Search

Case Presentation: An 8-month-old infant presented to a general emergency department with chief complaints of rhinorrhea, decreased activity, and fever. A point-of-care lung ultrasound (LUS) was performed at bedside with potential early findings of pneumonia. Based on these findings on LUS, a chest radiograph (CXR) was ordered and performed with no acute findings. He was discharged without antibiotics based on these findings; unfortunately, he returned two days later with worsening symptoms requiring chest tube placement, mechanical ventilation, and prolonged hospitalization for complicated bacterial pneumonia.Discussion: Pneumonia is a major cause of pediatric morbidity and mortality worldwide. Despite evidence supporting the utilization of LUS for the diagnosis of pediatric pneumonia, CXR remains the default imaging for clinical decision-making in most settings. In this case, earlier antibiotics and higher reliance on LUS for clinical decision-making may have prevented the morbidity associated with this hospitalization.

The Coronavirus (COVID-19) outbreak in December 2019 has drastically affected humans worldwide, creating a health crisis that has infected millions of lives and devastated the global economy. COVID-19 is ongoing, with the emergence of many new strains. Deep learning (DL) techniques have proven helpful in efficiently analysing and delineating infectious regions in radiological images. This survey paper draws a taxonomy of deep learning techniques for detecting COVID-19 infection in radiographic imaging modalities Chest X-Ray, and Computer Tomography. DL techniques are broadly categorised into classification, segmentation, and multi-stage approaches for COVID-19 diagnosis at the image and region-level analysis. These techniques are further classified as pre-trained and custom-made Convolutional Neural Network architectures. Furthermore, a discussion is drawn on radiographic datasets, evaluation metrics, and commercial platforms provided for detection. In the end, a brief look is paid to emerging ideas, gaps in existing research, and challenges in developing diagnostic techniques. This survey provides insight into the promising areas of research in DL and is likely to guide the research community on the upcoming development of deep learning techniques for COVID-19. This will pave the way to accelerate the research in designing customised DL-based diagnostic tools for effectively dealing with new variants of COVID-19 and emerging challenges. [ABSTRACT FROM AUTHOR]

Objectives: To determine the incidence of lung cancer amongst primary care referrals for investigation with a chest radiograph (CXR). Methods: Retrospective evaluation of datasets from the national Clinical Practice Research Datalink (CPRD) and from a single large regional centre. Data were extracted for cohorts of consecutive adults aged over 40 years for whom a CXR had been performed between 2016 and 2018. Using cancer registry data, the incidence of lung cancer within a 2 years of the CXR referral and the variations with age, gender, and smoking status were evaluated. Results: A total of 291 294 CXR events were evaluated from the combined datasets. The incidence of lung cancer amongst primary care CXR referrals was 1.4% in CPRD with a consistent correlation with increasing age and smoking status. The incidence of lung cancer within two-years of the CXR varied between 0.03% (95%CI, 0.0-0.1) amongst never smokers aged 40-45 years to 4.8% (95%CI, 4.2-5.5) amongst current-smokers aged 70-75 years. The findings were similar for the single large centre data, although cancer incidence was higher. Conclusions: A simple estimation and stratification of the risk of lung cancer amongst primary care referrals for investigation with a CXR is possible using age and smoking status. Advances in knowledge: This is the first estimate of the incidence of lung cancer amongst primary care CXR referrals and a demonstration of how the demographic information contained within a request could be used to optimize investigations and interpret test results. [ABSTRACT FROM AUTHOR]

Medical imaging is an indispensable and very important step in the diagnosis and treatment of illnesses. However, due to large amounts of resources necessary for training the model, training from scratch may not invariably emerge as the optimal recourse. Transfer learning has emerged as a viable solution, where pretrained weights from ImageNet are initially utilized and fine-tuninned afterwards. This paper presents a novel approach employing transfer learning to classify both respiratory diseases and radiological findings from chest X-rays. The dataset comprises 191 660 X-ray images gathered from public databases and 752 chest X-ray images obtained from a retrospective study at the University Clinical Center of Kragujevac, forming the foundation of Big data analysis. It includes various conditions such as atelectasis, cardiomegaly, infiltration, pleural thickening, non-viral pneumonia, pneumothorax, COVID-19 viral pneumonia, tuberculosis, etc. as well as masses and nodules indicative of tumors and images of healthy subjects. Although there are existing solutions with some diseases, this is the first paper that inlcludes differentiation between healthy and diseased cases, as well as in case of present disease, as much as 18 different classes are inlcuded in the analysis, which has not been done so far. The proposed methodology included transfer learning with DenseNet121 as the backbone and CheXNeXt weights as initialisation scheme, upon which additional layers were added for fine tuning. The results demonstrate the model's capacity to distinguish between healthy and diseased, with an average area under curve (AUC) of 0.99. The AUC ranges from 0.86 for nodules to 0.99 for pneumonia and 0.99 for COVID-19. Our method outperforms the state-of-the-art in accuracy across all 18 classes, with the exception of classes consolidation, mass, and nodule. These findings are promising for a tested clinical site, though further validation in clinical environment accros multiple sites may be necessary before using the model as a standalone decision system, rather than a decision support system for disease diagnosis based on chest X-rays. [ABSTRACT FROM AUTHOR]

Pneumonia, a prevalent respiratory disease, affects millions globally. Accurate diagnosis and early detection are essential for managing and treating pneumonia. In recent years, machine learning and visual analysis technologies have shown promise for detecting pneumonia from therapeutic imageries such as chest X-rays. The dataset is collected from a Kaggle and contains X-ray scans of lungs from people of all ages. This dataset includes 5,856 labelled images, of which 4,273 are positive for pneumonia and 1,583 are negative. The data set is preprocessed using data augmentation techniques such as rotation, shifting, shearing, flipping and fill mode. The preprocessed data is trained using a masked neural network (MNN). The essential features are extracted from the last layer of MNN, and then the K-nearest neighbor (KNN) classify the chest X-rays to detect Pneumonia. This study developed a mask generation technique, dropout regularisation, and classifiers to train a model with 98.07% accuracy and minimal losses. This approach could lead to faster and more accurate pneumonia diagnoses, ultimately improving patient outcomes. Our research shows that transfer learning of KNN with MNN can effectively analyse chest X-rays to detect pneumonia. [ABSTRACT FROM AUTHOR]

Heart disease has been the leading cause of mortality worldwide in the recent decade. Since 2019, new lung-related infections have increased heart attack mortality. To minimize mortality, a unified framework is needed to predict early diagnosis utilizing different patient data. Existing methods failed to produce automatic solutions on the unified approach to cardiac problems considering lung infections. A unique automated disease diagnosis and classification framework using patient chest X-ray images and Electrocardiogram (ECG) signal is proposed. This integrated framework is unique in diagnosing and monitoring lung disease and cardiac problems utilizing patient X-ray and ECG. The proposed system is called the Deep Intelligence Framework for Diseases Detection (DIFDD). DIFDD procedures include pre-processing, automated feature extraction, and classification. An effective pre-processing method is designed to improve X-ray and ECG data. The 2D and 1D Convolutional Neural Network (CNN) techniques are proposed to extract automated features from pre-processed X-ray and ECG data. According to feature learning, automated detection uses several classifiers. Based on classifier results, a consolidated approach is presented for medical judgment on the patient's health for suitable treatment. The simulation results using the synthetic dataset revealed the efficiency of the proposed DIFDD model over the existing methods. The overall accuracy of the DIFDD model is improved by 1.5% and computational overhead is reduced by 13.56%. [ABSTRACT FROM AUTHOR]

