Chest Radiographs Of Patients Research Articles

Deep learning prediction of survival in patients with heart failure using chest radiographs.

Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our studyisto develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.

Diagnostic role of thoracic ultrasound in patients with acute respiratory failure at emergency service.

This study aimed to elucidate the effectiveness of bedside thoracic ultrasound according to BLUE protocol and to investigate its superiority over other imaging methods in the emergency service. A total of 120 patients admitted to our institution's emergency care department due to respiratory distress have been enrolled in this prospective research. Thorax USG has been performed in the right and left hemithorax at the points specified in the BLUE protocol for each patient. Pleural sliding motion, A-lines, B-lines, consolidation, effusion, and the presence of barcode signs were evaluated individually. Age, sex, comorbid diseases, other radiological examination findings, laboratory findings, final clinical diagnosis, and hospitalization-discharge status of the patients were recorded. When a correct diagnosis of pneumonia has been analyzed for imaging techniques, the diagnostic rate of chest radiography was 83.3%, CT was 100.0%, and USG was 66.6%. The correct diagnostic rate of chest radiography was 94.5%; CT and USG were 100.0%. The correct diagnosis of pulmonary edema on chest radiography was 94.5%; CT and USG were 100.0%. While the correct diagnosis of pleural effusion on chest radiography and CT was 100.0%, it was 92.3% in USG imaging. Finally, CT and USG imaging performed better than chest radiography in patients with pneumothorax (chest radiography 80.0%, CT and USG 100%). USG imaging could be preferred in the diagnosis of pneumonia, pulmonary edema, pleural effusion, pneumothorax, pulmonary embolism, and differential diagnosis at the emergency service.

Deep learning to predict long-term mortality from plain chest radiographs in patients referred for suspected angina

Abstract Background The chest radiograph (CXR) is a well-established and broadly used first line diagnostic tool in patients with suspected cardiac conditions. In previous literature, artificial intelligence (AI) based interpretation of CXR has been shown to predict follow-up mortality of patients screened for neoplastic disease. Purpose In this context, we summarize our experience with the training, testing, and validating (internally and externally) of a deep learning (DL) model purposefully designed for predicting, from a single projection (posteroanterior/anteroposterior) CXR, long-term mortality of patients referred for angina and suspected coronary artery disease (CAD). Methods Demographic, clinical, and follow-up data of patients referred for angina to our institution (located in southern Europe) and undergoing coronary angiography were analyzed retrospectively. A deep convolutional neural network (DCNN) was designed to predict follow-up mortality from CXRs. External validation was performed on patients referred to a different medical Institution (located in north-western Europe). Results 6031 was randomly divided for model training (70%; n=4259) and model fine-tuning/model validation (10%; n=602). Internal clinical validation (model testing) was performed with the remaining patients (20%; n=1170). Patients were stratified according to AI-based interpretation quartiles (DCNN-CXR risk score). Median follow-up was 6.1 years (IQR 3.3 – 8.7) with a Kaplan-Meier (KM) overall estimated mortality of 21.9% (CI 19.2%-24.5%). Estimated mortality increased significantly according to the DCNN-CXR risk score (Low-risk 5%, Moderate 17%, High 29%, Very High 46%; p&amp;lt;0.0001) (figure 1-A). At Cox regression, the AI-derived CXR-score was the strongest predictor of follow-up mortality (p&amp;lt;0.005; OR: 3.16; CI: 2.47-3.85) and had an AUC of 0.793 (95% AUC CI: 0.759-0.827, Sens. 78%, Spec. 0.68%), that was significantly better than that achieved when using coronary angiography findings (AUC: 0.569, 95% CI: 0.526-0.611) (p&amp;lt;0.001) and age (AUC 0.735, 95% CI: 0.694-0.776) (p&amp;lt;0.004) as predictors (figure 1-B). The DCNN-CXR mortality prediction model improved when age and CAD status at the referral time were included (AUC 0.81; CI: 0.775-0.843). Preliminary results on external validation confirmed the DCNN-CXR-risk prediction performance (AUC 0.712 CI: 0.495-0.928; Sens 0.838; Spec 0.338). Conclusion Our DCNN model predicted, from a CXR, long-term overall mortality of patients with suspected angina pectoris referred for coronary angiography. The performance has been confirmed at internal and external validation, on patients in a different European country. The DCNN CXR-risk score could stratify long-term mortality risk better than any other risk factor, including CAD presence and degree. These findings may be used to optimize screening and prevention actions for this very comorbid group of patients.

