our pipeline achieved the highest diagnostic performance than conventional methods. Graphical Abstract

Abstract Background Chest radiography (CXR) is an adjunct tool in treatment planning and monitoring of the disease course of COVID-19 pneumonia. The purpose of the study was to describe the radiographic patterns and severity scores of abnormal CXR findings in children diagnosed with COVID-19 pneumonia. Methods This retrospective study included children with confirmed COVID-19 by reverse transcriptase-polymerase chain reaction test who underwent CXR at the arrival. The CXR findings were reviewed, and modified radiographic scoring was assessed. Results The number of abnormal CXR findings was 106 of 976 (10.9%). Ground-glass opacity (GGO) was commonly found in children aged > 9 years (19/26, 73.1%), whereas peribronchial thickening was predominantly found in children aged 9 years, whereas peribronchial thickening was predominant in children aged

Abstract Background The deep learning-based nodule detection (DLD) system improves nodule detection performance of observers on chest radiographs (CXRs). However, its performance in different pulmonary nodule (PN) locations remains unknown. Methods We divided the CXR intrathoracic region into non-danger zone (NDZ) and danger zone (DZ). The DZ included the lung apices, paramediastinal areas, and retrodiaphragmatic areas, where nodules could be missed. We used a dataset of 300 CXRs (100 normal and 200 abnormal images with 216 PNs [107 NDZ and 109 DZ nodules]). Eight observers (two thoracic radiologists [TRs], two non-thoracic radiologists [NTRs], and four radiology residents [RRs]) interpreted each radiograph with and without the DLD system. The metric of lesion localization fraction (LLF; the number of correctly localized lesions divided by the total number of true lesions) was used to evaluate the diagnostic performance according to the nodule location. Results The DLD system demonstrated a lower LLF for the detection of DZ nodules (64.2) than that of NDZ nodules (83.2, p = 0.008). For DZ nodule detection, the LLF of the DLD system (64.2) was lower than that of TRs (81.7, p

Background and Objectives: This study aims to analyze survival in peritoneal and hemodialysis patients using chest radiography and biochemical parameters, determine common dialysis etiologies and causes of death, reveal prognostic factors, and contribute to clinical practice. Materials and Methods: A retrospective cross-sectional study was conducted with data from 33 peritoneal dialysis and 37 hemodialysis patients collected between October 2018 and February 2020. Survival and mortality were retrospectively tracked over 70 months (October 2018–June 2024). Chest X-ray measurements (cardiothoracic index, pulmonary vascular pedicle width, right pulmonary artery diameter, diaphragmatic height) and biochemical parameters (urea, albumin, creatinine, parathormone, ferritin, hemoglobin, arterial blood gas, potassium) were analyzed for their impact on survival. Statistical analyses included descriptive statistics, chi-square test, Fisher’s exact test, Bayesian analysis, McNemar test, Kaplan–Meier survival analysis, Cox regression, Bayesian correlation test, linear regression analysis (scatter plot), and ROC analysis. SPSS 20.0 was used for data analysis, with p < 0.05 considered statistically significant. Results: Hypertension, type 2 diabetes, and urogenital disorders were the main dialysis etiologies. Peritonitis (38.5%) and cardiovascular diseases (47.4%) were the leading causes of death in peritoneal and hemodialysis patients, respectively. Significant chest X-ray differences included pulmonary vascular pedicle width and pulmonary artery diameter in hemodialysis and diaphragm height in peritoneal dialysis. Kaplan–Meier showed no survival difference between methods. Cox regression identified age, intact parathormone levels, iPTH/PVPW ratio, and clinical status as survival and mortality factors. The iPTH/PVPW ratio cut-off for mortality prediction was ≤6.8. Conclusions: Age, intact parathormone levels, pulmonary vascular pedicle width, and clinical status significantly impact survival in dialysis patients. Management of hypertension and diabetes, management and follow-up of urogenital disorders, infection control, patient education, and regular cardiovascular check-ups may improve survival rates. Additionally, the iPTH/PVPW ratio can predict mortality risk.

