Search

Introduction: Tuberculosis (TB) remains a highly prevalent disease in Malaysia. Early identification using cost-effective methods such as chest radiography can reduce the health burden of a TB epidemic. However, normal chest radiographic findings are common. This study aimed to evaluate the characteristics of smear-positive pulmonary TB with normal chest radiographic findings during an outbreak. Methods: A cross-sectional study was conducted by reviewing the medical records of 56 pulmonary TB cases registered at Kodiang Health Clinic from April to October 2022. Smear-negative and extrapulmonary TB cases were excluded. Relevant information was extracted from the medical records and recorded in a case report form for data management and analysis. Results: Approximately 60.7% of the cases had symptoms lasting >2 weeks, and 89.3% showed abnormal findings upon clinical examination. Additionally, 73.2% had sputum acid-fast bacilli counts of ≥1+, and the sputum Mycobacterium tuberculosis culture and sensitivity test findings were positive in 82.1% of the cases. The proportion of smear-positive pulmonary TB with normal chest radiographic findings was 42.9%. The factors associated with smear-positive pulmonary TB with normal chest radiographic findings included being under 18 years old (P=0.021), being a student (P=0.010), being single (P=0.012) and being asymptomatic (P=0.04). Conclusion: Normal chest radiographic findings may lead to a misdiagnosis of smear-positive pulmonary TB, especially during an outbreak. Therefore, active case detection among close contacts with risk factors for normal radiographic findings should consider additional supportive tests. [ABSTRACT FROM AUTHOR]

Introduction: Central venous catheter (CVC) tip placement guided by chest X‐ray (CXR) landmarks is currently prone to inconsistency and malpositioning. This study aims to better define the relationship between the cavoatrial junction (CAJ) and selected X‐ray landmarks. Methods: Chest CTs of 100 patients were retrospectively assessed. CT images were converted to a 'virtual CXR' using a digital workstation, enabling simultaneous localisation of the CAJ and evaluation of CXR landmarks. Vertical distances between the CAJ and selected landmarks were measured for each patient. Measurements were assessed for correlation with age and compared between age groups and sexes. Results: The mean vertical distance of the following landmarks above the CAJ was found: the carina (46.2 mm), the intersection of the bronchus intermedius and the right heart border (7.6 mm) and the superior inflection of the right heart border (Sup‐RHB) (13.0 mm). The maximum lateral bulge of the right heart border (Lat‐RHB) was 18.4 mm below the CAJ. A new landmark: the mid‐superior right heart border, defined as the mid‐point between the Sup‐RHB and Lat‐RHB, was the closest to the CAJ, lying 2.6 mm below the CAJ. Conclusion: We propose that the CVC tip can be placed at the mid‐superior right heart border landmark. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate an artificial intelligence (AI)–assisted double reading system for detecting clinically relevant missed findings on routinely reported chest radiographs. Methods: A retrospective study was performed in two institutions, a secondary care hospital and tertiary referral oncology centre. Commercially available AI software performed a comparative analysis of chest radiographs and radiologists' authorised reports using a deep learning and natural language processing algorithm, respectively. The AI-detected discrepant findings between images and reports were assessed for clinical relevance by an external radiologist, as part of the commercial service provided by the AI vendor. The selected missed findings were subsequently returned to the institution's radiologist for final review. Results: In total, 25,104 chest radiographs of 21,039 patients (mean age 61.1 years ± 16.2 [SD]; 10,436 men) were included. The AI software detected discrepancies between imaging and reports in 21.1% (5289 of 25,104). After review by the external radiologist, 0.9% (47 of 5289) of cases were deemed to contain clinically relevant missed findings. The institution's radiologists confirmed 35 of 47 missed findings (74.5%) as clinically relevant (0.1% of all cases). Missed findings consisted of lung nodules (71.4%, 25 of 35), pneumothoraces (17.1%, 6 of 35) and consolidations (11.4%, 4 of 35). Conclusion: The AI-assisted double reading system was able to identify missed findings on chest radiographs after report authorisation. The approach required an external radiologist to review the AI-detected discrepancies. The number of clinically relevant missed findings by radiologists was very low. Clinical relevance statement: The AI-assisted double reader workflow was shown to detect diagnostic errors and could be applied as a quality assurance tool. Although clinically relevant missed findings were rare, there is potential impact given the common use of chest radiography. Key Points: • A commercially available double reading system supported by artificial intelligence was evaluated to detect reporting errors in chest radiographs (n=25,104) from two institutions. • Clinically relevant missed findings were found in 0.1% of chest radiographs and consisted of unreported lung nodules, pneumothoraces and consolidations. • Applying AI software as a secondary reader after report authorisation can assist in reducing diagnostic errors without interrupting the radiologist's reading workflow. However, the number of AI-detected discrepancies was considerable and required review by a radiologist to assess their relevance. [ABSTRACT FROM AUTHOR]

Objectives: To develop and validate a deep learning-based prognostic model in patients with idiopathic pulmonary fibrosis (IPF) using chest radiographs. Methods: To develop a deep learning-based prognostic model using chest radiographs (DLPM), the patients diagnosed with IPF during 2011–2021 were retrospectively collected and were divided into training (n = 1007), validation (n = 117), and internal test (n = 187) datasets. Up to 10 consecutive radiographs were included for each patient. For external testing, three cohorts from independent institutions were collected (n = 152, 141, and 207). The discrimination performance of DLPM was evaluated using areas under the time-dependent receiver operating characteristic curves (TD-AUCs) for 3-year survival and compared with that of forced vital capacity (FVC). Multivariable Cox regression was performed to investigate whether the DLPM was an independent prognostic factor from FVC. We devised a modified gender-age-physiology (GAP) index (GAP-CR), by replacing DLCO with DLPM. Results: DLPM showed similar-to-higher performance at predicting 3-year survival than FVC in three external test cohorts (TD-AUC: 0.83 [95% CI: 0.76–0.90] vs. 0.68 [0.59–0.77], p < 0.001; 0.76 [0.68–0.85] vs. 0.70 [0.60–0.80], p = 0.21; 0.79 [0.72–0.86] vs. 0.76 [0.69–0.83], p = 0.41). DLPM worked as an independent prognostic factor from FVC in all three cohorts (ps < 0.001). The GAP-CR index showed a higher 3-year TD-AUC than the original GAP index in two of the three external test cohorts (TD-AUC: 0.85 [0.80–0.91] vs. 0.79 [0.72–0.86], p = 0.02; 0.72 [0.64–0.80] vs. 0.69 [0.61–0.78], p = 0.56; 0.76 [0.69–0.83] vs. 0.68 [0.60–0.76], p = 0.01). Conclusions: A deep learning model successfully predicted survival in patients with IPF from chest radiographs, comparable to and independent of FVC. Clinical relevance statement: Deep learning-based prognostication from chest radiographs offers comparable-to-higher prognostic performance than forced vital capacity. Key Points: • A deep learning-based prognostic model for idiopathic pulmonary fibrosis was developed using 6063 radiographs. • The prognostic performance of the model was comparable-to-higher than forced vital capacity, and was independent from FVC in all three external test cohorts. • A modified gender-age-physiology index replacing diffusing capacity for carbon monoxide with the deep learning model showed higher performance than the original index in two external test cohorts. [ABSTRACT FROM AUTHOR]

Heart failure (HF) cannot be characterized as a condition/ disease in its own but is clinically described as a syndrome in which severe dysfunction leads to the inability of the cardiovascular system to maintain adequate blood circulation. From a clinical point of view, heart failure is the syndrome characterized by signs of stasis (pulmonary and/or systemic) and low cardiac output, occurring in most cases secondary to the evolution of a disease with cardiac involvement. There are limited and specific mechanisms by which heart disease can lead to cardiovascular failure. HF represents the onset of several phenomena that may be simultaneous or sequential and can be systematized into: circulatory failure, with decreased tissue perfusion; congestive manifestations by increased pulmonary and/ or systemic venous pressure; myocardial failure, specifically alteration of myocardial systolic and/or diastolic function. [ABSTRACT FROM AUTHOR]

