Normal Chest X-ray Research Articles

Ventilation-perfusion scan for diagnosing pulmonary embolism: do chest x-rays matter?

Ventilation-perfusion (V/Q) scan coupled with single photon emission computed tomography (SPECT) is commonly used for the diagnosis of pulmonary embolism (PE). An abnormal chest x-ray (CXR) is deemed to hinder the interpretation of V/Q scan and therefore a normal CXR is recommended prior to V/Q scan. To determine if an abnormal CXR impacted on V/Q scan interpretation and subsequent management. A retrospective cohort analysis of all patients who underwent a V/Q scan for diagnosis of suspected acute PE between March 2016 and 2022 was performed. CXR reports were reviewed and classified as normal or abnormal. Low-dose computerised tomography was routinely performed in patients above the age of 70. Data regarding V/Q scan results and subsequent management including initiation of anticoagulation for PE or further diagnostic investigations were collected. A total of 340 cases were evaluated. Of the positive V/Q scans (92/340), 98.3% of the normal CXR were anticoagulated compared to 100% of the abnormal CXR group. Of the negative V/Q scans (239/340), no cases were started on anticoagulation and no further investigations were performed across both normal and abnormal CXR groups. Indeterminate results occurred in only 9 cases with no significant difference in management between normal and abnormal CXR groups. An abnormal CXR does not affect the reliability of V/Q scan interpretation in the diagnosis of PE when coupled with SPECT. Unless clinically indicated, the mandate by clinical society guidelines for a normal CXR prior to V/Q should be revisited.

Tuberculosis treatment during the COVID-19 pandemic: actions offered and case profile.

To analyze the association between the provision of tuberculosis treatment actions and the sociodemographic and clinical characteristics of cases during the COVID-19 pandemic. Cross-sectional study conducted with data from secondary sources of 134 tuberculosis cases that underwent treatment in 2020 in the city of Pelotas, RS, Brazil. Data were analyzed using descriptive statistics, Chi-square test, and Fisher's exact test. The least frequently offered actions in the period were: three or more control smear microscopies (12.7%), smear microscopy at the end of treatment (16.7%), chest X-ray at sixth month (48.5%) and sputum culture (49%). The number of medical and nursing consultations did not reach six in 52.9% and 83.3% of cases, respectively. The lower offer of treatment actions was associated with: retreatment (p<0.001); comorbidities (p=0.023); HIV infection (p<0.001); mental disorder (p=0.013); illicit substance use (p=0.018); normal chest X-ray (p=0.024); and special treatment regimen (p=0.009). After the COVID-19 pandemic, it is essential to invest in cases follow-up, especially those undergoing retreatment, with comorbidities, drug use, normal chest X-ray results, and special treatment regimens.

Introducing SPINE: A Holistic Approach to Synthetic Pulmonary Imaging Evaluation Through End-to-End Data and Model Management.

In the evolving field of medical imaging and machine learning (ML), this paper introduces a novel framework for evaluating synthetic pulmonary imaging aiming to assess synthetic data quality and applicability. Our study concentrates on synthetic X-ray chest images, crucial for diagnosing respiratory diseases. We employ SPINE (Synthetic Pulmonary Imaging Evaluation) framework, a threefold synthetic images evaluation method including expert domain assessment, statistical data analysis and adversarial evaluation. In order to replicate and validate our methodology, we followed an End-to-End data and model management process which begins with a dataset of Normal and Pneumonia chest X-rays, generating synthetic images using Generative Adversarial Networks (GANs) and training a baseline classifier, essential in the adversarial evaluation axis, testing synthetic images against real data assessing their predictive value. The critical outcome of our approach is the post-market analysis of synthetic images. This innovative method evaluates synthetic images using clinical, statistical, and scientific criteria independently from traditional generation performance metrics. This independent evaluation provides deep insights into the clinical and research effectiveness of the synthetic data. By ensuring these images mirror real data's statistical properties and maintain clinical accuracy, our framework establishes a new standard for the ethical and reliable use of synthetic data in medical imaging and research.

Accuracy of an artificial intelligence-enabled diagnostic assistance device in recognizing normal chest radiographs: a service evaluation.