Invasive pulmonary mucormycosis (IPM) is a deadly opportunistic mold infection in patients with hematological malignancies (HM). Radiologic imaging is essential for its timely diagnosis. Here, we compared IPM lesions visualized by chest computed tomography (CCT) and chest X-ray (CXR) and determined the prognostic significance of discordant imaging. Therefore, we reviewed 44 consecutive HM patients with probable/proven IPM at MD Anderson Cancer Center in 2000–2020 who had concurrent CCT and CXR studies performed. All 44 patients had abnormal CCTs and 39 (89%) had anormal CXR findings at IPM diagnosis. However, only 26 patients (59%) showed CCT-matching IPM-suspicious lesions on CXR. Acute Physiology and Chronic Health Evaluation II score > 18 at IPM diagnosis and breakthrough infection to Mucorales-active antifungals were the only independent risk factors for 42-day and/or 84-day mortality. Absence of neutropenia at IPM diagnosis, neutrophil recovery in neutropenic patients, and surgical revision of mucormycosis lesions were protective factors. Although not reaching significance on multivariable analysis, visualization of CCT-matching lesions on CXR was associated with significantly increased 84-day mortality (log-rank test, p = 0.033), possibly as a surrogate of extensive lesions and tissue necrosis. This observation supports the exploration of radiologic lesion kinetics as a prognostic staging tool in IPM patients. [ABSTRACT FROM AUTHOR]

Background: Tuberculosis (TB) persists as a global health challenge, with pulmonary tuberculosis (PTB) constituting over 85% of all cases. India, with its distinctive demographic challenges, bears a significant burden, especially impacting the economically vital age group of 15 to 60 years. Methods: Our prospective study, conducted at the National Institute of Medical Science & Research, Jaipur, Rajasthan, encompassed a comprehensive reassessment of PTB subjects. Clinical evaluations, laboratory investigations, and radiological assessments, including chest X-rays (CXR) and high-resolution computed tomography (HRCT), were employed. A sample size of 320 cases underwent meticulous statistical analysis, adhering to ethical considerations. Results: Analysis revealed no significant association between gender and PTB cases (χ² = 0.186, df = 1, p = 0.666) or between age, gender, and PTB diagnosis (χ² = 4.651, df = 3, p = 0.266). Radiological findings demonstrated noteworthy correlations, emphasizing their diagnostic significance. Chest X-ray findings associated significantly with patchy infiltrate, mediastinal lymphadenopathy, fibrosis, and pleural effusion (p < 0.05). Conclusion: Our study unravels the complex tapestry of PTB, highlighting its historical significance and contemporary challenges. The pivotal role of radiological precision in diagnosis is underscored, especially in India's high-burden context. The findings emphasize the need for nuanced approaches and ongoing research to enhance our understanding and management of TB. As we confront the radiological intricacies of PTB, this study contributes to the discourse aimed at fostering transformative change in TB care and control. [ABSTRACT FROM AUTHOR]

Xpert MTB/RIF is recommended for the diagnosis of tuberculosis (TB) in children. We determined the performance of Xpert MTB/RIF in the diagnosis of pulmonary TB in children. The characteristics of children influencing Xpert MTB/RIF positivity were explored. Children aged <15 years with symptoms suggestive of pulmonary TB were prospectively enrolled from 2013 to 2019. Two sputum/early morning gastric aspirate specimens were collected for examination by smear (fluorescence microscopy), Xpert MTB/RIF, and culture [Mycobacteria growth indicator tube (MGIT)/Lowenstein–Jensen (LJ) medium]. Diagnostic performance of Xpert MTB/RIF was evaluated using LJ and or MGIT culture positivity as the reference standard. Sensitivity, specificity with 95% confidence interval (CI) were calculated. Stratified analysis was done; P  < .05 was considered statistically significant. Of the total 1727 enrolled children, 1674 (97%) with complete results for at least one sputum/gastric aspirate sample were analyzed. The sensitivity of Xpert MTB/RIF was 68.5% in sputum and 53.6% in gastric aspirate while the specificity was 99% for both. The sensitivity compared to smear was 68.5% vs. 33.7% (P  < .001) and 53.6% vs. 14.5%; (P  < .001) in sputum and gastric aspirate, respectively. The sensitivity of Xpert MTB/RIF was 23.9% with decision to treat as reference standard. Xpert MTB/RIF positivity was significantly influenced by sex, age, nutritional status, chest X-ray abnormality, TB infection status, and symptoms suggestive of TB. Xpert MTB/RIF as an upfront test compared to smear improves diagnosis of pulmonary TB in children yet the sensitivity is suboptimal. Newer TB diagnostic tools with improved sensitivity is warranted in children. [ABSTRACT FROM AUTHOR]

Lung imaging techniques are crucial for managing ventilated patients in pediatric intensive care units (PICUs). Bedside chest x-ray has limitations such as low sensitivity and radiation exposure risks. Recently, lung ultrasound has emerged as a promising technology offering advantages such as real-time monitoring and radiation-free imaging. However, the integration of lung ultrasound into clinical practice raises questions about its impact on chest x-ray prescriptions. This study aims to assess whether implementing lung ultrasound reduces reliance on chest x-rays for ventilated pediatric patients in the PICU. This before-and-after uncontrolled quality improvement project was conducted from January 2022 to December 2023 in a referral PICU. The study included three phases: retrospective evaluation, learning phase, and prospective evaluation. Patients aged under 14 years, intubated, and ventilated for ≤ 30 days were included. Lung ultrasound was performed using a standardized protocol, and chest x-rays were conducted as per clinical indications. During the study period, 430 patients were admitted to the PICU, with 142 requiring mechanical ventilation. Implementation of routine bedside lung ultrasound led to a 39% reduction in chest x-ray requests (p < 0.001). Additionally, there was a significant decrease in irradiation exposure and a 27% reduction in costs associated with chest x-rays. Conclusion: Routine bedside lung ultrasound is a valuable tool in the modern PICU, it reduces the number of chest x-rays, with reduced radiation exposure and a potential cost savings. What is known: • Bedside chest x-ray is the main imaging study in ventilated pediatric patients • Chest x-ray is a valuable tool in pediatric critical care but it is associated with irradiation exposure What is new: • Implementation of bedside lung ultrasound in pediatric critical care unites reduces the chest x-rays requests and therefore patient-irradiation [ABSTRACT FROM AUTHOR]

Before requesting any test, clinicians must consider how likely it is to be able to answer the clinical question. Multiple radiological investigations are available to aid diagnosis, assist with practical procedures and direct management of critically ill patients. This article gives an overview of commonly used thoracic imaging modalities and summarizes their indications, important findings and potential pitfalls. [ABSTRACT FROM AUTHOR]