Simple Summary: Immune-mediated polyarthritis (IMPA) is the most common disease affecting multiple joints in dogs. This study aimed to assess the utility of thoracic radiography and abdominal ultrasonography in canine IMPA and to assess whether abnormal findings influenced the overall case management of the patient at the time of diagnosis. Seventy-seven dogs were included. Thoracic radiography was considered not useful in the overall case management at the time of IMPA diagnosis in 70 cases, whilst abdominal ultrasonography was considered not useful in 57. Therefore, in the majority of the cases in this study, thoracic radiography and abdominal ultrasonography were considered not useful towards the overall case management at the time of initial diagnosis of IMPA. Thoracic radiography and abdominal ultrasonography are part of standard diagnostic investigations in cases of canine immune-mediated polyarthritis (IMPA). However, the clinical importance of thoracic and abdominal imaging towards the management of canine IMPA currently remains unknown. The primary aim of this study was to describe the findings documented on thoracic radiography and abdominal ultrasonography in dogs diagnosed with IMPA, and to evaluate the diagnostic utility of thoracic radiography and abdominal ultrasonography in the initial approach and management of these cases. Seventy-seven dogs diagnosed with IMPA who underwent thoracic radiography and abdominal ultrasonography at a single referral hospital between 2008 and 2022 were included. The diagnostic imaging studies of these 77 dogs were reviewed by one blinded board-certified diagnostic imaging specialist for quality assurance. The medical records, including the diagnostic imaging reports of these dogs, were then reviewed by three blinded board-certified internal medicine specialists. Using a modified version of a previous question and scoring system, the three internal medicine specialists then generated an answer for the overall diagnostic utility and a diagnostic utility score for thoracic radiography and abdominal ultrasonography for each case. The abnormal findings identified in radiography and ultrasonography were described. In the cases where the findings were considered significant enough to immediately affect the case management, the results of the further investigations that were subsequently performed were also described. No abnormalities were detected in thoracic radiography for 30 cases, and none were detected in abdominal ultrasound for 6. The majority of the internists considered thoracic radiography to be not useful in the overall case management at the time of IMPA diagnosis in 70 cases, and considered abdominal ultrasonography to be not useful in the overall case management in 57 cases. The majority of the internists agreed on the utility of thoracic radiography in 95% of the cases, and in 61% of the cases for abdominal ultrasonography. The most common finding in the thoracic radiography was a mild bronchial pulmonary pattern, and the most common in the abdominal ultrasonography was mild lymphadenomegaly. Therefore, although thoracic radiography and abdominal ultrasonography identified numerous abnormal findings in this population of dogs, in the majority of the cases, the findings were deemed not useful towards the overall case management at the time of the initial diagnosis of IMPA. Thus, the use of thoracic radiography and abdominal ultrasonography should be taken into careful consideration when considering initial diagnostic investigations for canine IMPA. [ABSTRACT FROM AUTHOR]

We performed this study to investigate if main pulmonary artery (mPA) diameter measured by axial chest computed tomography (CT) can predict the presence and degree of echocardiography-measured pulmonary hypertension (ePH) among emergency department (ED) patients. This retrospective cross-sectional study enrolled patients who underwent both chest CT and echocardiography within 24 h at the ED. The ePH was estimated using right ventricular systolic pressure (RVSP). RVSP <40 mmHg was classified as normal; 40-49 mmHg, mild ePH; 50-75 mmHg, moderate ePH; and =76 mmHg, severe ePH. Among 485 adult patients, 297 (61.2%) had normal RVSP and mean mPA of 30.3 mm. The numbers of patients with mild, moderate and severe ePH were 92 (19.0%), 85 (17.5%) and 11 (2.3%) with corresponding mean mPA diameters of 32.4, 34.5 and 35.9 mm, respectively. The best mPA diameters for predicting mild, moderate and severe ePH were 30.6, 31.8 and 33.8 mm, with area under the receiver operating characteristic curve of 0.697, 0.727 and 0.797 and sensitivities of 72.9%, 71.9% and 81.8%, respectively. Axial CT-measured mPA diameter can predict the presence and degree of ePH among ED patients. If the CT-measured mPA diameter is greater than 30.6 mm, the possibility of pulmonary hypertension should be considered and applied to the patient's treatment. [ABSTRACT FROM AUTHOR]

Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. For this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named “CovCXR-Net”, identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named “MDCXR3-Net”, identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named “MDCXR4-Net”, is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09 %, 97.74 %, and 90,37 % respectively with three benchmarks.

Introduction: Tuberculosis (TB) remains a highly prevalent disease in Malaysia. Early identification using cost-effective methods such as chest radiography can reduce the health burden of a TB epidemic. However, normal chest radiographic findings are common. This study aimed to evaluate the characteristics of smear-positive pulmonary TB with normal chest radiographic findings during an outbreak. Methods: A cross-sectional study was conducted by reviewing the medical records of 56 pulmonary TB cases registered at Kodiang Health Clinic from April to October 2022. Smear-negative and extrapulmonary TB cases were excluded. Relevant information was extracted from the medical records and recorded in a case report form for data management and analysis. Results: Approximately 60.7% of the cases had symptoms lasting >2 weeks, and 89.3% showed abnormal findings upon clinical examination. Additionally, 73.2% had sputum acid-fast bacilli counts of ≥1+, and the sputum Mycobacterium tuberculosis culture and sensitivity test findings were positive in 82.1% of the cases. The proportion of smear-positive pulmonary TB with normal chest radiographic findings was 42.9%. The factors associated with smear-positive pulmonary TB with normal chest radiographic findings included being under 18 years old (P=0.021), being a student (P=0.010), being single (P=0.012) and being asymptomatic (P=0.04). Conclusion: Normal chest radiographic findings may lead to a misdiagnosis of smear-positive pulmonary TB, especially during an outbreak. Therefore, active case detection among close contacts with risk factors for normal radiographic findings should consider additional supportive tests.

Suboptimal chest radiographs (CXR) can limit interpretation of critical findings. Radiologist-trained AI models were evaluated for differentiating suboptimal(sCXR) and optimal(oCXR) chest radiographs. Our IRB-approved study included 3278 CXRs from adult patients (mean age 55 ± 20 years) identified from a retrospective search of CXR in radiology reports from 5 sites. A chest radiologist reviewed all CXRs for the cause of suboptimality. The de-identified CXRs were uploaded into an AI server application for training and testing 5 AI models. The training set consisted of 2202 CXRs (n = 807 oCXR; n = 1395 sCXR) while 1076 CXRs (n = 729 sCXR; n = 347 oCXR) were used for testing. Data were analyzed with the Area under the curve (AUC) for the model's ability to classify oCXR and sCXR correctly. For the two-class classification into sCXR or oCXR from all sites, for CXR with missing anatomy, AI had sensitivity, specificity, accuracy, and AUC of 78%, 95%, 91%, 0.87(95% CI 0.82-0.92), respectively. AI identified obscured thoracic anatomy with 91% sensitivity, 97% specificity, 95% accuracy, and 0.94 AUC (95% CI 0.90-0.97). Inadequate exposure with 90% sensitivity, 93% specificity, 92% accuracy, and AUC of 0.91 (95% CI 0.88-0.95). The presence of low lung volume was identified with 96% sensitivity, 92% specificity, 93% accuracy, and 0.94 AUC (95% CI 0.92-0.96). The sensitivity, specificity, accuracy, and AUC of AI in identifying patient rotation were 92%, 96%, 95%, and 0.94 (95% CI 0.91-0.98), respectively. The radiologist-trained AI models can accurately classify optimal and suboptimal CXRs. Such AI models at the front end of radiographic equipment can enable radiographers to repeat sCXRs when necessary. [ABSTRACT FROM AUTHOR]