Artificial intelligence (AI) enabled devices may be able to optimize radiologists' productivity by identifying normal and abnormal chest X-rays (CXRs) for triaging. In this service evaluation, we investigated the accuracy of one such AI device (qXR). A randomly sampled subset of general practice and outpatient-referred frontal CXRs from a National Health Service Trust was collected retrospectively from examinations conducted during November 2022 to January 2023. Ground truth was established by consensus between 2 radiologists. The main objective was to estimate negative predictive value (NPV) of AI. A total of 522 CXRs (458 [87.74%] normal CXRs) from 522 patients (median age, 64 years [IQR, 49-77]; 305 [58.43%] female) were analysed. AI predicted 348 CXRs as normal, of which 346 were truly normal (NPV: 99.43% [95% CI, 97.94-99.93]). The sensitivity, specificity, positive predictive value, and area under the ROC curve of AI were found to be 96.88% (95% CI, 89.16-99.62), 75.55% (95% CI, 71.34-79.42), 35.63% (95% CI, 28.53-43.23), and 91.92% (95% CI, 89.38-94.45), respectively. A sensitivity analysis was conducted to estimate NPV by varying assumptions of the prevalence of normal CXRs. The NPV ranged from 88.96% to 99.54% as prevalence increased. The AI device recognized normal CXRs with high NPV and has the potential to increase radiologists' productivity. There is a need for more evidence on the utility of AI-enabled devices in identifying normal CXRs. This work adds to such limited evidence and enables researchers to plan studies to further evaluate the impact of such devices.

Simple Signs for Complex Problem

Objectives: To find simple clinical signs for diagnosing pulmonary embolism on bedside.&#x0D; Methodology: This was a hospital based cross sectional observational study conducted in cardiology department Saidu teaching hospital from July 2019 to December 2020. 89 patients of either sex and all age groups with suspected pulmonary embolism (PE) were included. Clinical data and basic tests of all these patients were obtained, then according to ESC diagnostic algorithm patients were divided into low, intermediate and high probability groups. 74 patients with intermediate and high probability went for CTPA, while 15 patients with low probability were exclude from study. In 67 patients pulmonary embolism was confirmed on CTPA. Clinical data of these 67 patients was analyzed for most common presenting symptoms and signs.&#x0D; Results: Data was available on 67 patients with confirmed PE, 58.2% were male and 41.8% were female. Mean age of study population was 53.15+/-16.29. Patients from different parts of Malakand division were included. 95.5 % patient presented with new onset dyspnea, 1.5 % presented with isolated chest pain, while 3% presented with other symptoms. 62.7 % patient had provoked and 37.3% had unprovoked PE. Mean heart rate of study population was 99.63. 95% patients had oxygen saturation of less than 96%. Other common findings included normal chest examination, sinus tachycardia on ECG, normal chest X-ray, and some form of right ventricular abnormality on Echo.&#x0D; Conclusion: Patient with new onset Dyspnea, resting Tachycardia, oxygen saturation below 95% at rest or mild exertion, and no other explanation for these findings should be evaluated for pulmonary embolism with CTPA.

Using Artificial Intelligence to Stratify Normal versus Abnormal Chest X-rays: External Validation of a Deep Learning Algorithm at East Kent Hospitals University NHS Foundation Trust.

Background: The chest radiograph (CXR) is the most frequently performed radiological examination worldwide. The increasing volume of CXRs performed in hospitals causes reporting backlogs and increased waiting times for patients, potentially compromising timely clinical intervention and patient safety. Implementing computer-aided detection (CAD) artificial intelligence (AI) algorithms capable of accurate and rapid CXR reporting could help address such limitations. A novel use for AI reporting is the classification of CXRs as 'abnormal' or 'normal'. This classification could help optimize resource allocation and aid radiologists in managing their time efficiently. Methods: qXR is a CE-marked computer-aided detection (CAD) software trained on over 4.4 million CXRs. In this retrospective cross-sectional pre-deployment study, we evaluated the performance of qXR in stratifying normal and abnormal CXRs. We analyzed 1040 CXRs from various referral sources, including general practices (GP), Accident and Emergency (A&E) departments, and inpatient (IP) and outpatient (OP) settings at East Kent Hospitals University NHS Foundation Trust. The ground truth for the CXRs was established by assessing the agreement between two senior radiologists. Results: The CAD software had a sensitivity of 99.7% and a specificity of 67.4%. The sub-group analysis showed no statistically significant difference in performance across healthcare settings, age, gender, and X-ray manufacturer. Conclusions: The study showed that qXR can accurately stratify CXRs as normal versus abnormal, potentially reducing reporting backlogs and resulting in early patient intervention, which may result in better patient outcomes.