Acute respiratory failure (ARF) is a sudden failure of the respiratory system to ensure adequate gas exchanges. Numerous clinical conditions may cause ARF, including pneumonia, obstructive lung diseases (e.g., asthma), restrictive diseases such as neuromuscular diseases (e.g., spinal muscular atrophy and muscular dystrophy), and albeit rarely, interstitial lung diseases. Children, especially infants, may be more vulnerable to ARF than adults due to anatomical and physiological features of the respiratory system. Assessing respiratory impairment in the pediatric population is particularly challenging as children frequently present difficulties in reporting symptoms and due to compliance and cooperation in diagnostic tests. The evaluation of clinical and anamnestic aspects represents the cornerstone of ARF diagnosis: first level exams (e.g., arterial blood gas analysis) confirm and evaluate the severity of the ARF and second level exams help to uncover the underlying cause. Prompt management is critical, with supplemental oxygen, mechanical ventilation, and the treatment of the underlying problem. The aim of this review is to provide a comprehensive summary of the current state of the art in diagnosing pediatric ARF, with a focus on pathophysiology, novel imaging applications, and new perspectives, such as biomarkers and artificial intelligence. [ABSTRACT FROM AUTHOR]

Pneumonia is a condition characterised by the sudden inflammation of lung tissue, which is triggered by microorganisms such as fungi, viruses, and bacteria. Chest X-ray imaging (CXR) can detect pneumonia, but it requires considerable time and medical expertise. Consequently, the objective of this study is to diagnose pneumonia using CXR imaging in order to effectively detect early cases of pneumonitis in children. The study employs the ensemble transfer learning convolutional neural network (ETL-CNN) transfer learning ensemble, which combines multiple CNN transfer learning models. Resnet50-VGG19 and VGG19-Xception are the ETL-CNN models used in this investigation. Comparing ETL-CNN models to CNN transfer learning models such as Resnet50, VGG19, and Xception. Pediatric CXR pneumonia, which consists of a normal and pneumonia image, is the source of these study results. The results of this analysis indicate that Resnet50-VGG19 achieved the highest level of accuracy, 99.14%. Additionally, the Resnet50-VGG19 obtained the highest levels of precision and recall when comparing to other models. Consequently, the conclusion of this study is that the Resnet50-VGG19 model can generate acceptable classification performance for pediatric pneumonia based on CXR. This study improves classification results for performance when compared to earlier studies. [ABSTRACT FROM AUTHOR]

Lung and respiratory ailments are among the leading causes of illness and fatalities. Coronavirus disease (COVID-19), caused by the SARS-CoV-2 virus, has convinced the world that early and affordable detection improves treatment. X-ray imaging systems are inexpensive and widely available. Chest X-ray (CXR) images are inadequate due to the acquiring environment and technician skill. Hence, CXR image contrast enhancement is necessary for a correct diagnosis. Various lung diseases create variable spatial variation in CXR image contrast and brightness; hence, a single contrast enhancement procedure cannot improve it. In the proposed method CXR images are first classified into four categories depending upon their quality defined by their statistical parameters, before applying adaptive gamma correction for contrast enhancement. The performance of the proposed method is compared with existing methods on four datasets for five different types of lung diseases. The performance of the proposed algorithm is evaluated using parameters, such as Root Mean Square Contrast (RMSC) to determine the relation of contrast enhancement between the original and enhanced image, Contrast Improvement Index (CII) to measure the achieved contrast enhancement and Tenengrad which calculates the variation of intensity in the direction of maximum gradient descent. The qualitative and quantitative performance of the proposed method is found better than the existing methods for CXR images for all five lung diseases, which shows the stable performance of the proposed method and improvement in the processed images. [ABSTRACT FROM AUTHOR]

Tuberculosis (TB) is one of the widespread infectious disease, and the early diagnosis and treatment can greatly improve the survival rate. Recently, machine learning has been introduced for assisting the diagnosis of TB, and to train a reliable diagnosis model, we need large amounts of data, which are often distributed in multiple medical centers. To protect the data privacy of different centers, we introduce federated learning (FL) in tuberculosis diagnosis. Since the data distributions of TB data vary significantly across different centers, we propose a personalized FL (PFL) method to explore the specific property of each client (i.e., medical center), and reduce its negative impacts from other clients. In particular, the contribution of each layer parameter is quantified by a hyper-network customized by the server for each client. Besides, a parameterization mechanism is introduced to update the hierarchical aggregation weights. To the best of our knowledge, this is the first PFL method for distributed TB diagnosis. Experimental results on several public datasets of chest X-ray images show that the proposed method significantly outperforms the state-of-the-art approaches in terms of both higher accuracy and faster convergence speed. [ABSTRACT FROM AUTHOR]

in the 1st and 6th months post-COVID and to determine contributing factors. BACKGROUND: The effects of COVID-19 can continue in the post-COVID period. The most common post-COVID symptoms are weakness, fatigue, nonproductive cough and exertional dyspnea. METHOD: The radiological findings of the patients at diagnosis, post-COVID 1st and 6th months; functional status and quality of life parameters at the 1st and 6th months of the post-COVID period were compared, and the factors affecting them were evaluated. The relationship between radiological involvement, quality of life and functional status parameters was investigated. RESULTS: Six months after the COVID infection, inpatient's resting oxygen saturation and effort capacity were comparable, even though they were significantly lower in the first month post-COVID. There was a correlation between functional and quality of life measures at 1 and 6 months after COVID-19 infection. In all patients, a significant improvement was found in the functional status and quality of life scales at 6 months after post- COVID infection compared to the 1st month. Even though radiological findings of both groups improved within the first month after COVID-19 infection, there remained a difference between them that disappeared after six months. CONCLUSION: It was found that in the post-COVID period, the severity of the disease had a negative effect on functional measurements and quality of life; however, regardless of the severity of the disease, after six months improvements in radiological findings, effort capacity, and quality of life measures were noted [ABSTRACT FROM AUTHOR]

Chest x‐ray (CXR) is an effective method for diagnosing heart failure, and identifying important features such as cardiomegaly, effusion, and edema on patient chest x‐rays is significant for aiding the treatment of heart failure. However, manually identifying a vast amount of CXR data places a huge burden on physicians. Deep learning's progression has led to the utilization of this technology in numerous research aimed at tackling these particular challenges. However, many of these studies utilize global learning methods, where the contribution of each pixel to the classification is considered equal, or they overly focus on small areas of the lesion while neglecting the global context. In response to these issues, we propose the Global Local Attention Network (GLAN), which incorporates an improved attention module on a branched structure. This enables the network to capture small lesion areas while also considering both local and global features. We evaluated the effectiveness of the proposed model by testing it on multiple public datasets and real‐world datasets. Compared to the state‐of‐the‐art methods, our network structure demonstrated greater accuracy and effectiveness in the identification of three key features: cardiomegaly, effusion, and edema. This provides more targeted support for diagnosing and treating heart failure. [ABSTRACT FROM AUTHOR]