The role of preoperative chest radiography (CR) for prediction of postoperative pneumonia remains uncertain. We aimed to develop and validate a prediction model for postoperative pneumonia incorporating findings of preoperative CRs evaluated by a deep learning-based computer-aided detection (DL-CAD) system This retrospective study included consecutive patients who underwent surgery between January 2019 and March 2020 and divided into development (surgery in 2019) and validation (surgery between January and March 2020) cohorts. Preoperative CRs obtained within 1-month before surgery were analyzed with a commercialized DL-CAD that provided probability values for the presence of 10 different abnormalities in CRs. Logistic regression models to predict postoperative pneumonia were built using clinical variables (clinical model), and both clinical variables and DL-CAD results for preoperative CRs (DL-CAD model). The discriminative performances of the models were evaluated by area under the receiver operating characteristic curves. In development cohort (n = 19,349; mean age, 57 years; 11,392 men), DL-CAD results for pulmonary nodules (odds ratio [OR, for 1% increase in probability value], 1.007; p = 0.021), consolidation (OR, 1.019; p < 0.001), and cardiomegaly (OR, 1.013; p < 0.001) were independent predictors of postoperative pneumonia and were included in the DL-CAD model. In validation cohort (n = 4957; mean age, 56 years; 2848 men), the DL-CAD model exhibited a higher AUROC than the clinical model (0.843 vs. 0.815; p = 0.012). Abnormalities in preoperative CRs evaluated by a DL-CAD were independent risk factors for postoperative pneumonia. Using DL-CAD results for preoperative CRs led to an improved prediction of postoperative pneumonia. [ABSTRACT FROM AUTHOR]

Copyright of Summa, Animali da Compagnia is the property of Point Veterinaire Italie s.r.l. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: To compare the visibility of anatomical structures and overall quality of the attenuation images obtained with a dark-field X-ray radiography prototype with those from a commercial radiography system. Methods: Each of the 65 patients recruited for this study obtained a thorax radiograph at the prototype and a reference radiograph at the commercial system. Five radiologists independently assessed the visibility of anatomical structures, the level of motion artifacts, and the overall image quality of all attenuation images on a five-point scale, with 5 points being the highest rating. The average scores were compared between the two image types. The differences were evaluated using an area under the curve (AUC) based z-test with a significance level of p ≤ 0.05. To assess the variability among the images, the distributions of the average scores per image were compared between the systems. Results: The overall image quality was rated high for both devices, 4.2 for the prototype and 4.6 for the commercial system. The rating scores varied only slightly between both image types, especially for structures relevant to lung assessment, where the images from the commercial system were graded slightly higher. The differences were statistically significant for all criteria except for the bronchial structures, the cardiophrenic recess, and the carina. Conclusions: The attenuation images acquired with the prototype were assigned a high diagnostic quality despite a lower resolution and the presence of motion artifacts. Thus, the attenuation-based radiographs from the prototype can be used for diagnosis, eliminating the need for an additional conventional radiograph. Key Points: • Despite a low tube voltage (70 kVp) and comparably long acquisition time, the attenuation images from the dark-field chest radiography system achieved diagnostic quality for lung assessment. • Commercial chest radiographs obtained a mean rating score regarding their diagnostic quality of 4.6 out of 5, and the grating-based images had a slightly lower mean rating score of 4.2 out of 5. • The difference in rating scores for anatomical structures relevant to lung assessment is below 5%. [ABSTRACT FROM AUTHOR]

Objective A cardiothoracic ratio ≥0.50 is widely used as an indicator of cardiomegaly, but associations between the cardiothoracic ratio and left ventricular systolic dysfunction (LVSD) have not been investigated previously. We conducted this study to investigate the relationship between cardiothoracic ratio measured using computed tomography (CT) and left ventricular ejection fraction (LVEF), and to determine the optimal cardiothoracic ratio for predicting left ventricular systolic dysfunction (LVSD). Methods A retrospective cross-sectional study was performed using data from patients who underwent both chest CT and echocardiography at the emergency department from January 1 to December 31, 2021. The patients were classified as normal, or having mild, moderate, and severe LVSD based on their LVEF, and the cardiothoracic ratios of each group were compared. The receiver operating characteristic (ROC) curve analyses were used to identify the optimal cardiothoracic ratio for prediction of mild, moderate, and severe LVSD. Results The final study population included 444 patients. The median CT-measured cardiothoracic ratio was 0.54 for patients with normal LVEF, and 0.60 for patients with LVSD (P

Thoracic radiography and abdominal ultrasonography are part of standard diagnostic investigations in cases of canine immune-mediated polyarthritis (IMPA). However, the clinical importance of thoracic and abdominal imaging towards the management of canine IMPA currently remains unknown. The primary aim of this study was to describe the findings documented on thoracic radiography and abdominal ultrasonography in dogs diagnosed with IMPA, and to evaluate the diagnostic utility of thoracic radiography and abdominal ultrasonography in the initial approach and management of these cases. Seventy-seven dogs diagnosed with IMPA who underwent thoracic radiography and abdominal ultrasonography at a single referral hospital between 2008 and 2022 were included. The diagnostic imaging studies of these 77 dogs were reviewed by one blinded board-certified diagnostic imaging specialist for quality assurance. The medical records, including the diagnostic imaging reports of these dogs, were then reviewed by three blinded board-certified internal medicine specialists. Using a modified version of a previous question and scoring system, the three internal medicine specialists then generated an answer for the overall diagnostic utility and a diagnostic utility score for thoracic radiography and abdominal ultrasonography for each case. The abnormal findings identified in radiography and ultrasonography were described. In the cases where the findings were considered significant enough to immediately affect the case management, the results of the further investigations that were subsequently performed were also described. No abnormalities were detected in thoracic radiography for 30 cases, and none were detected in abdominal ultrasound for 6. The majority of the internists considered thoracic radiography to be not useful in the overall case management at the time of IMPA diagnosis in 70 cases, and considered abdominal ultrasonography to be not useful in the overall case management in 57 cases. The majority of the internists agreed on the utility of thoracic radiography in 95% of the cases, and in 61% of the cases for abdominal ultrasonography. The most common finding in the thoracic radiography was a mild bronchial pulmonary pattern, and the most common in the abdominal ultrasonography was mild lymphadenomegaly. Therefore, although thoracic radiography and abdominal ultrasonography identified numerous abnormal findings in this population of dogs, in the majority of the cases, the findings were deemed not useful towards the overall case management at the time of the initial diagnosis of IMPA. Thus, the use of thoracic radiography and abdominal ultrasonography should be taken into careful consideration when considering initial diagnostic investigations for canine IMPA.