Abstract 14180: A Case of Symptomatic Thoracic Aortic Aneurysm After Recent Fluoroquinolone Use

Background: Thoracic aortic aneurysms (TAAs) can be found in 1-2/1000 individuals in the general population and are commonly associated with genetic disorders of connective tissue and bicuspid aortic valve (BAV). Larger size, distal aneurysms, high DBP and presence of BAV are some factors that can accelerate aneurysm growth. Case: A 37-year-old male without a history of recent trauma or stimulant use presented to the emergency room with 2 days of chest tightness. He had acute worsening overnight and awoke with chest pain, discomfort in the suprasternal notch and between the shoulder blades. He had no other medical history, however, was treated with a 10-day course of Ciprofloxacin for epididymitis 3 weeks prior. On presentation, the patient had active pleuritic chest pain, tachycardia and tachypnea with no abnormalities on cardiac auscultation. EKG showed sinus tachycardia, PVCs, and nonspecific ST elevations in leads II, III and aVF with normal troponins and chest X-ray. CT chest angiogram revealed a 60 mm ascending aortic aneurysm ( Fig. 1a ). Doming of the right cusp of the aortic valve in the parasternal view ( Fig. 1b ) raised suspicion for BAV which was confirmed with the classic fish mouth appearance on the TEE ( Fig. 1c ). The patient underwent successful aortic repair with graft placement. First degree relatives were offered screening for BAV. Ciprofloxacin was replaced with Sulfamethoxazole-Trimethoprim for treating his residual epididymal infection. Discussion: TAA rupture is associated with a &gt;90% mortality rate. It is important to be aware of echocardiographic features of BAV as this can predispose to accelerated aneurysm growth. Additionally, fluoroquinolones (FQs) are a commonly prescribed class of antibiotics that may affect the structural integrity of the aorta, associated with aneurysm enlargement and rupture. This case offers an important example to highlight why the FDA recommends against the use of FQs in patients with known TAA or risk factors for it.

Abstract 16513: Decreased Pulmonary Blood Flow and Airway Volumes in Patients With Long COVID Syndrome Assessed by Functional Respiratory Imaging

Introduction: In contrast to normal chest X-ray, lung computed tomography (CT), and physiological lung and cardiac functions, many patients with long COVID syndrome suffer from shortness of breath. Hypothesis: The aim of this study was to quantify the pulmonary blood and airway volumes of long COVID patients compared with that of healthy controls. Methods: Patients with long COVID syndromes were included if they had PCR-verified previous (≥3 months) SARS-CoV-2 infection, had normal laboratory (e.g. inflammation, coagulation, cardiac or other organ) parameter, normal pulmonary morphology (chest X-ray and CT) and function (spirometry and body plethysmography). The lung CT images were postprocessed by Functional Respiratory imaging analysis by using 3D reconstruction with automated lung vessel segmentation algorithm. Data of the quantitative images were compared with age, gender, and BMI-matched healthy controls. Results: Thirty patients (45±13 years, 37% male, 25.9±4.3 kg/m^2) at a median time of 256 (118-574) days after a confirmed COVID infection and 30 healthy controls (55±7y, 37% male, 26.3±2.7 kg/m^2) were included. All long COVID patients complained of dyspnoea and 14 (48.3%) patients reported thoracic pain. The total pulmonary blood volume was significantly lower in the long COVID patients compared to controls (190±24.3 mL/m^2 vs230.6±26.2 ml/m^2, p&lt;0.001). Similarly, the capillary-small vessel blood flow (vessel cross sectional area &lt;5 mm^2) was reduced in the long COVID population (118±19 mL vs 132±23 mL, p=0.011). (Figure). The specific image-based airway volume of the distal lung regions was lower than that of the healthy population (11.1±6.74 mL vs 17.33±7.7 mL, p&lt;0.05). Conclusions: Both the reduced global and capillary pulmonary blood flow, and distal airway volumes indicate impaired gas exchange and might explain the pulmonary complaints of patient with long COVID syndromes even severe months after Coronavirus infection.