Introduction: Chest X‐ray (CXR) remains one of the tools used in diagnosing tuberculosis (TB). However, few studies about such tools exist, specifically in children in Indonesia. We aim to investigate and compare the CXR findings of children with pulmonary drug‐resistant TB (DR‐TB) and drug‐sensitive TB (DS‐TB) that could help in the evaluation and management of TB cases in children. Methods: Retrospective analysis with cross‐sectional approach was conducted in children (<18 years old) diagnosed with pulmonary DR‐TB and DS‐TB from January 2018 to December 2021. Documented data were collected from the Paediatric Respirology Registry and Tuberculosis Information System at Dr. Hasan Sadikin General Hospital Bandung. Characteristics of children, CXR findings, and TB severity were assessed and compared using the chi‐square and Fisher's exact tests with significance levels set at p value <0.05. Results: Sixty‐nine children (DR‐TB 31 children vs. DS‐TB 38 children) were assessed. Of the 31 children with DR‐TB, 65% were classified as multidrug‐resistant TB (MDR‐TB), followed by rifampicin‐resistant TB (RR‐TB), pre‐extensively drug‐resistant TB (pre‐XDR‐TB), and extensively drug‐resistant TB (XDR‐TB). The most common CXR findings in DR‐TB are consolidation (68%), fibrosis (42%), and cavity (29%), whereas in DS‐TB, it is pleura effusion (37%). Severe TB accounts for 50% of DR‐TB (p = 0.008). Conclusions: Consolidation, fibrosis, cavities, and findings of severe TB are most common in DR‐TB. Pleural effusion is the most common in DS‐TB. These findings have the potential to be considered in further examination of children with pulmonary DR‐TB and DS‐TB; hence, more extensive studies are needed to confirm these results. [ABSTRACT FROM AUTHOR]

Background and Objective: Chest x‐ray (CXR) remains a core component of health monitoring guidelines for workers at risk of exposure to crystalline silica. There has however been a lack of evidence regarding the sensitivity of CXR to detect silicosis in artificial stone benchtop industry workers. Methods: Paired CXR and high‐resolution computed tomography (HRCT) images were acquired from 110 artificial stone benchtop industry workers. Blinded to the clinical diagnosis, each CXR and HRCT was independently read by two thoracic radiologists from a panel of seven, in accordance with International Labour Office (ILO) methodology for CXR and International Classification of HRCT for Occupational and Environmental Respiratory Diseases. Accuracy of screening positive (ILO major category 1, 2 or 3) and negative (ILO major category 0) CXRs were compared with identification of radiological features of silicosis on HRCT. Results: CXR was positive for silicosis in 27/110 (24.5%) workers and HRCT in 40/110 (36.4%). Of the 83 with a negative CXR (ILO category 0), 15 (18.1%) had silicosis on HRCT. All 11 workers with ILO category 2 or 3 CXRs had silicosis on HRCT. In 99 workers ILO category 0 or 1 CXRs, the sensitivity of screening positive CXR compared to silicosis identified by HRCT was 48% (95%CI 29–68) and specificity 97% (90–100). Conclusion: Compared to HRCT, sensitivity of CXR was low but specificity was high. Reliance on CXR for health monitoring would provide false reassurance for many workers, delay management and underestimate the prevalence of silicosis in the artificial stone benchtop industry. The use of CXR to screen artificial stone benchtop industry workers for silicosis has low sensitivity compared to HRCT chest, especially for early‐stage disease. Reliance on chest x‐ray for screening will fail to identify many workers with artificial stone silicosis and underestimate the prevalence of respiratory disease in this industry. [ABSTRACT FROM AUTHOR]

Presented is an approach to a chest radiograph, paying particular attention to features commonly seen in the intensive care unit (ICU) with regards to iatrogenic lines and tubes, together with common pathologies that may be encountered. This is accompanied by helpful images to use as an aide memoire when reviewing ICU chest X-rays. Pitfalls in interpreting these often complex X-rays are also discussed. [ABSTRACT FROM AUTHOR]

The world was affected by a novel coronavirus in December 2019 that changed human life. Several types of research have been done, substantial scientific advances have been made, and millions of dollars have been spent on bringing scholars and scientists to one platform to end this critical pandemic. Ascertaining COVID-19 diagnoses in the initial stage of the pandemic was critical, specifically for patients with no manifestations. In this case, artificial intelligence-based systems were proposed to identify the virus at an earlier phase. Thus, the present study suggests a machine vision scheme to identify COVID-19 from chest X-ray images. Three machine learning approaches, such as logistic regression (LR), decision tree (DT), and random forest (RF), were implemented with more than 95% accuracy. The deep convolutional neural network (CNN) architecture was also proposed and implemented with a 99.99% detection rate. Therefore, the present work can effectively detect COVID-19 cases in the early stages. [ABSTRACT FROM AUTHOR]

In accordance to the World Health Organization (WHO), various pulmonary diseases cause thousands of deaths annually. The early diagnosis is required to lessen the mortality rate. For this reason, A Convolutional Neural Network (CNN)-based Lung Disease (LD) detection system is developed to classify segregated lung sections into various pulmonary diseases types. However, epistemic uncertainty in the scanned images affecting the performance of detection classifiers. Hence, in this paper, a multi-modal approach is proposed to solve the epistemic uncertainty issue and provides a reliable solution for rapid detection of various LD types from CXR images. In this method, CT images are additionally used to improve model's performance as it contains detailed information that might be exploited to provide efficient results. Initially, the collected images are segmented using U-Net model to get enhanced lung Region of Interest (ROIs). Then ResNet50, DenseNet121, InceptionResNetV2 and XceptionV3 are used to hierarchically extract informative and discriminative features from collected CXR and CT images. The retrieved deep features are fed into the Ensemble-Convolutional Long Short Term Memory with Extreme Machine Learning (EconLSTM-ELM) to minimize the computational time and increase the accuracy. Moreover, Transfer Learning (TL) model is employed to learn the weight of the E-conLSTM-ELM to exchange the knowledge between features and classes relation among CXR and CT images. Also, the domain adaptation approach is a variant of TL model that relies on employing similar datasets for a shared learning problem. This adaption strategy reduces the domain shift (data dispersion) using Maximum Mean Discrepancy (MMD). The shared semantic features from CT images through TL improve the in-depth learning of softmax layer to classify different LD types. The proposed work is simply named as Convolutional LD Scan (CovLscan) framework The test outcomes reveal that the CovLscan model accomplishes an overall accuracy of 95.46% and 96.15% on the collected ChestX-ray8 and NIH-CXR datasets, which is higher than the existing models like Automated Hierarchical Deep Learning based LD Diagnosis(AHDL-LDD), EfficientNet version2-Medium (EfficientNet v2-M), Lung diseases prediction Network22(LungNet22), Chest tract disorder prediction using Dilated Convolutional Network(CDCNet) and Auction-Based Optimization Algorithm-CNN (ABOA-CNN). [ABSTRACT FROM AUTHOR]