Background: Severe courses and high hospitalization rates were ubiquitous during the first pandemic SARS-CoV-2 waves. Thus, we aimed to examine whether integrative diagnostics may aid in identifying vulnerable patients using crucial data and materials obtained from COVID-19 patients hospitalized between 2020 and 2021 (n = 52). Accordingly, we investigated the potential of laboratory biomarkers, specifically the dynamic cell decay marker cell-free DNA and radiomics features extracted from chest CT. Methods: Separate forward and backward feature selection was conducted for linear regression with the Intensive-Care-Unit (ICU) period as the initial target. Three-fold cross-validation was performed, and collinear parameters were reduced. The model was adapted to a logistic regression approach and verified in a validation naïve subset to avoid overfitting. Results: The adapted integrated model classifying patients into "ICU/no ICU demand" comprises six radiomics and seven laboratory biomarkers. The models' accuracy was 0.54 for radiomics, 0.47 for cfDNA, 0.74 for routine laboratory, and 0.87 for the combined model with an AUC of 0.91. Conclusion: The combined model performed superior to the individual models. Thus, integrating radiomics and laboratory data shows synergistic potential to aid clinic decision-making in COVID-19 patients. Under the need for evaluation in larger cohorts, including patients with other SARS-CoV-2 variants, the identified parameters might contribute to the triage of COVID-19 patients. [ABSTRACT FROM AUTHOR]

Objectives: To externally validate the performance of a commercial AI software program for interpreting CXRs in a large, consecutive, real-world cohort from primary healthcare centres. Methods: A total of 3047 CXRs were collected from two primary healthcare centres, characterised by low disease prevalence, between January and December 2018. All CXRs were labelled as normal or abnormal according to CT findings. Four radiology residents read all CXRs twice with and without AI assistance. The performances of the AI and readers with and without AI assistance were measured in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. Results: The prevalence of clinically significant lesions was 2.2% (68 of 3047). The AUROC, sensitivity, and specificity of the AI were 0.648 (95% confidence interval [CI] 0.630–0.665), 35.3% (CI, 24.7–47.8), and 94.2% (CI, 93.3–95.0), respectively. AI detected 12 of 41 pneumonia, 3 of 5 tuberculosis, and 9 of 22 tumours. AI-undetected lesions tended to be smaller than true-positive lesions. The readers' AUROCs ranged from 0.534–0.676 without AI and 0.571–0.688 with AI (all p values < 0.05). For all readers, the mean reading time was 2.96–10.27 s longer with AI assistance (all p values < 0.05). Conclusions: The performance of commercial AI in these high-volume, low-prevalence settings was poorer than expected, although it modestly boosted the performance of less-experienced readers. The technical prowess of AI demonstrated in experimental settings and approved by regulatory bodies may not directly translate to real-world practice, especially where the demand for AI assistance is highest. Key Points: • This study shows the limited applicability of commercial AI software for detecting abnormalities in CXRs in a health screening population. • When using AI software in a specific clinical setting that differs from the training setting, it is necessary to adjust the threshold or perform additional training with such data that reflects this environment well. • Prospective test accuracy studies, randomised controlled trials, or cohort studies are needed to examine AI software to be implemented in real clinical practice. [ABSTRACT FROM AUTHOR]

Vertebral heart size (VHS) is widely determined in clinical practice as an objective method to assess the cardiac silhouette dimensions. However, a key limitation is that it is difficult to determine VHS in dogs with vertebral alterations. This retrospective, method comparison, observer agreement study sought to overcome this limitation by using the heart‐to‐single vertebra ratio (HSVR), by evaluating the level of agreement between VHS and HSVR, as well as the intra‐ and inter‐observer agreement for HSVR. Three independent observers retrospectively evaluated thoracic radiographs obtained over a set time period. Exclusion criteria were the presence of alterations of the thoracic spine and the inability to clearly outline the cardiac silhouette. The lengths of the vertebral bodies, from the fourth to eighth thoracic vertebra, and VHS were measured on each radiograph. The HSVR was calculated by dividing the sum of the cardiac long and short axes by the length of each vertebral body. Eighty dogs of different breeds were included in the final analysis. Lin's concordance correlation coefficients revealed strong correlations between VHS and HSVR (0.91–0.96), and the Bland–Altman plots showed low bias (0.01–0.2) between the methods. The mean absolute errors indicated low average magnitudes of error (0.11–0.28). The intraclass correlation coefficients showed good to excellent inter‐observer (0.87–0.92; P = 0.000) and intra‐observer (0.87–0.99; P <.001) agreement. In the authors' opinion, this new method, which is less time consuming and more objective, could offer a valuable alternative to VHS. [ABSTRACT FROM AUTHOR]

Background: In Thailand, epidemiological data on silicosis in the ceramic sector is lacking and the underdiagnosis of silicosis remains an extensive concern. Therefore, this study aimed to determine the prevalence of silicosis and the extent of underdiagnosis among Thai ceramic workers by reinterpreting chest radiographs previously taken by a health check-up unit. Methods: This retrospective cross-sectional study was conducted on ceramic workers undergoing health surveillance using chest radiographs in one ceramic factory in September 2018. All chest radiographs were done retrospectively, then were reinterpreted by professional readers specially trained in using the ILO International Classification of Radiograph of Pneumoconioses (ILO/ICRP). Chest radiographs with a profusion of 1/1 or greater were suggestive of silicosis. Results: Out of the 244 participants undergoing chest radiography, the prevalence of silicosis was 2.9%. Overall, the mean age of the participants was 41 years, and 72.1% were female. Among individuals with silicosis, the median age was 43 years; 71.4% were male; the average employment duration was 26.9 years; while the male sex was the significant variable associated with silicosis with an odds ratio of 7.01 (95% confidence interval 1.31 to 37.4). Regarding the underdiagnosis, the health check-up unit failed to recognize all individuals with silicosis, and could not detect any radiographic chest abnormalities in 57.1% of those with silicosis. Conclusions: Despite the low prevalence of silicosis among Thai ceramic workers, this finding indicates ongoing exposure to silica in the ceramic industry. In addition, a significant proportion of the silicosis cases were underrecognized. Future efforts to prevent underdiagnosis and improve an occupational health surveillance service in Thailand are needed. [ABSTRACT FROM AUTHOR]

Purpose To develop and validate a deep learning-based screening tool for the early diagnosis of scoliosis using chest radiographs with a semi-supervised generative adversarial network (GAN). Materials and Methods Using a semi-supervised learning framework with a GAN, a screening tool for diagnosing scoliosis was developed and validated through the chest PA radiographs of patients at two different tertiary hospitals. Our proposed method used training GAN with mild to severe scoliosis only in a semi-supervised manner, as an upstream task to learn scoliosis representations and a downstream task to perform simple classification for differentiating between normal and scoliosis states sensitively. Results The area under the receiver operating characteristic curve, negative predictive value (NPV), positive predictive value, sensitivity, and specificity were 0.856, 0.950, 0.579, 0.985, and 0.285, respectively. Conclusion Our deep learning-based artificial intelligence software in a semi-supervised manner achieved excellent performance in diagnosing scoliosis using the chest PA radiographs of young individuals; thus, it could be used as a screening tool with high NPV and sensitivity and reduce the burden on radiologists for diagnosing scoliosis through health screening chest radiographs. [ABSTRACT FROM AUTHOR]

ObjectiveTo report values of the chest radiographic thoracic area (CRTA) in ventilated, term-born infants without respiratory disease and to evaluate whether CRTA is related to demographic data at birth.MethodsRetrospective, observational cohort study in a tertiary neonatal unit at King's College Hospital NHS Foundation Trust, London, UK.Newborn infants born after 36 completed weeks of gestation, ventilated for poor perinatal adaptation or hypoxic ischaemic encephalopathy without respiratory disease and admitted in a recent eight-year period (2014–2022).The CRTA was assessed by free-hand tracing of the perimeter of the thoracic area as outlined by the diaphragm and the rib cage excluding the mediastinal structures and was calculated using the Sectra PACS software.ResultsOne hundred and twenty-one infants (75 male) were included with a median (IQR) gestation of 40 (38–41) weeks and birth weight of 3.41 (3.04–3.75) kg. The median (IQR) CRTA was 2,589 (2,167–2,943) mm2 and was significantly related to birth weight (r = 0.316, p = 0.003), gestation at birth (r = 0.193, p = 0.032) and birth weight z-score (r = 0.187, p = 0.038).ConclusionsWe report values of the chest radiographic thoracic area in ventilated term-born infants which could be used as reference for determining respiratory disease severity.