Automatic detection of coronavirus disease (COVID-19) in X-ray images using transfer learning

In late 2019, coronavirus disease (COVID-19) began to spread globally and is highly contagious. Due to its exceptionally rapid spread and high mortality rate, it is not yet possible to be eradicated. In order to halt the spread of COVID-19, there is a pressing need for effective screening of infected patients and immediate medical intervention. The absence of rapid and accurate methods to identify infected patients has led to a need for a model for early diagnosis of patients with and suspected of having COVID-19 to reduce the probability of missed diagnosis and misdiagnosis. Modern automatic image recognition techniques are an important diagnostic method for COVID-19. The aim of this thesis is to propose a novel deep learning technique for the automatic diagnosis and recognition of coronavirus disease (COVID-19) on X-ray images using a transfer learning approach. A new dataset containing COVID-19 information was created by merging two publicly available datasets. This dataset includes 912 COVID-19 images, 4273 pneumonia images, and 1583 normal chest X-ray images. We used this dataset to train and test the deep learning algorithm. With this new dataset, two pre-trained models (Xception and ResNetRS50) were trained and validated using transfer learning techniques. 3-class images were identified (Pneumonia vs. COVID-19 vs. Normal), and the two models generated validation accuracies of 90% and 97.21%, respectively, in the experiments. This demonstrates that our proposed algorithm can be well applied in diagnosing patients with lung diseases. In this study, we found the ResNetRS50 model to be superior.

The human role to guarantee an ethical AI in healthcare: a five-facts approach

AbstractWith the emergence of AI systems to assist clinical decision-making, several ethical dilemmas are brought to the general attention. AI systems are claimed to be the solution for many high-skilled medical tasks where machines can potentially surpass human ability as for example in identifying normal and abnormal chest X-rays. However, there are also warns that AI tools could be the basis for a human replacement that can risk dehumanisation in medicine. In recent years, important proposals in the domain of AI ethics in healthcare have identified main ethical issues, as for example fairness, autonomy, transparency, and responsibility. The human warranty, which implies human evaluation of the AI procedures, has been described to lower the ethical risks. However, as relevant these works have been, translating principles into action has proved challenging as existing codes were mostly a description of principles. There is a great need to produce how-to proposals that are specific enough to be action-guiding. We present five human-focussed facts designed into a framework of human action for an ethical AI in healthcare. Through the factors, we examine the role of medical practitioners, patients, and developers in designing, implementing, and using AI in a responsible manner that preserves human dignity. The facts encompass a range of ethical concerns that were commonly found in relevant literature. Given that it is crucial to bring as many perspectives as possible to the field, this work contributes to translate principles into human action to guarantee an ethical AI in health.

Foreign body aspiration in children at University of Gondar Comprehensive Specialized Hospital, a two year retrospective study

IntroductionForeign body aspiration (FBA) is defined as asphyxia, suffocation, or inhalation of items of food, such as bone and seed, and non-food, such as toys, into the respiratory tract. Aspiration of foreign bodies is an important and preventable cause of mortality and morbidity in children, especially those less than 3 years of age. The aim of this study was to analyse the clinical and radiological profile, modes of management, and outcomes of foreign body aspiration in children at the University of Gondar Comprehensive Specialized Hospital and identify areas of possible interventions for proper management of such cases. MethodA retrospective review of the medical records of all patients suspected of foreign body aspiration at the University of Gondar Comprehensive Specialized Hospital (UoGCSH) from January 1, 2021, to January 1, 2023, G.C. was conducted. Clinico-radiological features, types and locations of foreign bodies, modes of management, and patient outcomes were studied. ResultsA total of 73 patients suspected of having a possible foreign body aspiration were identified. The median age of the patients was 24 months, with an IQR of 14 and 39, with 46 (75.3 %) being under 3 years of age. 45 (61.6 %) were male, while 28 (38.4 %) were female, making the M:F ratio 1.6:1. A foreign body aspiration history could be obtained in 68 (93.1 %) of the patients, while in 4 (5.9 %) of the cases, patients or their families were not aware of any kind of aspiration. Among the children presented, 65 (89 %) had a choking episode, coughing 66 (91 %), vomiting 63 (86.3 %), tachypnea 61 (83.6 %), and stridor 15 (20.5 %). The most common physical finding observed was nasal flaring along with subcostal and intercostal retraction in 59 (80.8 %), followed by decreased air entry in 40 (54.8 %), wheeze in 37 (50.7 %), and absent air entry in the affected side in 4 (5.5 %) of the patients. A chest x-ray was done on all patients. 28 (41.2 %) had normal chest x-rays. With regard to procedure-related complications, 3 (4.1 %) patients had cardiac arrest, 1 (1.36 %) had pneumothorax, and 1 patient died. ConclusionAny bronchopulmonary infection with an unusual course should be suspected of being the result of the aspiration of a foreign body. Increased public and professional awareness of the importance of early bronchoscopy in all suspected cases of foreign body aspiration is necessary. In order to lower the incidence, those providing care must be taught routine preventive measures.