Abstract Medical imaging is an indispensable and very important step in the diagnosis and treatment of illnesses. However, due to large amounts of resources necessary for training the model, training from scratch may not invariably emerge as the optimal recourse. Transfer learning has emerged as a viable solution, where pretrained weights from ImageNet are initially utilized and fine-tuninned afterwards. This paper presents a novel approach employing transfer learning to classify both respiratory diseases and radiological findings from chest X-rays. The dataset comprises 191 660 X-ray images gathered from public databases and 752 chest X-ray images obtained from a retrospective study at the University Clinical Center of Kragujevac, forming the foundation of Big data analysis. It includes various conditions such as atelectasis, cardiomegaly, infiltration, pleural thickening, non-viral pneumonia, pneumothorax, COVID-19 viral pneumonia, tuberculosis, etc. as well as masses and nodules indicative of tumors and images of healthy subjects. Although there are existing solutions with some diseases, this is the first paper that inlcludes differentiation between healthy and diseased cases, as well as in case of present disease, as much as 18 different classes are inlcuded in the analysis, which has not been done so far. The proposed methodology included transfer learning with DenseNet121 as the backbone and CheXNeXt weights as initialisation scheme, upon which additional layers were added for fine tuning. The results demonstrate the model’s capacity to distinguish between healthy and diseased, with an average area under curve (AUC) of 0.99. The AUC ranges from 0.86 for nodules to 0.99 for pneumonia and 0.99 for COVID-19. Our method outperforms the state-of-the-art in accuracy across all 18 classes, with the exception of classes consolidation, mass, and nodule. These findings are promising for a tested clinical site, though further validation in clinical environment accros multiple sites may be necessary before using the model as a standalone decision system, rather than a decision support system for disease diagnosis based on chest X-rays.

No abstract available. Manuscript truncated after 150 words. History of Present Illness The patient is a 57-year-old woman with a history of ulcerative colitis (UC) complicated by toxic megacolon with subsequent colectomy. She presented to the emergency department with cough, shortness of breath and hypoxemia (87% on RA). PMH, SH • UC with history of toxic megacolon (4 years prior) with a total colectomy • History of a prior episode of respiratory failure a year earlier thought possibly medication induced (ustekinumab, Stelara®) which she was taking for her UC. She was treated with steroids at that time with good response. • Pyoderma gangrenosum of both ankles (attributed to UC). • Anemia of chronic disease. • She is a lifelong non-smoker. • No exposures to toxic dusts, birds, down, humidifiers, mold or other antigens associated with hypersensitivity pneumonitis. Physical Exam • Afebrile, Oxygen saturation 94% on 2 lpm supplemental oxygen. • Chest: crackles noted at left base. • CV regular rhythm, no murmur. Ext: scarring and erythema on …

Persistent left superior vena cava (PLSVC) is a rare congenital anomaly. We presented PLSVC in a patient with end-stage renal disease (ESRD) requiring hemodialysis. The left internal jugular vein was utilized for central venous access due to difficult central vascular access, resulting in a diagnosis of PLSVC draining in the left atrium. This case underscores the importance of awareness of anatomical variations before central catheter placement.

No abstract available. Article truncated after 150 words. A 79-year-old man presented to our institution for evaluation of intermittent fevers, profound nasal pain with congestion, cough, sore throat, voice changes, fatigue, generalized weakness, and loose stools which had been progressively affecting the patient for the last 6 months. The patient has a past medical history of ulcerative colitis, hypothyroidism, atrial fibrillation, and hypertension. Just preceding the onset of symptoms, the patient had gone on a month-long trip through Africa and Asia. His symptoms were presumed infectious in the outpatient setting and had responded somewhat to an extended course of ciprofloxacin and metronidazole. The patient had an outpatient head and neck CT that demonstrated significant mucosal thickening of the maxillary sinuses (Figure 3A). An outside hospital CT of the abdomen/pelvis was unremarkable aside from sigmoid diverticulosis. The patient’s significant nasal pain and congestion along with the fevers was suggestive of granulomatosis with polyangiitis (GPA). The differential also included hematologic …

Atopobium minutum (A. minutum) has rarely been documented in human infections. However, this report describes a case involving a 52-year-old woman who developed empyema and lung collapse due to A. minutum. She initially presented to the emergency department with nausea, vomiting, diarrhea, and abdominal pain. Her condition quickly declined within the first day of arrival, leading to respiratory failure and requiring intubation and ICU-level care. Despite receiving intensive antibiotic treatment, the patient needed prolonged intubation and a tracheostomy. Initial cultures indicated Streptococcus intermedius and Lactobacillus minutus, but final culture results identified A. minutum as the cause. This case highlights the difficulty in diagnosing A. minutum infections, often necessitating advanced DNA sequencing, and raises concerns about potential multidrug resistance. It highlights the importance of prompt identification of the pathogen by laboratories to allow for effective treatment of these rare infections.

PURPOSE: To integrate and evaluate an artificial intelligence (AI) system that assists in checking endotracheal tube (ETT) placement on chest x-rays (CXRs) in clinical practice. APPROACH: In clinical use over 17 months, 214 CXR images were ordered to check ETT placement with AI assistance by intensive care unit (ICU) physicians. The system was built on the SimpleMind Cognitive AI platform and integrated into a clinical workflow. It automatically identified the ETT and checked its placement relative to the trachea and carina. The ETT overlay and misplacement alert messages generated by the AI system were compared with radiology reports as the reference. A survey study was also conducted to evaluate usefulness of the AI system in clinical practice. RESULTS: The alert messages indicating that either the ETT was misplaced or not detected had a positive predictive value of 42% (21/50) and negative predictive value of 98% (161/164) based on the radiology reports. In the survey, radiologist and ICU physician users indicated that they agreed with the AI outputs and that they were useful. CONCLUSIONS: The AI system performance in real-world clinical use was comparable to that seen in previous experiments. Based on this and physician survey results, the system can be deployed more widely at our institution, using insights gained from this evaluation to make further algorithm improvements and quality assurance of the AI system.

Abstract COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus’s variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework’s reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings.

No abstract available. Article truncated after 150 words. Clinical History: A 65-year-old woman with presents with intermittent right-sided chest pain and shortness of breath / dyspnea on exertion for several months’ duration. The patient’s past medical history includes a history of myocardial infarction with stent placement and atrial fibrillation. She has no prior surgical history aside from carpal tunnel release and tonsillectomy. The patient is a lifelong non-smoker, she reports no allergies and she drinks alcohol only socially and denies illicit drug use. Her medications include Xarelto (rivaroxaban) for her atrial fibrillation, alendronate, atorvastatin, metoprolol, and pantoprazole in addition to a multivitamin. On physical examination the patient was obese but not in acute distress, with normal blood pressure, pulse rate, and respiratory rate. Her pulmonary and cardiovascular examination was unremarkable aside for dullness to percussion over the right posterior and lateral thorax, and her musculoskeletal examination did not disclose any abnormalities. She was neurologically intact. Oxygen saturation at …

COVID-19 detection is mainly based on molecular testing, especially polymerase chain reaction (PCR) analyses, to find the occurrence of the virus's genetic material in respiratory samples. Computed tomography (CT) scans and X-rays are the two chest imaging techniques, which may provide more details on lungs, aiding in the diagnosis. Radiological findings in COVID-19 cases typically involve special features such as bilateral involvement, ground-glass opacities, and consolidation of the lungs. Deep learning (DL) methods, particularly convolutional neural networks (CNNs) are used for analyzing COVID-19 infection. By training these techniques on large datasets of annotated chest X-rays (CXRs), researches have attained superior outcomes in precisely detecting the possible COVID-19 cases. Leveraging artificial intelligence together with radiological expertise holds great potential for facilitating prompt intervention in the ongoing global efforts and improving the efficiency of early detection. This article focuses on the design of mother optimization algorithm with DL-enabled detection and classification (MOA-DLEDC) technique for COVID-19 diagnosis using CXR images. In the MOA-DLEDC technique, the adaptive median filtering (AMF) approach is used to eliminate the existence of noise. In addition, the complex and intrinsic feature patterns are derived from the Efficient DenseNet model. Besides, the hyperparameter optimization of the Efficient DenseNet model takes place using MOA. For the COVID-19 detection process, the MOA-DLEDC technique applies sparse autoencoder (SAE) model. A detailed set of experiments was conducted on the CXR dataset to highlight the promising results of the MOA-DLEDC technique. The extensive results inferred that the used technique gains superior performance over other models with maximum accuracy of 99.59 %.