Utility of routine postoperative chest radiography in patients undergoing clavicle fixation: a retrospective chart review.

Although uncommon, pneumothorax is a potentially serious complication following open reduction and internal fixation (ORIF) of clavicle fractures. In many centres it is routine practice to obtain postoperative chest radiographs following ORIF of clavicle fractures to assess for iatrogenic pneumothorax. Given the need to contain health care costs, the low sensitivity for detecting small pneumothorax and a desire to decrease patient radiation exposure, the practice of ordering chest radiographs following ORIF of clavicle fractures may be unnecessary. All patients undergoing ORIF of clavicle fractures with plate and screw fixation at Kingston Health Sciences Centre between April 2009 and June 2020 were identified from the Discharge Abstract Database (inpatient) and National Ambulatory Care Reporting System (outpatient) using relevant Canadian Classification of Health Intervention procedure codes. Charts were manually reviewed to confirm diagnosis and procedure, and patients with preoperative pneumothorax were excluded. The frequency of postoperative chest radiograph and pneumothorax detection were calculated. Among the 292 patients who underwent ORIF of clavicle fractures during the study period, 17 were excluded for having a pneumothorax on preoperative chest radiograph. Of the remaining 275 patients, 101 (36.7%) had postoperative chest radiographs, of whom none were found to have postoperative iatrogenic pneumothorax. Since 2009, the rate of routine postoperative chest radiography following ORIF of clavicle fractures is 36.7% at our centre. During this time period, none of the 101 patients who had postoperative chest radiographs had a postoperative iatrogenic pneumothorax. To our knowledge, this is the largest series of patients available, and our findings confirm those of several smaller studies. Owing to the low rate of postoperative iatrogenic pneumothorax, we conclude that postoperative chest radiography is unnecessary following ORIF of clavicle fractures.

Comparative Review of Computed Tomography Scans and Radiography in Evaluating Blunt Chest Trauma

Previous comparative studies revealed that a substantial proportion of blunt chest trauma often goes unnoticed when evaluated \with chest X-rays. The computed tomography scan, therefore, could play an important role in the initial assessment of patients following blunt chest trauma. This review aims to highlight the findings of chest computed tomography scans and compare them to chest radiography in patients with thoracic trauma resulting from blunt trauma. A systematic search across diverse online databases was performed in PubMed, MEDLINE, and Embase databases. The study selection process was guided by inclusion criteria that focused on individuals afflicted with chest injuries following accidents, engaged in a direct comparison of the diagnostic efficacy of chest CT scans and conventional chest X-rays, and was available in English. In the medical literature, chest radiography and CT imaging provide essential insights to guide clinical decision-making. The precise ability to distinguish between typical and atypical indications of damage across both superficial and deeper anatomical structures holds considerable importance during the initial assessment of such cases. A systematic approach, exemplified through the proposed "outside-in" sequence, offers a proficient strategy to evaluate all potential injuries comprehensively. This approach streamlines the evaluation process, ultimately empowering the medical team to promptly and effectively identify and manage these injuries.