Serum interleukin-6 level and its association with pulmonary involvement in progressive systemic sclerosis; a case-control study

BackgroundPrimary Systemic Sclerosis (PSS) is a connective tissue disorder characterized by excessive collagen deposition in the skin and internal organs. Interstitial lung disease (ILD) is a late demonstration of PSS and cytokines can contribute to the disease pathology. The purpose of the current study was to determine the association between serum interleukin-6 level and pulmonary involvement in progressive systemic sclerosis.Methods and materialsDemographic data and serum interleukin-6 levels were measured for 30 PSS patients with pulmonary involvement (case group) and 30 PSS patients without pulmonary involvement (control group) following informed consent. The disease duration and activity, C-reactive protein (CRP), chest x-ray and highresolution CT scan (HRCT) findings, ejection fraction (EF) and echocardiography findings, and pulmonary artery pressure (PAP) were also determined in both groups.ResultsThe age of patients in case and control groups was 52.5 ± 9.3 and 43.9 ± 9.7 years, respectively (p = 0.001). No significant difference was found between serum levels of IL-6 in case and control groups (73.1 ± 95.4 vs 46.7 ± 83.6 pg/ml, p = 0.267). However, IL-6 level was significantly higher in male case patients compared to male controls (p = 0.007). The duration of PSS was 11.6 ± 6.4 and 7.4 ± 4.2 years in case and control groups, respectively (p = 0.002). The quantitative CRP and PAP was also significantly higher in case patients (p = 0.01 and p < 0.001, respectively). There was found reticulonodular pattern in 20 (66.7%) of the cases, whereas 28 (93.3%) of the controls had normal Chest X-rays (CXR) (p < 0.001). EF was significantly lower in case patients compared to control patients (p = 0.001).ConclusionThe serum level of IL-6 did not appear to have a relationship with pulmonary involvement, hence it could not be regarded as a potential therapeutic target.

Low CRB-65 Scores Effectively Rule out Adverse Clinical Outcomes in COVID-19 Irrespective of Chest Radiographic Abnormalities.

Background: CRB-65 (Confusion; Respiratory rate ≥ 30/min; Blood pressure ≤ 90/60 mmHg; age ≥ 65 years) is a risk score for prognosticating patients with COVID-19 pneumonia. However, a significant proportion of COVID-19 patients have normal chest X-rays (CXRs). The influence of CXR abnormalities on the prognostic value of CRB-65 is unknown, limiting its wider applicability. Methods: We assessed the influence of CXR abnormalities on the prognostic value of CRB-65 in COVID-19. Results: In 589 study patients (71 years (IQR: 57-83); 57% males), 186 (32%) had normal CXRs. On ROC analysis, CRB-65 performed similarly in patients with normal vs. abnormal CXRs for predicting inpatient mortality (AUC 0.67 ± 0.05 vs. 0.69 ± 0.03). In patients with normal CXRs, a CRB-65 of 0 ruled out mortality, NIV requirement and critical illness (intubation and/or ICU admission) with negative predictive values (NPVs) of 94%, 98% and 99%, respectively. In patients with abnormal CXRs, a CRB-65 of 0 ruled out the same endpoints with NPVs of 91%, 83% and 86%, respectively. Patients with low CRB-65 scores had better inpatient survival than patients with high CRB-65 scores, irrespective of CXR abnormalities (all p < 0.05). Conclusions: CRB-65, CXR and CRP are independent predictors of mortality in COVID-19. Adding CXR findings (dichotomised to either normal or abnormal) to CRB-65 does not improve its prognostic accuracy. A low CRB-65 score of 0 may be a good rule-out test for adverse clinical outcomes in COVID-19 patients with normal or abnormal CXRs, which deserves prospective validation.

