Performance of thoracic ultrasonography compared with chest radiography for the detection of rib fractures using computed tomography as a reference standard.

OBJECTIVE: Although there is growing evidence that ultrasonography is superior to X-ray for rib fractures' detection, X-ray is still indicated as the most appropriate method. This has partially been attributed to a lack of studies using an appropriate reference modality. We aimed to compare the diagnostic accuracy of ultrasonography and X-ray in the detection of rib fractures, considering CT as the reference standard. MATERIALS AND METHODS: Within a 2.5-year period, all consecutive patients with clinically suspected rib fracture(s) following blunt chest trauma and available posteroanterior/anteroposterior X-ray and thoracic CT were prospectively studied and planned to undergo thoracic ultrasonography, by a single operator. All imaging examinations were evaluated for cortical rib fracture(s), and their location was recorded. The cartilaginous rib portions were not assessed. CTs and X-rays were evaluated retrospectively. Concomitant thoracic/extra-thoracic injuries were assessed on CT. Comparisons were performed with the Mann-Whitney U test and Fisher's exact test. RESULTS: Fifty-nine patients (32 males, 27 females; mean age, 53.1 ± 16.6 years) were included. CT, ultrasonography, and X-ray (40 posteroanterior/19 anteroposterior views) diagnosed 136/122/42 rib fractures in 56/54/27 patients, respectively. Ultrasonography and X-ray had sensitivity of 100%/40% and specificity of 89.7%/30.9% for rib fractures' detection. Ultrasound accuracy was 94.9% compared to 35.4% for X-rays (P < .001) in detecting individual rib fractures. Most fractures involved the 4th-9th ribs. Upper rib fractures were most commonly overlooked on ultrasonography. Thoracic cage/spine fractures and haemothorax represented the most common concomitant injuries. CONCLUSION: Ultrasonography appeared to be superior to X-ray for the detection of rib fractures with regard to a reference CT.

COVID-19 Hierarchical Classification Using a Deep Learning Multi-Modal.

Coronavirus disease 2019 (COVID-19), originating in China, has rapidly spread worldwide. Physicians must examine infected patients and make timely decisions to isolate them. However, completing these processes is difficult due to limited time and availability of expert radiologists, as well as limitations of the reverse-transcription polymerase chain reaction (RT-PCR) method. Deep learning, a sophisticated machine learning technique, leverages radiological imaging modalities for disease diagnosis and image classification tasks. Previous research on COVID-19 classification has encountered several limitations, including binary classification methods, single-feature modalities, small public datasets, and reliance on CT diagnostic processes. Additionally, studies have often utilized a flat structure, disregarding the hierarchical structure of pneumonia classification. This study aims to overcome these limitations by identifying pneumonia caused by COVID-19, distinguishing it from other types of pneumonia and healthy lungs using chest X-ray (CXR) images and related tabular medical data, and demonstrate the value of incorporating tabular medical data in achieving more accurate diagnoses. Resnet-based and VGG-based pre-trained convolutional neural network (CNN) models were employed to extract features, which were then combined using early fusion for the classification of eight distinct classes. We leveraged the hierarchal structure of pneumonia classification within our approach to achieve improved classification outcomes. Since an imbalanced dataset is common in this field, a variety of versions of generative adversarial networks (GANs) were used to generate synthetic data. The proposed approach tested in our private datasets of 4523 patients achieved a macro-avg F1-score of 95.9% and an F1-score of 87.5% for COVID-19 identification using a Resnet-based structure. In conclusion, in this study, we were able to create an accurate deep learning multi-modal to diagnose COVID-19 and differentiate it from other kinds of pneumonia and normal lungs, which will enhance the radiological diagnostic process.

The Performance of Computer-Aided Detection Digital Chest X-ray Reading Technologies for Triage of Active Tuberculosis Among Persons With a History of Previous Tuberculosis.