Background Inactive or old, healed tuberculosis (TB) on chest radiograph (CR) is often found in high TB incidence countries, and to avoid unnecessary evaluation and medication, differentiation from active TB is important. This study develops a deep learning (DL) model to estimate activity in a single chest radiographic analysis. Methods A total of 3,824 active TB CRs from 511 individuals and 2,277 inactive TB CRs from 558 individuals were retrospectively collected. A pretrained convolutional neural network was fine-tuned to classify active and inactive TB. The model was pretrained with 8,964 pneumonia and 8,525 normal cases from the National Institute of Health (NIH) dataset. During the pretraining phase, the DL model learns the following tasks: pneumonia vs. normal, pneumonia vs. active TB, and active TB vs. normal. The performance of the DL model was validated using three external datasets. Receiver operating characteristic analyses were performed to evaluate the diagnostic performance to determine active TB by DL model and radiologists. Sensitivities and specificities for determining active TB were evaluated for both the DL model and radiologists. Results The performance of the DL model showed area under the curve (AUC) values of 0.980 in internal validation, and 0.815 and 0.887 in external validation. The AUC values for the DL model, thoracic radiologist, and general radiologist, evaluated using one of the external validation datasets, were 0.815, 0.871, and 0.811, respectively. Conclusion This DL-based algorithm showed potential as an effective diagnostic tool to identify TB activity, and could be useful for the follow-up of patients with inactive TB in high TB burden countries.

Aim:Lower respiratory tract infections (LRTIs) are one of the leading causes of mortality and morbidity in children. Chest X-rays, which are frequently used in diagnosis, cause ionizing radiation exposure and a loss of time. We aimed to compare the diagnostic accuracy of chest radiography (CR) and lung ultrasonography (US) in patients with LRTIs.Materials and Methods:This study was designed as methodological research. Of the 62 patients evaluated in our study, four refused to participate, and eight were excluded from the study due to their underlying chronic diseases. All 50 remaining patients (between the ages of 0-18 years) were evaluated with a preliminary LRTI diagnosis. Lung US was performed by a 3rd-year pediatric resident who had six hours of online US training. CR was taken after lung US.Results:The mean age of the 50 cases included in this study was five years and three months; 35 of the 50 patients (70%) had a clinical diagnosis of pneumonia, 15 (30%) of them had a clinical diagnosis of bronchiolitis. Statistically significant interobserver agreement was found between US and CR [Kappa value 0.772, 95% confidence interval (0.590-0.925) (p=0.000)]. The sensitivity of lung US was 95%, and its specificity was 85.7% when CR was accepted as the gold standard.Conclusion:Our study demonstrates that lung US can be used instead of CR to diagnose and follow-up pediatric cases with LRTIs.

The COVID-19 pandemic has put intense pressure on the healthcare systems. As the lung complication of COVID-19, pneumonia can be assessed by chest radiography which can be used to predict the severity of patient deterioration using Brixia and RALE scores. This research aims to assess the Radiologists' agreement on diagnosing pneumonia COVID-19 by RT-PCR in CXR using the Brixia and RALE score at Dr. Sardjito Central General Hospital from May 2020-January 2021. Two separate radiologists scored initial chest radiographs for RALE and Brixia independently. The analysis assessed included a descriptive analysis of demographic data, and Bland-Altman plots were used to visualize intra-observer agreement. A total of 332 samples were 162 men (48.8%) and 170 women (51.2%), with a mean age of 42.37. The ICC of Brixia score (0.855, CI:0.794-0.895) and RALE score (0.756, CI:0.662-0.812). Bland–Altman analysis revealed a bias of 5.08 ± 6.04 (95% limits of agreement of -6.760 and 16.929) for Brixia and RALE scores and significantly correlated (r=0.886 (p0.05)). The average score of Brixia (6.29±4.430) and RALE (11.56±9.997) in men was higher than in women. The agreement of Radiologists in diagnosing pneumonia COVID-19 using Brixia and RALE scores with the Bland Altman curve was significant or reliable.