Abstract Background In dogs, antimicrobial drugs are widely prescribed for aspiration pneumonia (AP) despite poor documentation of bacterial infection in AP (b‐AP) using bronchoalveolar lavage fluid (BALF) analysis. Interpretating discordant cytology and culture results is challenging, contributing to lack of a criterion standard, and highlighting differences between veterinary and human medical criteria for b‐AP. Objectives Determine how many dogs with AP had BALF collection and differences in diagnosis of b‐AP using veterinary vs human medical criteria. Report findings of noninvasive markers (e.g. fever, band neutrophilia, radiographic severity score) in dogs with and without b‐AP. Animals Retrospective cohort study of client‐owned dogs (n = 429) with AP at 2 university veterinary hospitals. Twenty‐four dogs met enrollment criteria. Methods Inclusion criteria were radiographic diagnosis of AP, ≥1 risk factor, CBC findings, and BALF cytology and culture results. Veterinary medical b‐AP criteria were cytology findings compatible with sepsis with or without positive culture, or cytology findings not consistent with sepsis and positive culture (≥1.7 × 103 cfu/mL). Human medical b‐AP criteria required culture with ≥104 cfu/mL or > 7% cells with intracellular bacteria on cytology. Results Only 24/429 dogs met all enrollment criteria; 379/429 dogs lacked BALF collection. Diagnosis of b‐AP differed using veterinary (79%) vs human (29%) medical criteria. Fever, band neutrophils and high radiographic scores were noted in dogs with and without b‐AP. Conclusions and Clinical Importance Lack of routine BALF collection hampers definitive recognition of bacterial infection in AP. Differences in dogs meeting veterinary vs human medical definitions for b‐AP and usefulness of noninvasive markers warrant further study to improve understanding of the role of bacteria in AP.

Background: Many invasive procedures performed in the emergency room (ER) have potential risks and complications. Because of their limitations, in particular size, portable X-ray devices are generally not used during such procedures. However, miniaturized units enable physicians to obtain X-ray images without assistance. Methods: We developed a safe, compact, and lightweight X-ray unit that was used during five invasive procedures in the ER. In all procedures, a chest X-ray image was obtained, to confirm the utility of the unit. Results: Case 1 (central venous catheter placement): After needle and guidewire insertion and catheter placement, the location of the catheter could be confirmed. Case 2 (chest tube insertion): During insertion of a chest tube into the pleural space, the tip of the thoracic tube was confirmed to be at the correct location. Case 3 (percutaneous tracheostomy or cricothyroidotomy): After needle and guidewire insertion, the guidewire was visualized in the right main bronchus and was inserted into the trachea. Case 4 (resuscitative endovascular aortic balloon of the aorta): The captured image revealed that the catheter was located in zone I before balloon inflation. Case 5 (Sengstaken-Blakemore tube): The image revealed that the balloon was located in the stomach. Conclusions: The portable X-ray unit improved medical safety during invasive procedures frequently performed in the ER. [ABSTRACT FROM AUTHOR]

This study was performed for the purpose of comparing vertebral heart score (VHS), radiographic left atrial dimension (RLAD) and vertebral left atrial size (VLAS) values derived from plain and contrast right lateral thoracic radiographs from 70 healthy, young adult Wistar albino rats and to identify reference values for these radiographic cardiac indices. Measurements were taken by two observers blinded to the study data. VHS, RLAD and VLAS median values and reference ranges were 8v and 7-9.3v for plain radiography, 8.2v and 7.4-9.5v for contrast radiography (P< 0.000), 1.3v and 1-1.8v for plain radiography, 1.3v and 1.1-1.6v for contrast radiography (P <0.000) and 1.9v and 1.4-2.4v for plain radiography and 1.95v 1.5-2.4v for contrast radiography (P<0.001), respectively. The only statistically significant difference was observed in terms of gender between VHS values from plain and contrast radiographs (P<0.02). Intraobserver and interobserver measurements revealed excellent agreement for radiographic cardiac indices obtained from contrast radiography. The study measurements indicate that contrast radiography provides a more effective quantitative assessment of cardiac and left atrial sizes than plain radiography. The radiographic cardiac index measurements presented in this study can serve as a reference baseline for both veterinarians and experimental cardiovascular studies. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Medical Imaging & Radiation Sciences is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

BackgroundThoracic ultrasonography (TUS) is widely used in equine practice but comparison to radiography is limited in horses.ObjectivesTo validate a novel, objective scoring system for TUS in adult horses and to compare ultrasonographic and radiographic findings.Animals13 healthy horses and 9 with confirmed bacterial pneumoniaMethodsProspective study in which TUS and radiography were performed on healthy horses and those with bacterial pneumonia confirmed by clinical signs and results of transtracheal wash analysis. Ultrasonography was scored utilizing a novel scoring system evaluating number of comet tail lesions, the presence or absence of pleural effusion and/or pulmonary consolidation in each intercostal space. Eighteen horses had thoracic radiographs taken that were scored by a board-certified radiologist utilizing a previously described system. Total scores were recorded and compared between control and diseased patients.Results/FindingsUltrasonographic scores were significantly higher in the diseased group (median= 126) than in the control group (median = 20, p = 0.01). Receiver operating characteristics (ROC) analysis identified a sensitivity of 66.7% (95% CI 0.417–1) and specificity of 92.3% (95% CI 0.462–1) for the ability of ultrasonography to identify bacterial pneumonia utilizing a TUS score cutoff of 37.Conclusions and clinical importanceTUS had moderate sensitivity and high specificity for identification of bacterial pneumonia in adult horses. TUS appears to be an acceptable stand-alone imaging modality for diagnosis of bacterial pneumonia in horses when radiography is not practical.

Background: Severe courses and high hospitalization rates were ubiquitous during the first pandemic SARS-CoV-2 waves. Thus, we aimed to examine whether integrative diagnostics may aid in identifying vulnerable patients using crucial data and materials obtained from COVID-19 patients hospitalized between 2020 and 2021 (n = 52). Accordingly, we investigated the potential of laboratory biomarkers, specifically the dynamic cell decay marker cell-free DNA and radiomics features extracted from chest CT. Methods: Separate forward and backward feature selection was conducted for linear regression with the Intensive-Care-Unit (ICU) period as the initial target. Three-fold cross-validation was performed, and collinear parameters were reduced. The model was adapted to a logistic regression approach and verified in a validation naïve subset to avoid overfitting. Results: The adapted integrated model classifying patients into “ICU/no ICU demand” comprises six radiomics and seven laboratory biomarkers. The models’ accuracy was 0.54 for radiomics, 0.47 for cfDNA, 0.74 for routine laboratory, and 0.87 for the combined model with an AUC of 0.91. Conclusion: The combined model performed superior to the individual models. Thus, integrating radiomics and laboratory data shows synergistic potential to aid clinic decision-making in COVID-19 patients. Under the need for evaluation in larger cohorts, including patients with other SARS-CoV-2 variants, the identified parameters might contribute to the triage of COVID-19 patients.