Negative Chest Radiograph in Patients with Symptomatic Lung Cancer

Objective: To evaluate the percentage of negative chest radiograph in patients with symptomatic lung cancer. Materials and Methods: The authors retrospectively reviewed the chest radiographs of 263 patients with symptomatic lung cancer. The findings were divided into two categories and three subgroups, negative findings as normal, no abnormality detected or abnormal, or no cancer suspected, and positive findings as abnormal or cancer suspected. The recorded data included the tumor size, location, features of all lesions, the duration of symptom, and time intervals between the first chest radiograph until diagnosis. Computed tomography (CT) scan of the negative finding chest radiographs were reviewed to verify whether the causes of unsuspected malignancy were on a radiograph. Results: Negative chest radiographs in the present study were 12.9%. Three patients (1.1%) were classified as entirely normal. Most findings in the abnormal, no cancer suspected group were patchy infiltration (8.4%), interstitial infiltration (1.9%), and thin wall lung cavity (1.1%). The major causes of negative findings were tumor location, size, conspicuity, obscured primary tumor, pulmonary tuberculosis mimicking lung cancer, and characteristic of lung cavity on the radiograph. Conclusion: Negative chest radiographs can be found even in patients with symptomatic lung cancer, resulting in delayed diagnosis and treatment. Using chest radiograph as a first-line imaging investigation, especially in high-risk lung cancer patients, should be cognizant of false negatives. Keywords: Lung cancer; Chest radiograph

Interpretation of chest radiography in patients with known or suspected SARS-CoV-2 infection: what we learnt from comparison with computed tomography.

Differently from computed tomography (CT), well-defined terminology for chest radiography (CXR) findings and standardized reporting in the setting of known or suspected COVID-19 are still lacking. We propose a revision of CXR major imaging findings in SARS-CoV-2 pneumonia derived from the comparison of CXR and CT, suggesting a precise and standardized terminology for CXR reporting. This description will consider asymptomatic patients, symptomatic patients, and patients with SARS-CoV-2-related pulmonary complications. We suggest using terms such as ground-glass opacities, consolidation, and reticular pattern for the most common findings, and characteristic chest radiographic pattern in presence of one or more of the above-mentioned findings with peripheral and mid-to-lower lung zone distribution.

Radiograph Feature in COVID-19 Patients With Diabetes Mellitus At Dr. Soetomo Hospital Surabaya

Objectives : COVID-19 disease causes considerable morbidity and mortality. Older age and the presence of diabetes mellitus, hypertension and obesity significantly increase the risk of hospitalization and death in COVID-19 patients. COVID-19 patients with other comorbidities such as diabetes are at higher risk of developing severe pneumonia. Several studies have shown a higher susceptibility to several infectious diseases in people with diabetes, possibly due to an unregulated immune system. Plasma glucose levels and diabetes are independent predictors of mortality and morbidity in patients with SARS. Chest X-ray imaging plays an important role in both assessment of disease extent and follow-up, by knowing the pattern of chest radiography in patients with COVID-19 with Diabetes Mellitus, a radiologist can assist clinicians in predicting the progression of chest radiography in relation to blood glucose levels in patients. Method : A descriptive study with a retrospective design was conducted on 134 patients with confirmed COVID-19 and diabetes mellitus who were admitted to Dr. Soetomo General Academic Hospital in 2020. Data on chest radiography and random blood glucose levels were obtained during the first 24 hours of treatment. We evaluated the lung disease based on features, distribution and location. Result : The gender of COVID-19 patients who had the most Diabetes Mellitus was male (55.2%) with the highest age group being more than 50 years (70.8%) with the highest random glucose levels > 200 mg/dl (64.9%). The most radiographic features in COVID-19 patients with Diabetes Mellitus were consolidation/alveolar infiltrate both in patients with glucose level > 200 mg/dl (64.9%) or < 200 mg/dl (35.1%), with the most peripheral distribution (97,8%) and the most locations being a combination of the upper-middle-lower zone at right lung (81,3%) and left lung (70,9%) Conclusion: Radiograph feature of COVID-19 patients with Diabetes Mellitus both in patients with glucose level > 200 mg/dl and < 200 mg/dl were mostly consolidation/alveolar infiltrate, with the most peripheral distribution and the most locations being a combination of the upper-middle-lower zone.