997 Traumatic Jejunal Rupture Following Gaelic Football Game. Case Report

Abstract Aim Abdominal injury accounts for just 6.3% of injuries in sport. The most common mechanisms are contacts with a player (74.5%), a surface (8.1%) or equipment (0.6%). Only twelve cases of Jejunal rupture are described in the literature. Method This case involves a young Gaelic football player who had significant abdominal contact with other players’ knees. He experienced nausea and left flank pain radiating to the groin. At the Emergency Department the heart rate was 95 beats per minute and blood pressure was 120/70 mmHg. There was bruising in the left flank at the impact site and some guarding. Initial investigations showed normal inflammatory markers and a normal Chest X-ray. Nine hours later the white cell count had increased to 17.85x10^9 and CRP to 106mg/L. Abdominal and Pelvic CT scanning suggested a bowel injury with free fluid in the left flank and pelvis. Management Exploratory laparotomy identified a jejunal rupture 10cm distal to the duodenal-jejunal flexure. A primary two-layer repair was performed. Antibiotic and anti-fungal cover were prescribed, and he was discharged well on day 5. Conclusions Owing to the rarity of bowel injury after blunt trauma, soft peritoneal signs and radiological insensitivity, the diagnosis of small bowel perforation is often delayed and can be associated with marked morbidity and mortality. Serial examinations and a high index of suspicion is required to detect bowel injuries in the case of blunt abdominal trauma in contact sports.

Association of lung function by spirometry with serum ferritin in transfusion-dependent thalassemia patients in a tertiary care centre

Background: β-thalassemia major is an inherited, transfusion-dependent chronic anemia which is caused by decreased production of β-globin chains required for formation of hemoglobin. Regular blood transfusion is most important factors that help in improving the survival of patients with TM; however, it leads to iron deposition in many organs such as lung. Most studied concerned about effect of iron on lung functions, revealed abnormalities, but limited data were observed. The aim of our study was to determine pulmonary function abnormalities in children with thalassemia major and assess the relation between these abnormalities and iron overload. Methods: This study had included 51 children in each group, aged between 6 and 18 years (28 males and 23 females) with TM. All included children were subjected to full clinical examination and laboratory investigations including complete blood counts and serum ferritin. Pulmonary function tests (PFTs) were assessed in all included children using spirometry. Results: 31.4% patients had restrictive lung functions. Spirometer parameters i.e., FEF25-75% (p value≤0.0001) and PEFR (%pred) (p value≤0.0001) had significant difference in both groups. FEF25-75% and PEFR had no effect of serum ferritin. Conclusions: The lung may be considered a site for organ damage, and alteration of pulmonary function may be expected in transfusion-dependent patients in spite of no pulmonary symptoms or normal chest X-ray.

Early Trends to Show the Efficacy of Cordyceps militaris in Mild to Moderate COVID Inflammation.

Background/objective Cordyceps enhances animal survival against influenza by boosting the immune system. In animal studies, it also had anti-inflammatory and preventive properties. Cordyceps stimulates the immune system by increasing the activity and production of various immune cells. Some studies have shown the role of Cordyceps in the novel SARS-CoV-2 virus responsible for the COVID-19 pandemic, in addition to other respiratory diseases caused by the Picorna viruses, SARS-CoV, MERS-CoV, and Influenza viruses. However, it remains unknown whether this food supplement is safe and has anti-inflammatory effects in patients with COVID-19. Therefore, the objectives of this study were to evaluate the use and efficacy of Cordyceps capsules as an adjunct to standard treatment in patients with mild (symptomatic) to moderate COVID-19 infection. Methods A randomised, double-blind, placebo-controlled study was conducted to evaluate the efficacy and safety of Cordyceps capsules (a food supplement) 500 mg as adjuvant therapy in patients with COVID-19. The rationale for dose selection was as per the existing evidence from toxicity studies. The inclusion criteria were patients with either a mild or moderate COVID-19 infection. Clinical features suggestive of dyspnoea or hypoxia, fever, and cough, including SpO2 <94% (range 90-94%) on room air and a respiratory rate ≥24 per minute, were also included. Results Sixty-five patients were recruited for the study, with 33 in the Cordyceps group and 32 in the placebo group. Out of 58 evaluable patients, 33 recovered on day 5, 49 on day 10, and 58 on days 16 and 30. The recovery of patients steadily increased from 56.9% on day 5 to 100% on day 30. The time to clinical recovery was shorter in the Cordyceps group than in the placebo group (mean 6.6 vs. 7.3 days; p > 0.05) overall and for mild disease. However, there was no difference in the time to recovery (time from day 1 to the resolution of all symptoms) for moderate disease. A lower frequency of normal chest X-rays on day 1 and a higher number on day 16 in the treatment group than in the placebo group suggest an improvement in the number of normal chest X-rays with Cordyceps. Significant changes were seen in biomarkers MCPIP, CxCL10, and IL-1β for overall (both mild and moderate patients) on days 5 and 10 as compared to baseline, and in biomarkers CRP and CxCL10 in moderate category patients on days 5 and 10, respectively. There were no statistically significant changes in IL-6, ferritin, lactate dehydrogenase (LDH), C-reactive protein (CRP), or D-dimer levels between baseline and day 5/10 in patients taking Cordyceps capsules and also between the treatment and placebo groups. Conclusion Cordyceps capsules administered at a dose of 500 mg three times a day along with supportive treatment showed effectiveness in patients with mild to moderate COVID-19 infection, as evidenced by the proportionately higher number of recoveries on day 5, the relatively shorter time for improvement of clinical symptoms, and the proportionately higher number of patients showing negative RT-PCR tests on day 10. Thus, Cordyceps appears to be a safe immunological adjuvant for the treatment of patients with mild-to-moderate COVID-19. Future studies with a larger sample size would shed more light on the evidence, as there are limitations in the generalizability of the results from the present study due to the small sample size.