Mediastinal cysts are previously described as incidental findings in cats. A nine years old, 2.8 kg, Persian cat was presented to out Veterinary Teaching Hospital (VTH) for mild dyspnea. Chest radiographies, revealed an incapsulated soft tissue opacity in the cranial mediastinum. Thoracic lung ultrasonography (LUS), evinced the presence of a cyst-like structure. Furthermore, the cat was subjected to complete cardiological examination and complete blood analysis. Echoguided drainage followed by cytological examination was carried out in order to reach a definitive diagnostic and to improve the general status of the patient. No other medical treatment has been pursued. Monthly evaluations have been performed during a period of five months, and the drainage was repeated one more time until the complete resolution of the pathology. No signs of relapse have been noticed over a period of two years. Only four cats diagnosed with idiopathic mediastinal cyst have been mentioned in the literature. To the author’s best knowledge, this is the first case report which describes the dynamic evolution of an idiopathic mediastinum cyst in Persian cat presented for mild dyspnoea. [ABSTRACT FROM AUTHOR]

Purpose: We investigated whether lung ultrasound (US) performed in primary care is useful and feasible for diagnosing community-acquired pneumonia (CAP) compared with chest radiography, as most previous research has been conducted in hospital settings.Methods: We undertook a prospective observational cohort study of lung US performed in 12 primary care centers. Patients aged 5 years and older with symptoms suggesting CAP were examined with lung US (by 21 family physicians and 7 primary care pediatricians) and chest radiograph on the same day. We compared lung US findings with the radiologist's chest radiograph report as the reference standard, given that the latter is the most common imaging test performed for suspected CAP in primary care. The physicians had varied previous US experience, but all received a 5-hour lung US training program.Results: The study included 82 patients. Compared with chest radiography, positive lung US findings (consolidation measuring >1 cm or a focal/asymmetrical B-lines pattern) showed a sensitivity of 87.8%, a specificity of 58.5%, a positive likelihood-ratio of 2.12, and a negative likelihood-ratio of 0.21. Findings were similar regardless of the physicians' previous US training or experience. We propose a practical algorithm whereby patients having consolidation measuring greater than 1 cm or normal findings on lung US could skip chest radiography, whereas patients with a B-lines pattern without consolidation (given its low specificity) would need chest radiography to ensure appropriate management. Lung US was generally performed in 10 minutes or less.Conclusion: Point-of-care lung US in primary care could be useful for investigating suspected CAP (avoiding chest radiography in most cases) and is likely feasible in daily practice, as short training programs appear sufficient and little time is needed to perform the scan. [ABSTRACT FROM AUTHOR]

Introduction: To determine the radiologic profile of 'the prisoners at Osório Modular Prison and estimate the prevalence of active tuberculosis in the institution. Methods: We retrospectively analyzed 677 chest radiographs obtained for tuberculosis screening and data from the medical records of prisoners seen at the Radiology Department from July to October 2019. Results: Of 677 radiographs, 150 (22%) showed abnormalities. Of these, 109 (16% of total or 72% of abnormal radiographs) showed lesions characteristic of granulomatous disease. Of all 677 patients, 11.5% reported current or previous treatment of tuberculosis, accounting for 38% of all abnormal radiographs. Fifty patients with no previous history of tuberculosis had lesions that were most likely due to active tuberculosis (7.3% of total), and were referred for further investigation as new cases. The responses to the questionnaire revealed no significant difference between patients who reported or denied coughing when comparing those with normal vs abnormal radiographs. Conclusions: Individuals deprived of liberty had a high prevalence of radiologic abnormalities suggestive of granulomatous disease. These findings allow us to infer that there is a high prevalence of tuberculosis at Osório Modular Prison, probably at levels comparable to those of other prison facilities in Brazil. [ABSTRACT FROM AUTHOR]

Purpose: Hernias spanning both chest and abdominal walls are uncommon and associated with chest wall trauma, coughing and obesity. This study describes the radiographic appearance of these hernias to guide proper identification and operative planning. Proposed standardized reporting patterns are also presented. Methods: The cross sectional imaging of patients presenting with thoracoabdominal hernias was reviewed. Radiographic reports were supplemented by surgeon imaging review and operative findings during repair. Defect dimensions, hernia content, level of herniation, presence of osseous or cartilaginous disruption of the chest wall and degree of rib displacement were collected. Disruption of myofascial planes was also noted. Results: Six patients were identified. All hernias occurred below the 9th rib and were associated with complete intercostal muscle disruption. The transversus abdominis was disrupted in all hernias and the internal oblique was disrupted in five of the hernias. The majority (83%) had caudal rib displacement (median 6.8 cm compared to contralateral side). Median hernia width was 10.35 cm (1.6–19.1 cm) and median length was 10.2 cm (1.8–14.3 cm). Five patients had associated bone/cartilage injuries: two with 11th rib fractures, two with combined bone and cartilaginous fractures and one with a surgical rib resection. Conclusion: The typical injury pattern of thoracoabdominal hernias includes disruption of the intercostal muscles, transversus abdominis, and commonly the internal oblique with an intact external oblique. Inferior rib displacement by hernia contents and unopposed pull of the abdominal musculature is common. Osseous or cartilaginous disruption always occurs unless the defect is bounded on at least one side by a floating rib. [ABSTRACT FROM AUTHOR]

Copyright of Der Radiologe is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Der Radiologe is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: In dogs, antimicrobial drugs are widely prescribed for aspiration pneumonia (AP) despite poor documentation of bacterial infection in AP (b‐AP) using bronchoalveolar lavage fluid (BALF) analysis. Interpretating discordant cytology and culture results is challenging, contributing to lack of a criterion standard, and highlighting differences between veterinary and human medical criteria for b‐AP. Objectives: Determine how many dogs with AP had BALF collection and differences in diagnosis of b‐AP using veterinary vs human medical criteria. Report findings of noninvasive markers (e.g. fever, band neutrophilia, radiographic severity score) in dogs with and without b‐AP. Animals Retrospective cohort study of client‐owned dogs (n = 429) with AP at 2 university veterinary hospitals. Twenty‐four dogs met enrollment criteria. Methods: Inclusion criteria were radiographic diagnosis of AP, ≥1 risk factor, CBC findings, and BALF cytology and culture results. Veterinary medical b‐AP criteria were cytology findings compatible with sepsis with or without positive culture, or cytology findings not consistent with sepsis and positive culture (≥1.7 × 103 cfu/mL). Human medical b‐AP criteria required culture with ≥104 cfu/mL or > 7% cells with intracellular bacteria on cytology. Results: Only 24/429 dogs met all enrollment criteria; 379/429 dogs lacked BALF collection. Diagnosis of b‐AP differed using veterinary (79%) vs human (29%) medical criteria. Fever, band neutrophils and high radiographic scores were noted in dogs with and without b‐AP. Conclusions and Clinical Importance: Lack of routine BALF collection hampers definitive recognition of bacterial infection in AP. Differences in dogs meeting veterinary vs human medical definitions for b‐AP and usefulness of noninvasive markers warrant further study to improve understanding of the role of bacteria in AP. [ABSTRACT FROM AUTHOR]

Aim: This study aimed to determine the accuracy of the current methods for diagnosing heart diseases in cats. Materials and Methods: The data of 58 cats were retrospectively retrieved. Cats were classified into two groups: Thirty-eight cats with heart diseases and 20 healthy cats. Echocardiography was the gold standard method for diagnosing heart disease. The results of seven methods were retrieved: (1) Vertebral heart score (VHS) with a cutoff value >8, (2) VHS with a cutoff value >8.5, (3) multiplication of cardiac length (L) and width (W), (4) multiplication of cardiac L and W divided by the L of the fourth sternal thoracic bone, (5) N-terminal Pro-B-type natriuretic peptide (NT-proBNP) point-of-care test, (6) subjective ultrasonographic assessment of the left atrial size, and (7) subjective radiographic assessment of the left atrial size. Cross-tabulation was used to calculate the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for each test. This study found that using the NT-proBNP point-of-care test was optimal in the diagnosis of cats with heart disease. Results: The subjective ultrasonographic assessment of the left atrial size was good for diagnosing hypertrophic cardiomyopathy and congestive heart failure. Conclusion: This study showed that the more tests used, the higher the reliability of the diagnosis.