Correlation of chest radiography of confirmed COVID-19 patients with comorbid hypertension and diabetes mellitus

Introduction: Several studies showed 324 severe cases of COVID-19 and 1234 mild cases with the highest comorbidities of Hypertension, Diabetes Mellitus, Chronic Obstruvtives Pulmonary Disease (COPD), and Cardiovascular disease. These comorbid factors lead to a poor prognosis in COVID-19. Chest radiography is an important modality as one of the parameters that can indicate the severity of COVID-19. This study aims to determine the relationship between Covid-19, comorbid Hypertension, and Diabetes Mellitus with chest radiography. Method: This research is analitic observational with cross-sectional, relationship between Covid-19 patients with comorbid Hypertension and Diabetes Mellitus with chest radiography (type, location, and extent of lesions) that Modified Chest X-Ray Scoring System in Evaluating Severity of COVID-19 Patient in Dr. Soetomo General Hospital Surabaya, Indonesia in 2021, COVID-19 radiology category. The data from PKU Muhammadiyah Gamping Hospital, Yogyakarta retrospectively from the medical records of Covid-19 patients who met the inclusion and exclusion criteria. Chi-Square analyzed the results variables with unpaired categorization. Result: Most of the respondents who had comorbid diseases had moderate chest radiological features (65.4%) and those who did not have comorbid diseases had mild chest radiological features (71.9%), the results of chi-square data analysis between variables were p: 0.000. Conclusion: The results of data analysis showed that comorbid diseases had a significant relationship with chest radiography in patients with confirmed COVID-19. The novelty of this study is the importance of radiological modalities as one of the parameters that can indicate the severity of Covid-19 patients with comorbidities.

Deep learning to detect significant coronary artery disease from plain chest radiographs AI4CAD

BackgroundThe predictive role of chest radiographs in patients with suspected coronary artery disease (CAD) is underestimated and may benefit from artificial intelligence (AI) applications. ObjectivesTo train, test, and validate a deep learning (DL) solution for detecting significant CAD based on chest radiographs. MethodsData of patients referred for angina and undergoing chest radiography and coronary angiography were analysed retrospectively. A deep convolutional neural network (DCNN) was designed to detect significant CAD from posteroanterior/anteroposterior chest radiographs. The DCNN was trained for severe CAD binary classification (absence/presence). Coronary angiography reports were the ground truth. Stenosis severity of ≥70% for non–left main vessels and ≥ 50% for left main defined severe CAD. ResultsInformation of 7728 patients was reviewed. Severe CAD was present in 4091 (53%). Patients were randomly divided for algorithm training (70%; n = 5454) and fine-tuning/model validation (10%; n = 773). Internal clinical validation (model testing) was performed with the remaining patients (20%; n = 1501). At binary logistic regression, DCNN prediction was the strongest severe CAD predictor (p < 0.0001; OR: 1.040; CI: 1.032–1.048). Using a high sensitivity operating cut-point, the DCNN had a sensitivity of 0.90 to detect significant CAD (specificity 0.31; AUC 0.73; 95% CI DeLong, 0.69–0.76). Adding to the AI chest radiograph interpretation angina status improved the prediction (AUC 0.77; 95% CI DeLong, 0.74–0.80). ConclusionAI-read chest radiographs could be used to pre-test significant CAD probability in patients referred for suspected angina. Further studies are required to externally validate our algorithm, develop a clinically applicable tool, and support CAD screening in broader settings.