Introducing a secondary segmentation to construct a radiomics model for pulmonary tuberculosis cavities

PurposeAccurate segmentation (separating diseased portions of the lung from normal appearing lung) is a challenge in radiomic studies of non-neoplastic diseases, such as pulmonary tuberculosis (PTB). In this study, we developed a segmentation method, applicable to chest X-rays (CXR), that can eliminate the need for precise disease delineation, and that is effective for constructing radiomic models for automatic PTB cavity classification.MethodsThis retrospective study used a dataset of 266 posteroanterior CXR of patients diagnosed with laboratory confirmed PTB. The lungs were segmented using a U-net-based in-house automatic segmentation model. A secondary segmentation was developed using a sliding window, superimposed on the primary lung segmentation. Pyradiomics was used for feature extraction from every window which increased the dimensionality of the data, but this allowed us to accurately capture the spread of the features across the lung. Two separate measures (standard-deviation and variance) were used to consolidate the features. Pearson’s correlation analysis (with a 0.8 cut-off value) was then applied for dimensionality reduction followed by the construction of Random Forest radiomic models.ResultsTwo almost identical radiomic signatures consisting of 10 texture features each (9 were the same plus 1 other feature) were identified using the two separate consolidation measures. Two well performing random forest models were constructed from these signatures. The standard-deviation model (AUC = 0.9444 (95% CI, 0.8762; 0.9814)) performed marginally better than the variance model (AUC = 0.9288 (95% CI, 0.9046; 0.9843)).ConclusionThe introduction of the secondary sliding window segmentation on CXR could eliminate the need for disease delineation in pulmonary radiomic studies, and it could improve the accuracy of CXR reporting currently regaining prominence as a high-volume screening tool as the developed radiomic models correctly classify cavities from normal CXR.

Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: Analysis of an international, multicenter migrants screening study.

The aim of this study was to independently evaluate the diagnostic accuracy of three artificial intelligence (AI)-based computer aided detection (CAD) systems for detecting pulmonary tuberculosis (TB) on global migrants screening chest x-ray (CXR) cases when compared against both microbiological and radiological reference standards (MRS and RadRS, respectively). Retrospective clinical data and CXR images were collected from the International Organization for Migration (IOM) pre-migration health assessment TB screening global database for US-bound migrants. A total of 2,812 participants were included in the dataset used for analysis against RadRS, of which 1,769 (62.9%) had accompanying microbiological test results and were included against MRS. All CXRs were interpreted by three CAD systems (CAD4TB v6, Lunit INSIGHT v4.9.0, and qXR v2) in offline setting, and re-interpreted by two expert radiologists in a blinded fashion. The performance was evaluated using receiver operating characteristics curve (ROC), estimates of sensitivity and specificity at different CAD thresholds against both microbiological and radiological reference standards (MRS and RadRS, respectively), and was compared with that of the expert radiologists. The area under the curve against MRS was highest for Lunit (0.85; 95% CI 0.83-0.87), followed by qXR (0.75; 95% CI 0.72-0.77) and then CAD4TB (0.71; 95% CI 0.68-0.73). At a set specificity of 70%, Lunit had the highest sensitivity (81.4%; 95% CI 77.9-84.6); at a set sensitivity of 90%, specificity was also highest for Lunit (54.5%; 95% CI 51.7-57.3). The CAD systems performed comparable to the sensitivity (98.3%), and except CAD4TB, to specificity (13.7%) of the expert radiologists. Similar trends were observed when using RadRS. Area under the curve against RadRS was highest for CAD4TB (0.87; 95% CI 0.86-0.89) and Lunit (0.87; 95% CI 0.85-0.88) followed by qXR (0.81; 95% CI 0.80-0.83). At a set specificity of 70%, CAD4TB had highest sensitivity (84.1%; 95% CI 82.3-85.8) followed by Lunit (80.9%; 95% CI 78.9-82.7); and at a set sensitivity of 90%, specificity was also highest for CAD4TB (54.6%; 95% CI 51.3-57.8). In conclusion, the study demonstrated that the three CAD systems had broadly similar diagnostic accuracy with regard to TB screening and comparable accuracy to an expert radiologist against MRS. Compared with different reference standards, Lunit performed better than both qXR and CAD4TB against MRS, and CAD4TB and Lunit better than qXR against RadRS. Moreover, the performance of the CADs can be impacted by characteristics of subgroup of population. The main limitation was that our study relied on retrospective data and MRS was not routinely done in individuals with a low suspicion of TB and a normal CXR. Our findings suggest that CAD systems could be a useful tool for TB screening programs in remote, high TB prevalent places where access to expert radiologists may be limited. However, further large-scale prospective studies are needed to address outstanding questions around the operational performance and technical requirements of the CAD systems.