Background and purpose: Leptospirosis is a common disease between humans and animals, the source of which is rodents, canines, etc., the disease is transmitted by scratching the skin and getting it contaminated with water contaminated with animal urinary waste and is currently an endemic disease in neighboring northern provinces of Iran. The purpose of this study was to investigate the findings of chest X-ray and lung CT scans in leptospirosis with or without pulmonary symptoms. Materials and methods: The current descriptive and retrospective research examined the findings of chest X-ray and CT scan of the lungs in patients with leptospirosis with or without pulmonary manifestations in Razi Ghaemshahr Hospital. In this study, 49 hospitalized patients were randomly selected from the records of leptospirosis patients in Razi Ghaemshahr Hospital during the spring and summer of 2017 from an information form based on clinical epidemiological characteristics and risk factors for leptospirosis patients using the mentioned characteristics. The disease was prepared in the infectious reference books and articles published in Farsi and English about this disease, and help was taken from a radiologist colleague to interpret the findings of the chest X-ray and CT scan of the lungs. After recording in SPSS 16 software, the data were analyzed through a Q_Q graph and skewness index. The clinical and epidemiological findings of leptospirosis were considered as inclusion criteria in the study, and the absence of serological tests to confirm leptospirosis was considered as exclusion criteria. Results: Among 49 hospitalized patients with leptospirosis, 11 patients had abnormal radiological findings and 38 patients had normal X-rays. Among 11 patients with abnormal radiological findings, 6 patients had respiratory symptoms, which included 54.54% cough and 18.18% bloody sputum. Among 38 patients with normal radiography, 11 patients had pulmonary symptoms, which included 29.94% cough and 2.63% bloody sputum. The amount of cough was significantly higher. Abnormal findings in chest X-ray, alveolar infiltration, ground glass opacity, and consolidation were the most frequent in the CT scan of the lung. Conclusion: Considering the significant percentage of normal chest radiographs in patients suffering from rice field fever with pulmonary symptoms, it is essential to perform a CT scan of the chest and decide on more effective therapeutic interventions. Therefore, it is considerable that usually changes in the chest CT scan in the severe form of the disease that causes vasculitis and alveolar bleeding appear before the appearance of severe symptoms such as bloody sputum and make a decision to start more effective drugs in the patient's treatment plan. As a result, pulmonary involvement in patients with leptospirosis is of special importance and it should be given special attention due to the endemicity of leptospirosis in the province, considering the associated complications and high mortality and the possibility of its occurrence even in patients who do not have respiratory complaints at the time of presentation. It is suggested to conduct more extensive research based on the population in this field.

Artificial intelligence (AI) technology is actively being applied for the interpretation of medical imaging, such as chest X-rays. AI-based software medical devices, which automatically detect various types of abnormal findings in chest X-ray images to assist physicians in their interpretation, are actively being commercialized and clinically implemented in Korea. Several important issues need to be considered for AI-based detection assistant tools to be applied in clinical practice: the evaluation of performance and efficacy prior to implementation; the determination of the target application, range, and method of delivering results; and monitoring after implementation and legal liability issues. Appropriate decision making regarding these devices based on the situation in each institution is necessary. Radiologists must be engaged as medical assessment experts using the software for these devices as well as in medical image interpretation to ensure the safe and efficient implementation and operation of AIbased detection assistant tools.

Abstract Quick and accurate diagnosis of COVID‐19 is crucial in preventing its transmission. Chest X‐ray (CXR) imaging is often used for diagnosis, however, even experienced radiologists may misinterpret the results, necessitating computer‐aided diagnosis. Deep learning has yielded favourable results previously, but overfitting, excessive variance, and generalization errors may occur due to noise and limited datasets. Ensemble learning can improve predictions by using robust techniques. Therefore, this study, proposes two‐fold strategy that combines advanced and robust algorithms, including DenseNet201, EfficientNetB7, and Xception, to achieve faster and more accurate COVID‐19 detection. Segmented lung images were generated from CXR images using the residual U‐Net model, and two attention‐based ensemble neural networks were used for classification. The COVID‐19 radiography dataset was used to evaluate the proposed approach, which achieved an accuracy of 98.21%, 93.4%, and 89.06% for two, three, and four classes respectively which outperformed previous studies by a significant margin considering COVID, viral pneumonia, and lung opacity simultaneously. Despite the similarity in CXR images of COVID, pneumonia, and lung opacity, the proposed approach achieved 89.06% accuracy, demonstrating its ability to recognize distinguishable features. The developed algorithm is expected to have applications in clinics for diagnosing different diseases using X‐ray images.

Abstract In tuberculosis (TB), chest radiography (CXR) patterns are highly variable, mimicking pneumonia and many other diseases. This study aims to evaluate the efficacy of Google teachable machine, a deep neural network-based image classification tool, to develop algorithm for predicting TB probability of CXRs. The training dataset included 348 TB CXRs and 3806 normal CXRs for training TB detection. We also collected 1150 abnormal CXRs and 627 normal CXRs for training abnormality detection. For external validation, we collected 250 CXRs from our hospital. We also compared the accuracy of the algorithm to five pulmonologists and radiological reports. In external validation, the AI algorithm showed areas under the curve (AUC) of 0.951 and 0.975 in validation dataset 1 and 2. The accuracy of the pulmonologists on validation dataset 2 showed AUC range of 0.936–0.995. When abnormal CXRs other than TB were added, AUC decreased in both human readers (0.843–0.888) and AI algorithm (0.828). When combine human readers with AI algorithm, the AUC further increased to 0.862–0.885. The TB CXR AI algorithm developed by using Google teachable machine in this study is effective, with the accuracy close to experienced clinical physicians, and may be helpful for detecting tuberculosis by CXR.