Accuracy of pulmonary ultrasound versus chest radiography for detecting pulmonary congestion resulting from increased pulmonary blood flow in children with congenital heart disease and left-to-right shunting

Introduction: Congenital heart diseases are a set of simple or complex dynamic heterogeneous malformations that originate in the embryo, progress through the pregnancy, and considerably change throughout the course of extrauterine life. They are the most common congenital defect, with a global prevalence estimated at 1.8 cases per 100 live births. These diseases can be classified by the cardiovascular segment affected and the impact on blood oxygenation and pulmonary flow. One of their most feared repercussions is pulmonary hypertension, which can result from lung exposure to increased blood flow, which changes vascular tone and causes medial hypertrophy and vascular remodeling. The advent of echocardiography has revolutionized healthcare for these children; however, chest radiography is still the most commonly used method for detecting increased blood flow and pulmonary edema. Objectives: Thus, this study compared the accuracy of ultrasound and chest radiography in detecting congestion resulting from increased pulmonary blood flow in children with congenital heart disease and left-to-right shunting. Methods: This is an observational longitudinal analytical prospective study comparing lung ultrasounds and chest radiographs of patients with congenital heart disease. Results: Our results suggest that ultrasound, which is a noninvasive diagnostic method that emits no radiation, has a discriminatory capacity similar to that of radiography, and has 92.59 % accuracy, 89.47 % sensitivity, and 100 % specificity. Conclusions: Pulmonary ultrasound is highly accurate, sensitive, and specific, and can be used to assess pulmonary congestion and edema resulting from increased blood flow in patients with heart disease.

CHEST RADIOGRAPHIC FINDINGS IN RT-PCR POSITIVE COVID-19 PATIENTS

Aims and objectives : To describe the chest radiographic ndings in RT-PCR positive COVID 19 patients and to evaluate the effectiveness of chest radiographs in detecting pulmonary alterations in RT-PCR positive COVID-19 patients. Materials and methods: A retrospective cross-sectional study was carried out from May 2021 to June 2021 in a tertiary care hospital in Karnataka, India. A total of 100 covid positive patients who underwent chest X-ray were included in the study. The chest X-rays were evaluated for presence or absence and the type of pulmonary alterations, and their distribution. Chi-square test was used to compare percentages and p- value of less than 0.05 was considered statistically signicant. Results: In total, 100 patients consisting of 70 males and 30 females with positive RT-PCR results for COVID-19 pneumonia were included in this study, their mean age being 51.6 years. The presence of at least one chest alteration was found in 90 patients. The presence of ground-glass opacities (51%) and consolidation (41%) was the most common ndings. Reticular opacities were found in 6% of the cases. Seventy percent of the radiographic ndings were bilateral and involvement of both peripheral and central zones was signicantly frequent. Conclusion: Frequent ndings at chest radiography in patients with COVID-19 included bilateral lower zone ground glass opacity and consolidation.

Correlation of Interleukin-6 Levels with Clinical Features and Chest X-Ray Imaging in Coronavirus Disease-19 (COVID-19) Patients at Dr. Mohammad Hoesin General Hospital Palembang

Background. COVID-19 infection, both moderate and severe symptoms can cause pneumonia that can be detected on a chest X-ray. Along with the increasing severity of the clinical picture of COVID 19, it can also trigger a cytokine storm, one of which is an increase in Interleukin-6 levels. This study was conducted to see the correlation between IL-6 levels with clinical features and chest radiographs in patients with COVID-19&#x0D; Methods. This research is a cross-sectional study using an observational analytic. The samples in this study were confirmed COVID-19 patients who were being treated at Dr. Mohammad Hoesin General Hospital, Palembang. A history and physical examination were performed to determine the clinical picture as well as a chest X-ray and IL-6 levels.&#x0D; Results. There were 31 samples of COVID 19 patients. High levels of IL-6 were found in 26 (83.9%) samples. The clinical picture of the patient was dominated by dyspnea as much as 19 (61.3%), fever 16 (5.6%), low O2 saturation 12 (38.4%) and a chest X-ray of pneumonia 26 (83.9%). There was a significant relationship (P&lt;0.05) between IL-6 levels with clinical features and chest X-rays. The R-value on the thorax with pneumonia (0.692), lesion area (0.711) and clinical features with temperature (0.906), respiratory rate (0.706) indicated a strong correlation, while O2 (-0.732) indicated a strong negative correlation.&#x0D; Conclusion. There is a significantly strong correlation between Interleukin 6 levels with clinical features and chest X-rays in patients with COVID-19.