Predictive power of chest radiography for infectious or inflammatory lung disease.

Children frequently present with chronic cough, recurrent respiratory infections, and dysphagia. These symptoms are poor predictors of significant inflammatory lung disease, such as from chronic aspiration. Bronchoalveolar lavage (BAL) is the gold standard for identification of lung infection and airway inflammation but is expensive and requires sedation. Chest X-rays (CXR) are inexpensive, low-radiation tests that do not require sedations and can document findings associated with infectious or inflammatory lung disease. The accuracy of CXR to predict or exclude infectious or inflammatory lung disease has not been directly evaluated and is unknown. Retrospective cohort of all pediatric patients who underwent FFB with BAL within 2weeks of a CXR. Blinded CXR images reviewed for findings consistent with inflammatory disease by two senior pediatric radiologists. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for CXR to identify significant inflammation and/or infection on BAL were calculated. Three hundred and forty-four subjects included. Two hundred and sixty-three had positive CXR (77%), 183 had inflammatory BAL (53%), and 110 had infection (32%). The sensitivity of CXR changes for BAL inflammation, infection, and either inflammation or infection was 84.7, 90.9, and 85.3, respectively. The PPV of CXR was 58.9, 38.0, and 59.7. The NPV of CXR was 65.0, 87.5, and 66.3. Although CXR are inexpensive, do not require sedation, and are of low radiation dose, the ability of an entirely normal CXR to exclude active inflammatory or infectious lung disease is limited.

The role of chest X-ray in coronavirus disease 2019 (COVID-19) infection: findings and correlation with clinical outcome.

It is possible to diagnose coronavirus disease 2019 (COVID-19) faster and more accurately with chest X-ray (CXR) and chest computed tomography (CT) than with reverse transcriptase PCR (RT-PCR) tests. The aim of this study was to verify the possibility of reducing the use of CT in diagnosis and follow-up of COVID-19 infection by using CXR. A total of 326 COVID-19 patients who were hospitalized in Ankara City Hospital were included in this retrospective study. A total of 326 patients were RT-PCR positive for COVID-19 infection; 178 were male (54.6%) and 148 were female (45.4%), with a median age of 45. Considering the results, the baseline CXR sensitivity in our experience was approximately 72%. The CXRs of 113 patients with abnormal CT were divided into 2 groups, the CXR normal and abnormal groups, and were then compared. In the 1st group with abnormal CXR, the mean age, the number of patients over 65 years old, and the comorbidity rate were higher. Additionally, it was determined that the number of patients requiring respiratory support and intensive care unit (ICU) admission in this 1st group was higher than in the 2nd group (with normal CXR). Most of the patients who died (91%, 10/11) were in Group 1. In the group with normal CXR, no patients in the critically ill category needed invasive or non-invasive mechanical ventilators. CXR can help in detecting clinically moderate and severe cases of COVID-19. CXR can assist clinicians in patient management and treatment planning regarding the clinical course, respiratory support, ICU need, and mortality and can help them prepare for potential negative outcomes.