History of Present Illness: The patient is a 57-year-old woman who presented to the emergency department with increasing cough and shortness of breath over several days. She has a history of ulcerative colitis complicated by toxic megacolon with subsequent colectomy. Past Medical History, Family History and Social History • Ulcerative colitis with history of toxic megacolon (4 years prior), s/p total colectomy • History of recent respiratory failure thought secondary to ustekinumab (Stelara). The respiratory failure responded well to steroid therapy. • She has a history of latent Tb treated with rifampin • Anxiety Medications • Clonazepam 1.0 mg daily at bedtime • Gabapentin 300 mg TID • Pantoprazole 40 mg BID • Prednisone 5 mg daily Physical Examination • Mild-moderate respiratory distress • Afebrile. SpO2 87% on room air. Oxygen saturation 94% on 2 lpm supplemental oxygen. • Chest: crackles noted at left base • Cardiovascular: regular rhythm, no murmur • Extremities: scarring and erythema on both ankles consistent with resolving pyoderma …

COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus’s variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework’s reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings. [ABSTRACT FROM AUTHOR]

Background: Chest X-rays (CXRs) are pivotal in clinical diagnostics, particularly in assessing cardiomegaly through the cardiothoracic ratio (CTR). This systematic review and meta-analysis evaluate the efficacy of artificial intelligence (AI) in automating CTR determination to enhance patient care and streamline diagnostic processes. They are concentrated on comparing the performance of AI models in determining the CTR against human assessments, identifying the most effective models for potential clinical implementation. This study was registered with PROSPERO (no. CRD42023437459). No funding was received. Methods: A comprehensive search of medical databases was conducted in June 2023. The search strategy adhered to the PICO framework. Inclusion criteria encompassed original articles from the last decade focusing on AI-assisted CTR assessment from standing-position CXRs. Exclusion criteria included systematic reviews, meta-analyses, conference abstracts, paediatric studies, non-original articles, and studies using imaging techniques other than X-rays. After initial screening, 117 articles were reviewed, with 14 studies meeting the final inclusion criteria. Data extraction was performed by three independent investigators, and quality assessment followed PRISMA 2020 guidelines, using tools such as the JBI Checklist, AMSTAR 2, and CASP Diagnostic Study Checklist. Risk of bias was assessed according to the Cochrane Handbook guidelines. Results: Fourteen studies, comprising a total of 70,472 CXR images, met the inclusion criteria. Various AI models were evaluated, with differences in dataset characteristics and AI technology used. Common preprocessing techniques included resizing and normalization. The pooled AUC for cardiomegaly detection was 0.959 (95% CI 0.944–0.975). The pooled standardized mean difference for CTR measurement was 0.0353 (95% CI 0.147–0.0760). Significant heterogeneity was found between studies (I2 89.97%, p < 0.0001), with no publication bias detected. Conclusions: Standardizing methodologies is crucial to avoid interpretational errors and advance AI in medical imaging diagnostics. Uniform reporting standards are essential for the further development of AI in CTR measurement and broader medical imaging applications. [ABSTRACT FROM AUTHOR]

Aims and Objectives: To measure the reliability of pH testing to confirm ongoing nasogastric tube (NGT) position and to document associated complications. Background: Confirming NGT position is essential, as use of an incorrectly positioned tube can cause harm. Substantial evidence examines initial confirmation of NGT position, yet limited evidence exists considers NGT displacement which is identified via ongoing NGT position tests. In the NHS, pH testing is recommended to confirm ongoing NGT position; however, there may be an association with excess X‐rays and missed enteral nutrition and/or medications. Design: Prospective observational study using STROBE checklist. Methods: Data collected from medical records of 136 patients with NGTs in a London NHS Trust included pH tests, test results and complications related to ongoing pH tests which failed to confirm the tube was positioned in the stomach, that is, X‐rays, and disruptions to enteral nutrition and medication. Cohen's Kappa determined pH test reliability. Results: Of 1381 pH tests conducted to confirm NGT position, five (0.3%) correctly identified an NGT displacement, and one (0.07%) failed to identify displacement before use. The reliability of ongoing pH tests using Cohen's Kappa was minimal (0.29). Ongoing pH tests that failed to confirm a correctly positioned NGT led to 31 (22.8%) patients having X‐rays, 24 (17.6%) missing >10% of prescribed enteral nutrition and 25 (18.4%) missing a critical medication. Conclusion: Ongoing NGT position testing using pH tests did not prevent the use of a displaced tube, and more than one‐fifth of patients required X‐rays to confirm a correctly position NGT, contributing to missed medications and enteral nutrition. Relevance to Clinical Practice: Caution should be used when confirming ongoing NGT position with a pH test. Future guidelines should balance the risk of using a displaced tube with potential delays to nutrition and/or medication. More research is needed to explore alternative methods of ongoing NGT position testing. [ABSTRACT FROM AUTHOR]

COVID-19 detection is mainly based on molecular testing, especially polymerase chain reaction (PCR) analyses, to find the occurrence of the virus's genetic material in respiratory samples. Computed tomography (CT) scans and X-rays are the two chest imaging techniques, which may provide more details on lungs, aiding in the diagnosis. Radiological findings in COVID-19 cases typically involve special features such as bilateral involvement, ground-glass opacities, and consolidation of the lungs. Deep learning (DL) methods, particularly convolutional neural networks (CNNs) are used for analyzing COVID-19 infection. By training these techniques on large datasets of annotated chest X-rays (CXRs), researches have attained superior outcomes in precisely detecting the possible COVID-19 cases. Leveraging artificial intelligence together with radiological expertise holds great potential for facilitating prompt intervention in the ongoing global efforts and improving the efficiency of early detection. This article focuses on the design of mother optimization algorithm with DL-enabled detection and classification (MOA-DLEDC) technique for COVID-19 diagnosis using CXR images. In the MOA-DLEDC technique, the adaptive median filtering (AMF) approach is used to eliminate the existence of noise. In addition, the complex and intrinsic feature patterns are derived from the Efficient DenseNet model. Besides, the hyperparameter optimization of the Efficient DenseNet model takes place using MOA. For the COVID-19 detection process, the MOA-DLEDC technique applies sparse autoencoder (SAE) model. A detailed set of experiments was conducted on the CXR dataset to highlight the promising results of the MOA-DLEDC technique. The extensive results inferred that the used technique gains superior performance over other models with maximum accuracy of 99.59 %. [ABSTRACT FROM AUTHOR]

Many researchers and medical practitioners have recently focused on the automatic detection of COVID-19 using chest X-Ray (CXR) images. In the past, several computer-aided diagnostic (CAD) schemes were developed to assist healthcare professionals. These CAD systems using CXR images can speed up the identification process. As a result, we have proposed an automatic diagnosis (CAD-CXR) system by using the haar-like feature and XgBoost classifier. To develop a CAD-CXR system, we have used a pre-processing step and Haar-Like feature descriptor to extract features from chest X-ray images. Afterward, many machine learning classifiers are employed to categorize the images into coronavirus-19 and normal. Feature extraction and classification techniques are evaluated based on detection performance. Several experiments are performed to compare the performance of the proposed method with other classifiers. Our work is evaluated by public datasets with three different train-test splits in terms of average accuracy, F1-score, recall, and precision metrics. Compared to state-of-the-art methods, the XgBoost classifier with the Haar-Like feature obtained excellent performance based on the accuracy of 97.5%, F1-score of 96%, recall of 96%, and precision of 97%. These experimental results conclude that the CAD-CXR system outperforms to detect most of the covid-19 cases. The proposed CAD-CXR approach can be utilized to effectively screen the COVID-19-infected patients using CXR images. [ABSTRACT FROM AUTHOR]