Objective To evaluate the prevalence rate, types, characteristics, and associated factors of esophageal dysphagia detected on chest X-ray images after videofluoroscopic swallowing study (VFSS). Methods The medical records of 535 adults were reviewed retrospectively. Chest X-ray images taken after barium swallow study were analyzed and presence of any residual barium in the esophagus was considered as esophageal dysphagia. Esophageal dysphagia was classified based on the largest width of barium deposit (mild,

Rationale and Objectives: To evaluate the effect of reduction in effective dose on the reproduction of anatomical structures in chest tomosynthesis (CTS).Materials and Methods: Twenty-four CTS examinations acquired at exposure settings resulting in an effective dose of 0.12 mSv for an average sized patient were included in the study. The examinations underwent simulated dose reduction to dose levels corresponding to 32%, 50%, and 70% of the original dose using a previously described and validated method. The image quality was evaluated by five thoracic radiologists who rated the fulfillment of specified image quality criteria in a visual grading study. The ratings for each image quality criterion in the dose-reduced images were compared to the corresponding ratings for the full-dose examinations using visual grading characteristics (VGC) analysis. The area under the resulting VGC curve (AUCVGC) provides a measure of the difference between the ratings, where an AUCVGC of 0.5 indicates no difference.Results: The dose reductions resulted in inferior reproduction of structures compared to the original dose level (AUCVGC <0.5). Structures in the central region of the lung obtained the lowest AUCVGC for each dose level whereas the reproduction of structures in the parenchyma was least affected by the dose reduction.Conclusion: Although previous studies have shown that dose reduction in CTS is possible without affecting the performance of certain clinical tasks, the reproduction of normal anatomical structures is significantly degraded even at small reductions. It is therefore important to consider the clinical purpose of the CTS examinations before deciding on a permanent dose reduction. [ABSTRACT FROM AUTHOR]

The goal of this review was to systematize the evidence on pulmonary ultrasound (PU) use in diagnosis, monitorization or hospital discharge criteria for patients with coronavirus disease 2019 (COVID-19). Evidence on the use of PU for diagnosis and monitorization of or as hospital discharge criteria for COVID-19 patients confirmed to have COVID-19 by reverse transcription polymerase chain reaction (RT-PCR) between December 1, 2019 and July 5, 2020 was compared with evidence obtained with thoracic radiography (TR), chest computed tomography (CT) and RT-PCR. The type of study, motives for use of PU, population, type of transducer and protocol, results of PU and quantitative or qualitative correlation with TR and/or chest CT and/or RT-PCR were evaluated. A total of 28 articles comprising 418 patients were involved. The average age was 50 y (standard deviation: 25.1 y), and there were 395 adults and 23 children. One hundred forty-three were women, 13 of whom were pregnant. The most frequent result was diffuse, coalescent and confluent B-lines. The plural line was irregular, interrupted or thickened. The presence of subpleural consolidation was noduliform, lobar or multilobar. There was good qualitative correlation between TR and chest CT and a quantitative correlation with chest CT of r = 0.65 (p < 0.001). Forty-four patients were evaluated only with PU. PU is a useful tool for diagnosis and monitorization and as criteria for hospital discharge for patients with COVID-19. [ABSTRACT FROM AUTHOR]

The aim of this study was to estimate echocardiographic elevated mean left atrium pressure (MLAP) based on measurements from thoracic radiographs and to determine a cut-off value for each radiographic measurement that suggests a high MLAP. A retrospective cross-sectional study was performed to include cases admitted from January 2015 to December 2016. Thoracic radiographic examinations from 93 dogs with and without a high MLAP were included. Specific measurements were made from thoracic radiographs and compared with echocardiographic variables known to indicate high MLAP. This comparison was used to generate equations that allowed the estimation of echocardiographic surrogates from the radiographic measurements. The values indicative of high MLAP were obtained using a regression curve. Formulas that indicated high MLAP were generated using a number of radiographic measurements. Positive echocardiographic findings of high MLAP were used as the gold standard. These formulas helped to predict high MLAP in myxomatous mitral valve disease (MMVD) without the need for echocardiographic examination. The best formula was left atrium (LA):aorta (Ao)echo = 0.03×(vertebral heart score,VHS) + 0.14×(LA) + 0.27×(LA:caudal vena cava (CVC)rad). Values ? 12.2v for VHS, ? 4.5cm for LA, ? 3.3 for LA:Aorad and ? 3.2 for LA:CVCrad suggested high MLAP. Thus, we propose equations, based on measurements from thoracic radiographs, to identify high MLAP. Simple radiographic thoracic measurements, such as LA:CVCrad, can be used to define overload and a high MLAP in dogs with MMVD.

Objectives: To evaluate the calibration of a deep learning (DL) model in a diagnostic cohort and to improve model's calibration through recalibration procedures. Methods: Chest radiographs (CRs) from 1135 consecutive patients (M:F = 582:553; mean age, 52.6 years) who visited our emergency department were included. A commercialized DL model was utilized to identify abnormal CRs, with a continuous probability score for each CR. After evaluation of the model calibration, eight different methods were used to recalibrate the original model based on the probability score. The original model outputs were recalibrated using 681 randomly sampled CRs and validated using the remaining 454 CRs. The Brier score for overall performance, average and maximum calibration error, absolute Spiegelhalter's Z for calibration, and area under the receiver operating characteristic curve (AUROC) for discrimination were evaluated in 1000-times repeated, randomly split datasets. Results: The original model tended to overestimate the likelihood for the presence of abnormalities, exhibiting average and maximum calibration error of 0.069 and 0.179, respectively; an absolute Spiegelhalter's Z value of 2.349; and an AUROC of 0.949. After recalibration, significant improvements in the average (range, 0.015–0.036) and maximum (range, 0.057–0.172) calibration errors were observed in eight and five methods, respectively. Significant improvement in absolute Spiegelhalter's Z (range, 0.809–4.439) was observed in only one method (the recalibration constant). Discriminations were preserved in six methods (AUROC, 0.909–0.949). Conclusion: The calibration of DL algorithm can be augmented through simple recalibration procedures. Improved calibration may enhance the interpretability and credibility of the model for users. Key Points: • A deep learning model tended to overestimate the likelihood of the presence of abnormalities in chest radiographs. • Simple recalibration of the deep learning model using output scores could improve the calibration of model while maintaining discrimination. • Improved calibration of a deep learning model may enhance the interpretability and the credibility of the model for users. [ABSTRACT FROM AUTHOR]

The objective of this study was to correlate cardiovascular parameters with obesity in adult cats. Forty mixed-breed cats (20 obese and 20 controls) underwent echocardiographic measurements and thoracic radiography to establish a relationship between the obtained data and the body condition score (BCS), body mass index (BMI), and vertebral heart size (VHS). Systolic arterial pressure (SAP) was also studied in 15 obese cats. Compared to the control cats, obese cats presented higher VHS values across several measurements, but among the echocardiographic parameters, only the difference in the left ventricular free wall at diastole was statistically significant. A positive relationship was established between body weight, left ventricular internal diameter at diastole, and left ventricular free wall at diastole. Positive relationships were also observed between BMI and diameter of the aorta, BCS and the left ventricular free wall at diastole, VHS and the left atrium, and the left atrial to aortic root diameter ratio and the left ventricular internal diameter at diastole. SAP was higher in obese cats and presented a positive correlation with body weight. Obesity correlated with an increase in SAP and with some echocardiographic and radiographic cardiac measurements in adult cats. Further studies are needed to better assess the effects of obesity on the cardiovascular system of cats and to reassess the parameters related to body weight and condition.