Utility of a Deep Learning Algorithm for Detection of Reticular Opacity on Chest Radiography in Patients With Interstitial Lung Disease.

BACKGROUND. Deep learning has been heavily explored for pulmonary nodule detection on chest radiographs. Detection of reticular opacity in interstitial lung disease (ILD) is challenging and may also benefit from a deep learning algorithm (DLA). OBJECTIVE. The purpose of this study was to evaluate the utility of a DLA for detection of reticular opacity on chest radiographs of patients with surgically confirmed ILD. METHODS. This retrospective study included 197 patients (130 men, 67 women; mean age, 62.6 ± 7.6 [SD] years) with surgically proven ILD between January 2017 and December 2018 who underwent preoperative chest radiography and chest CT within a 30-day interval. A total of 197 age- and sex-matched control patients with normal chest radiographs were randomly selected. A commercially available DLA was used to detect lower lobe or subpleural abnormalities; those matching the reticular opacity location on CT were deemed true-positive. Six readers (three thoracic radiologists, three residents) independently reviewed radiographs with and without the DLA for the presence of reticular opacity. Interobserver agreement was assessed. Diagnostic performance was compared among interpretations. Subanalysis was performed according to CT-based classification of the severity of reticular opacity. Performance of the DLA was also assessed on 102 chest radiographs from a second institution (51 patients with ILD, 51 matched patients in the control group). RESULTS. Interobserver agreement was moderate (κ = 0.517) for readers alone and almost perfect (κ = 0.870) for readers using the DLA. Sensitivity, specificity, and accuracy of the DLA for reticular opacity were 98.0%, 99.0%, and 98.5%; of pooled readers alone were 77.3%, 92.3%, and 84.8%; and of readers using the DLA were 93.8%, 97.3%, and 95.6%. All metrics were significantly better (all p ≤ .002) for the DLA and for readers using the DLA than for readers alone. Sensitivity for readers without and with the DLA were 66.7% and 86.8% for mild disease, 84.2% and 98.8% for moderate disease, and 87.3% and 100.0% for severe disease. The DLA had 100.0% accuracy at the second institution. CONCLUSION. The DLA outperformed readers in detection of reticular opacity, and use of the DLA improved reader performance and interobserver agreement. The benefit of the DLA was more notable in sensitivity than in specificity and was maintained in mild disease. CLINICAL IMPACT. Use of the DLA may facilitate detection of reticular opacity on chest radiographs in the early stages of ILD.

Gamification in Radiology Training Module Developed During the Society for Imaging Informatics in Medicine Annual Meeting Hackathon.

The purpose of this manuscript is to report our experience in the 2021 SIIM Virtual Hackathon, where we developed a proof-of-concept of a radiology training module with elements of gamification. In the 50h allotted in the hackathon, we proposed an idea, connected with colleagues from five different countries, and completed an operational proof-of-concept, which was demonstrated live at the hackathon showcase, competing with eight other teams. Our prototype involved participants annotating publicly available chest radiographs of patients with tuberculosis. We showed how we could give experience points to trainees based on annotation precision compared to ground truth radiologists' annotation, ranked in a live leaderboard. We believe that gamification elements could provide an engaging solution for radiology education. Our project was awarded first place out of eight participating hackathon teams.

COVID-19 in Kidney Transplant Recipient and Waitlist Patients: Implications of Chest Radiographic Severity Score.