Guidelines generally recommend a combination of immunological assays and chest X-ray imaging (CXR) when screening for latent tuberculosis infection (LTBI) prior to biologic treatment in inflammatory bowel disease (IBD). To investigate whether CXR identify patients with suspected LTBI/TB who were not identified with QuantiFERON tests (QFT) when screening for LTBI/TB before starting biologic treatment in IBD patients. Single-center, retrospective cohort study of patients with inflammatory bowel disease who had a QFT and a CXR prior to initiation of biologic treatment in a 5-year period (October 1st, 2017 to September 30th, 2022). 520 patients (56% female, mean age 40.1 years) were included. The majority had none or few risk factors for TB (as reflected by the demographic characteristics) but some risk factors for having false negative QFT results (concurrent glucocorticoid treatment and inflammatory activity). QFT results were positive in 8 patients (1.5%), inconclusive in 18 (3.5%) and negative in 494 (95.0%). Only 1 patient (0.19%) had CXR findings suspicious of LTBI. This patient also had a positive QFT and was subsequently diagnosed with active TB. All patients with negative or inconclusive QFT had CXR without any findings suggesting LTBI/TB. One patient developed active TB after having initiated biologic treatment in spite of having negative QFT and a normal CXR at screening. In a population with low risk of TB, the benefits of supplementing the QFT with a CXR are limited and are unlikely to outweigh the cost in both patient test-burden, radioactive exposure, and economic resources. [ABSTRACT FROM AUTHOR]

To create robust and adaptable methods for lung pneumonia diagnosis and the assessment of its severity using chest X-rays (CXR), access to well-curated, extensive datasets is crucial. Many current severity quantification approaches require resource-intensive training for optimal results. Healthcare practitioners require efficient computational tools to swiftly identify COVID-19 cases and predict the severity of the condition. In this research, we introduce a novel image augmentation scheme as well as a neural network model founded on Vision Transformers (ViT) with a small number of trainable parameters for quantifying COVID-19 severity and other lung diseases. Our method, named Vision Transformer Regressor Infection Prediction (ViTReg-IP), leverages a ViT architecture and a regression head. To assess the model's adaptability, we evaluate its performance on diverse chest radiograph datasets from various open sources. We conduct a comparative analysis against several competing deep learning methods. Our results achieved a minimum Mean Absolute Error (MAE) of 0.569 and 0.512 and a maximum Pearson Correlation Coefficient (PC) of 0.923 and 0.855 for the geographic extent score and the lung opacity score, respectively, when the CXRs from the RALO dataset were used in training. The experimental results reveal that our model delivers exceptional performance in severity quantification while maintaining robust generalizability, all with relatively modest computational requirements. The source codes used in our work are publicly available at https://github.com/bouthainas/ViTReg-IP. [ABSTRACT FROM AUTHOR]

Background: Pneumothorax is a common acute presentation in healthcare settings. A chest radiograph (CXR) is often necessary to make the diagnosis, and minimizing the time between presentation and diagnosis is critical to deliver optimal treatment. Deep learning (DL) algorithms have been developed to rapidly identify pathologic findings on various imaging modalities. Purpose: The purpose of this systematic review and meta-analysis was to evaluate the overall performance of studies utilizing DL algorithms to detect pneumothorax on CXR. Methods: A study protocol was created and registered a priori (PROSPERO CRD42023391375). The search strategy included studies published up until January 10, 2023. Inclusion criteria were studies that used adult patients, utilized computer-aided detection of pneumothorax on CXR, dataset was evaluated by a qualified physician, and sufficient data was present to create a 2 × 2 contingency table. Risk of bias was assessed using the QUADAS-2 tool. Bivariate random effects meta-analyses and meta-regression modeling were performed. Results: Twenty-three studies were selected, including 34 011 patients and 34 075 CXRs. The pooled sensitivity and specificity were 87% (95% confidence interval, 81%, 92%) and 95% (95% confidence interval, 92%, 97%), respectively. The study design, use of an institutional/public data set and risk of bias had no significant effect on the sensitivity and specificity of pneumothorax detection. Conclusions: The relatively high sensitivity and specificity of pneumothorax detection by deep-learning showcases the vast potential for implementation in clinical settings to both augment the workflow of radiologists and assist in more rapid diagnoses and subsequent patient treatment. [ABSTRACT FROM AUTHOR]

Pediatric respiratory disease diagnosis and subsequent treatment require accurate and interpretable analysis. A chest X-ray is the most cost-effective and rapid method for identifying and monitoring various thoracic diseases in children. Recent developments in self-supervised and transfer learning have shown their potential in medical imaging, including chest X-ray areas. In this article, we propose a three-stage framework with knowledge transfer from adult chest X-rays to aid the diagnosis and interpretation of pediatric thorax diseases. We conducted comprehensive experiments with different pre-training and fine-tuning strategies to develop transformer or convolutional neural network models and then evaluate them qualitatively and quantitatively. The ViT-Base/16 model, fine-tuned with the CheXpert dataset, a large chest X-ray dataset, emerged as the most effective, achieving a mean AUC of 0.761 (95% CI: 0.759–0.763) across six disease categories and demonstrating a high sensitivity (average 0.639) and specificity (average 0.683), which are indicative of its strong discriminative ability. The baseline models, ViT-Small/16 and ViT-Base/16, when directly trained on the Pediatric CXR dataset, only achieved mean AUC scores of 0.646 (95% CI: 0.641–0.651) and 0.654 (95% CI: 0.648–0.660), respectively. Qualitatively, our model excels in localizing diseased regions, outperforming models pre-trained on ImageNet and other fine-tuning approaches, thus providing superior explanations. The source code is available online and the data can be obtained from PhysioNet. [ABSTRACT FROM AUTHOR]

This paper addresses the significant problem of identifying the relevant background and contextual literature related to deep learning (DL) as an evolving technology in order to provide a comprehensive analysis of the application of DL to the specific problem of pneumonia detection via chest X-ray (CXR) imaging, which is the most common and cost-effective imaging technique available worldwide for pneumonia diagnosis. This paper in particular addresses the key period associated with COVID-19, 2020–2023, to explain, analyze, and systematically evaluate the limitations of approaches and determine their relative levels of effectiveness. The context in which DL is applied as both an aid to and an automated substitute for existing expert radiography professionals, who often have limited availability, is elaborated in detail. The rationale for the undertaken research is provided, along with a justification of the resources adopted and their relevance. This explanatory text and the subsequent analyses are intended to provide sufficient detail of the problem being addressed, existing solutions, and the limitations of these, ranging in detail from the specific to the more general. Indeed, our analysis and evaluation agree with the generally held view that the use of transformers, specifically, vision transformers (ViTs), is the most promising technique for obtaining further effective results in the area of pneumonia detection using CXR images. However, ViTs require extensive further research to address several limitations, specifically the following: biased CXR datasets, data and code availability, the ease with which a model can be explained, systematic methods of accurate model comparison, the notion of class imbalance in CXR datasets, and the possibility of adversarial attacks, the latter of which remains an area of fundamental research. [ABSTRACT FROM AUTHOR]