Introduction: The study was undertaken to evaluate the practice of chest radiography using different digital imaging systems and its influence on dose and image quality. Materials and Methods: The study was carried out in two hospitals from March 2016 to June 2016. Sixty ambulatory patients aged 21 to 60 years who were able to cooperate without difficulty and weighed between 60 to 80 kg were selected randomly. The active matrix flat panel imagers technology was employed in the direct radiography (DR) system for Hospital A, whilst Hospital B used the single read out computed radiography (CR) system. The dose area product (DAP) meter was utilized in measuring the entrance surface air kerma. The chest radiographs were evaluated by two radiologists. Results: The mean entrance surface doses (ESDs) for posteroanterior chest in Hospital A (0.098 mGy) was lower than that obtained in Hospital B (0.161 mGy). However, the ESDs at both centres were lower than the recommended value by the International Atomic Energy Agency (IAEA; 0.3 mGy). The quality of the images for chest radiography in both hospitals was adequate to make a diagnosis with ESDs and effective doses lower than those recommended by IAEA and United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR). Conclusion: The study serves to highlight the practice of chest radiography with two different systems and its influence on image quality and dose. It can be concluded that there were significant differences in image quality and radiation dose for chest radiography practice using CR and DR.

Objectives: To investigate the optimal input matrix size for deep learning-based computer-aided detection (CAD) of nodules and masses on chest radiographs.Methods: We retrospectively collected 2088 abnormal (nodule/mass) and 352 normal chest radiographs from two institutions. Three thoracic radiologists drew 2758 abnormalities regions. A total of 1736 abnormal chest radiographs were used for training and tuning convolutional neural networks (CNNs). The remaining 352 abnormal and 352 normal chest radiographs were used as a test set. Two CNNs (Mask R-CNN and RetinaNet) were selected to validate the effects of the squared different matrix size of chest radiograph (256, 448, 896, 1344, and 1792). For comparison, figure of merit (FOM) of jackknife free-response receiver operating curve and sensitivity were obtained.Results: In Mask R-CNN, matrix size 896 and 1344 achieved significantly higher FOM (0.869 and 0.856, respectively) for detecting abnormalities than 256, 448, and 1792 (0.667-0.820) (p < 0.05). In RetinaNet, matrix size 896 was significantly higher FOM (0.906) than others (0.329-0.832) (p < 0.05). For sensitivity of abnormalities, there was a tendency to increase sensitivity when lesion size increases. For small nodules (< 10 mm), the sensitivities were 0.418 and 0.409, whereas the sensitivities were 0.937 and 0.956 for masses. Matrix size 896 and 1344 in Mask R-CNN and matrix size 896 in RetinaNet showed significantly higher sensitivity than others (p < 0.05).Conclusions: Matrix size 896 had the highest performance for various sizes of abnormalities using different CNNs. The optimal matrix size of chest radiograph could improve CAD performance without additional training data.Key Points: • Input matrix size significantly affected the performance of a deep learning-based CAD for detection of nodules or masses on chest radiographs. • The matrix size 896 showed the best performance in two different CNN detection models. • The optimal matrix size of chest radiographs could enhance CAD performance without additional training data. [ABSTRACT FROM AUTHOR]

Background/aim: Sugammadex, which offsets the effects of neuromuscular blocking agents (NMBs), has advantages over traditional reversal agents like pyridostigmine, as it enables fast and reliable recovery from neuromuscular blockade. This study compared the incidence of early postoperative chest radiographic abnormalities (CRA) between sugammadex (group S) and pyridostigmine (group P) following video-assisted thoracoscopic (VAT) lobectomy for lung cancer. Materials and methods: We performed a retrospective cohort analysis by reviewing the medical records of patients who underwent VAT lobectomy at a single university medical center. We defined the early postoperative CRA as a characteristic appearance on chest radiograph up to 2 days after surgery. Arterial blood gas analysis (ABGA), surgical time, anaesthesia time, extubation time, and the total dose of rocuronium were analysed. Postoperative nausea and vomiting (PONV) and pain scores were observed until 2 days after surgery. Results: A total of 257 patients underwent VAT lobectomy during the study period; 159 were included in the final analysis. Ninety patients received sugammadex while 69 received pyridostigmine. The incidence of early postoperative atelectasis was significantly lower in group S than in group P (26.7%, 95% CI: 17.5%‒35.8% and 43.5%, 95% CI: 31.8%‒55.2%, respectively, P = 0.013). The median dose of rocuronium was higher in group S than in group P (120 mg vs. 90 mg, P < 0.001). ABGA, extubation time, and PONV were similar in both groups. Conclusion: Sugammadex decreased the incidence of CRA in the early postoperative period despite higher NMB consumption. [ABSTRACT FROM AUTHOR]

Objective: To enhance the positive predictive value (PPV) of chest digital tomosynthesis (DTS) in the lung cancer detection with the analysis of radiomics features.Method: The investigation was carried out within the SOS clinical trial (NCT03645018) for lung cancer screening with DTS. Lung nodules were identified by visual analysis and then classified using the diameter and the radiological aspect of the nodule following lung-RADS. Haralick texture features were extracted from the segmented nodules. Both semantic variables and radiomics features were used to build a predictive model using logistic regression on a subset of variables selected with backward feature selection and using two machine learning: a Random Forest and a neural network with the whole subset of variables. The methods were applied to a train set and validated on a test set where diagnostic accuracy metrics were calculated.Results: Binary visual analysis had a good sensitivity (0.95) but a low PPV (0.14). Lung-RADS classification increased the PPV (0.19) but with an unacceptable low sensitivity (0.65). Logistic regression showed a mildly increased PPV (0.29) but a lower sensitivity (0.20). Random Forest demonstrated a moderate PPV (0.40) but with a low sensitivity (0.30). Neural network demonstrated to be the best predictor with a high PPV (0.95) and a high sensitivity (0.90).Conclusions: The neural network demonstrated the best PPV. The use of visual analysis along with neural network could help radiologists to reduce the number of false positive in DTS.Key Points: • We investigated several approaches to enhance the positive predictive value of chest digital tomosynthesis in the lung cancer detection. • Neural network demonstrated to be the best predictor with a nearly perfect PPV. • Neural network could help radiologists to reduce the number of false positive in DTS. [ABSTRACT FROM AUTHOR]

Objectives: Pneumothorax is the most common and potentially life-threatening complication arising from percutaneous lung biopsy. We evaluated the performance of a deep learning algorithm for detection of post-biopsy pneumothorax in chest radiographs (CRs), in consecutive cohorts reflecting actual clinical situation.Methods: We retrospectively included post-biopsy CRs of 1757 consecutive patients (1055 men, 702 women; mean age of 65.1 years) undergoing percutaneous lung biopsies from three institutions. A commercially available deep learning algorithm analyzed each CR to identify pneumothorax. We compared the performance of the algorithm with that of radiology reports made in the actual clinical practice. We also conducted a reader study, in which the performance of the algorithm was compared with those of four radiologists. Performances of the algorithm and radiologists were evaluated by area under receiver operating characteristic curves (AUROCs), sensitivity, and specificity, with reference standards defined by thoracic radiologists.Results: Pneumothorax occurred in 17.5% (308/1757) of cases, out of which 16.6% (51/308) required catheter drainage. The AUROC, sensitivity, and specificity of the algorithm were 0.937, 70.5%, and 97.7%, respectively, for identification of pneumothorax. The algorithm exhibited higher sensitivity (70.2% vs. 55.5%, p < 0.001) and lower specificity (97.7% vs. 99.8%, p < 0.001), compared with those of radiology reports. In the reader study, the algorithm exhibited lower sensitivity (77.3% vs. 81.8-97.7%) and higher specificity (97.6% vs. 81.7-96.0%) than the radiologists.Conclusion: The deep learning algorithm appropriately identified pneumothorax in post-biopsy CRs in consecutive diagnostic cohorts. It may assist in accurate and timely diagnosis of post-biopsy pneumothorax in clinical practice.Key Points: • A deep learning algorithm can identify chest radiographs with post-biopsy pneumothorax in multicenter consecutive cohorts reflecting actual clinical situation. • The deep learning algorithm has a potential role as a surveillance tool for accurate and timely diagnosis of post-biopsy pneumothorax. [ABSTRACT FROM AUTHOR]