Purpose:To evaluate the chest radiographic severity score (CXR-SS) for coronavirus disease 2019 (COVID-19) patients who are kidney transplant recipients compared with patients on the waitlist.Study Design and Methods:This retrospective cohort includes 78 kidney transplant recipients (50 men, mean age 59.9±11.9 y) and 59 kidney transplant waitlist patients (33 men, mean age 58.8±10.8 y) diagnosed with COVID-19 between March 15 and May 30, 2020 with reverse transcriptase-polymerase chain reaction. Patient chest radiographs were divided into 6 zones and examined for consolidation. Primary outcome was mortality. Secondary outcomes included hospital admission, intensive care unit (ICU) admission, and intubation. Predictors of our primary and secondary outcomes were identified by bivariate analysis and multivariate regression analysis.Results:No significant difference was found in CXR-SS between 2 groups (P=0.087). Transplant recipients had significantly higher rates of hospitalization (odds ratio, 6.8; 95% confidence interval: 1.7, 39.3; P<0.001), ICU admission (odds ratio, 6.5; 95% confidence interval [CI]: 1.8-35.9; P=0.002), intubation (odds ratio, 11; 95% CI: 2.4-96.9; P=0.001), and mortality (odds ratio, 17; 95% CI: 3.9-153.1; P<0.001). A higher CXR-SS was not predictive of mortality, intubation, or ICU admission. CXR-SS was associated with hospital admission overall (odds ratio, 1.613; 95% CI: 1.04-2.49; P=0.0314).Conclusion:The CXR-SS was not predictive of mortality, ICU admission or intubation in our population. Kidney transplant patients with COVID-19 had near universal hospital admission, more than one-third mortality and about a quarter were intubated and admitted to the ICU—all significantly worse outcomes than for patients on the transplant waitlist.

The Radiographic and Mycobacteriologic Correlates of Subclinical Pulmonary TB in Canada: A Retrospective Cohort Study

Very little is known about subclinical pulmonary TB (PTB), a recently described intermediate state, in high-income countries. What is the prevalence of subclinical PTB in Canada? What are its diagnostic chest radiography features? What is the relationship between those features and time to culture positivity, and what is the association between DNA fingerprint clustering, a measure of local transmission, and radiographic or other features in the foreign-born? We used primary source data to identify a 16-year retrospective cohort of patients with PTB. Demographic and mycobacteriologic features in patients with subclinical and clinical disease were compared, and the reason for assessment of patients with subclinical disease was described. Diagnostic chest radiographs in patients with subclinical disease were read by two independent readers and were arbitrated by a third reader. Linear regression was used to compute time to culture positivity (in days) in relationship to the change in chest radiograph findings from normal or minimally abnormal to moderately or far advanced, adjusted for age and sex and stratified by reason for assessment. Multivariate logistic regression was used in foreign-born patients with subclinical disease to determine associations between DNA fingerprint clustering of Mycobacterium TB isolates and age, sex, chest radiograph features, and time since arrival. We identified 1,656 patients with PTB, 347 of whom (21%) were subclinical. Compared with patients with clinical disease, patients with subclinical disease were more likely to be foreign-born (90.2%vs79.6%) and to demonstrate negative smear results (88.2%vs43.5%). The median time to culture-positivity was 18days (interquartile range [IQR], 14-25days) vs12days (IQR, 7-17days). Most patients with PTB (75.2%) were identified during active case finding. Parenchymal disease was absent or minimal on chest radiography in 86.4%of patients. More advanced disease on chest radiography was associated with shorter times to culture positivity in nonstratified (by 3.3days) and stratified (by 4.5-5.8days) analysis (active case-finding groups). DNA fingerprint clustering was associated with male sex and a longer time between arrival and diagnosis. Subclinical patients with PTB constitute a substantial and heterogeneous minority of patients with PTB in high-income countries. DNA fingerprint clustering is consistent with some, albeit limited, local transmission.

The method of increasing the information content of microfocus X-ray images

A method for processing microfocus X-ray images is described. It is based on high-frequency filtration and morphological image processing, which increases the contrast of the X-ray details. One of the most informative X-ray techniques is microfocus X-ray. In some cases, microfocus X-ray images cannot be reliably analyzed due to the peculiarities of the shooting method. So, the main disadvantages of microfocus X-ray images are most often an uneven background, distorted brightness characteristics and the presence of noise. The proposed method for enhancing the contrast of fine image details is based on the idea of combining high-frequency filtering and morphological image processing. The method consists of the following steps: noise suppression in the image, high-frequency filtering, morphological image processing, obtaining the resulting image. As a result of applying the method, the brightness of the contours in the image is enhanced. In the resulting image, all objects will have double outlines. The method was tested in the processing of 50 chest radiographs of patients with various pathologies. Radiographs were performed at the Mariinsky Hospital of St. Petersburg using digital stationary and mobile X-ray machines. In most of the radiographs, it was possible to improve the images contrast, to highlight the objects boundaries. Besides, the method was applied in microfocus X-ray tomography to improve the information content of projection data and improve the reconstruction of the 3D image of the research object. In both the first and second cases, the method showed satisfactory results. The developed method makes it possible to significantly increase the information content of microfocus X-ray images. The obtained practical results make it possible to count on broad prospects for the method application, especially in microfocus X-ray.

Association of Vitamin D Deficiency in Newly Diagnosed Pulmonary Tuberculosis

Aim: Relationship between Vitamin D deficiency and pulmonary tuberculosis. Methodology: Study duration: November 2020 to April 2021 Sampling technique: A case-control study Setting: Hayatabad Medical Complex, Peshawar It included 30 adult newly identified sputum-quality pulmonary tuberculosis patients and 30 age and sex matched healthy cases as controls. All cases had undergone a thorough medical examination and repeated laboratory tests, including vitamin D, calcium, and sputum for AFB and X-ray chest. Results: Majority were males (88%). In the Study group, BMI decreased significantly i.e. 19.0 vs 23.5. Serum vitamin D concentrations were significantly lower in the tuberculosis group i.e. 17.9ng/dl than in the control group 24.8ng/dl. Mean of serum albumin in the control group was 3.9 ng/dl whereas 2.9 ng/dl in the study group. Conclusion: Hypovitaminosis D was associated with more severe medical symptoms, increased sputum smear positivity and large lesions on chest radiographs in patients with pulmonary tuberculosis. Keywords: Vitamin D, Pulmonary Tuberculosis, Sputum

Deep Learning for Detection of Pulmonary Metastasis on Chest Radiographs.

Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD system can improve diagnostic yield for newly visible lung metastasis on chest radiographs in patients with cancer. Materials and Methods A regulatory-approved CAD system for lung nodules was implemented to interpret chest radiographs from patients referred by the medical oncology department in clinical practice. In this retrospective diagnostic cohort study, chest radiographs interpreted with assistance from a CAD system after the implementation (January to April 2019, CAD-assisted interpretation group) and those interpreted before the implementation (September to December 2018, conventional interpretation group) of the CAD system were consecutively included. The diagnostic yield (frequency of true-positive detections) and false-referral rate (frequency of false-positive detections) of formal reports of chest radiographs for newly visible lung metastasis were compared between the two groups using generalized estimating equations. Propensity score matching was performed between the two groups for age, sex, and primary cancer. Results A total of 2916 chest radiographs from 1521 patients (1546 men, 1370 women; mean age, 62 years) and 5681 chest radiographs from 3456 patients (2941 men, 2740 women; mean age, 62 years) were analyzed in the CAD-assisted interpretation and conventional interpretation groups, respectively. The diagnostic yield for newly visible metastasis was higher in the CAD-assisted interpretation group (0.86%, 25 of 2916 [95% CI: 0.58, 1.3] vs 0.32%, 18 of 568 [95% CI: 0.20, 0.50%]; P = .004). The false-referral rate in the CAD-assisted interpretation group (0.34%, 10 of 2916 [95% CI: 0.19, 0.64]) was not inferior to that in the conventional interpretation group (0.25%, 14 of 5681 [95% CI: 0.15, 0.42]) at the noninferiority margin of 0.5% (95% CI of difference: -0.15, 0.35). Conclusion A deep learning-based computer-aided detection system improved the diagnostic yield for newly visible metastasis on chest radiographs in patients with cancer with a similar false-referral rate. © RSNA, 2021 Online supplemental material is available for this article.