BACKGROUND: Digital chest X-ray (dCXR) computer-aided detection (CAD) technology uses lung shape and texture analysis to determine the probability of tuberculosis (TB). However, many patients with previously treated TB have sequelae, which also distort lung shape and texture. We evaluated the diagnostic performance of 2 CAD systems for triage of active TB in patients with previously treated TB. METHODS: We conducted a retrospective analysis of data from a cross-sectional active TB case finding study. Participants ≥15 years, with ≥1 current TB symptom and complete data on history of previous TB, dCXR, and TB microbiological reference (Xpert MTB/RIF) were included. dCXRs were evaluated using CAD4TB (v.7.0) and qXR (v.3.0). We determined the diagnostic accuracy of both systems, overall and stratified by history of TB, using a single threshold for each system that achieved 90% sensitivity and maximized specificity in the overall population. RESULTS: Of 1884 participants, 452 (24.0%) had a history of previous TB. Prevalence of microbiologically confirmed TB among those with and without history of previous TB was 12.4% and 16.9%, respectively. Using CAD4TB, sensitivity and specificity were 89.3% (95% CI: 78.1-96.0%) and 24.0% (19.9-28.5%) and 90.5% (86.1-93.3%) and 60.3% (57.4-63.0%) among those with and without previous TB, respectively. Using qXR, sensitivity and specificity were 94.6% (95% CI: 85.1-98.9%) and 22.2% (18.2-26.6%) and 89.7% (85.1-93.2%) and 61.8% (58.9-64.5%) among those with and without previous TB, respectively. CONCLUSIONS: The performance of CAD systems as a TB triage tool is decreased among persons previously treated for TB.

A clinical evaluation study of cardiothoracic ratio measurement using artificial intelligence.

BACKGROUND: Artificial intelligence, particularly the deep learning (DL) model, can provide reliable results for automated cardiothoracic ratio (CTR) measurement on chest X-ray (CXR) images. In everyday clinical use, however, this technology is usually implemented in a non-automated (AI-assisted) capacity because it still requires approval from radiologists. We investigated the performance and efficiency of our recently proposed models for the AI-assisted method intended for clinical practice. METHODS: We validated four proposed DL models (AlbuNet, SegNet, VGG-11, and VGG-16) to find the best model for clinical implementation using a dataset of 7517 CXR images from manual operations. These models were investigated in single-model and combined-model modes to find the model with the highest percentage of results where the user could accept the results without further interaction (excellent grade), and with measurement variation within ± 1.8% of the human-operating range. The best model from the validation study was then tested on an evaluation dataset of 9386 CXR images using the AI-assisted method with two radiologists to measure the yield of excellent grade results, observer variation, and operating time. A Bland-Altman plot with coefficient of variation (CV) was employed to evaluate agreement between measurements. RESULTS: The VGG-16 gave the highest excellent grade result (68.9%) of any single-model mode with a CV comparable to manual operation (2.12% vs 2.13%). No DL model produced a failure-grade result. The combined-model mode of AlbuNet + VGG-11 model yielded excellent grades in 82.7% of images and a CV of 1.36%. Using the evaluation dataset, the AlbuNet + VGG-11 model produced excellent grade results in 77.8% of images, a CV of 1.55%, and reduced CTR measurement time by almost ten-fold (1.07 ± 2.62 s vs 10.6 ± 1.5 s) compared with manual operation. CONCLUSION: Due to its excellent accuracy and speed, the AlbuNet + VGG-11 model could be clinically implemented to assist radiologists with CTR measurement.

Deep transfer learning to quantify pleural effusion severity in chest X-rays.

PURPOSE: The detection of pleural effusion in chest radiography is crucial for doctors to make timely treatment decisions for patients with chronic obstructive pulmonary disease. We used the MIMIC-CXR database to develop a deep learning model to quantify pleural effusion severity in chest radiographs. METHODS: The Medical Information Mart for Intensive Care Chest X-ray (MIMIC-CXR) dataset was divided into patients 'with' or 'without' chronic obstructive pulmonary disease (COPD). The label of pleural effusion severity was obtained from the extracted COPD radiology reports and classified into four categories: no effusion, small effusion, moderate effusion, and large effusion. A total of 200 datasets were randomly sampled to manually check each item and determine whether the tags are correct. A professional doctor re-tagged these items as a verification cohort without knowing their previous tags. The learning models include eight common network structures including Resnet, DenseNet, and GoogleNET. Three data processing methods (no sampling, downsampling, and upsampling) and two loss algorithms (focal loss and cross-entropy loss) were used for unbalanced data. The Neural Network Intelligence tool was applied to train the model. Receiver operating characteristic curves, Area under the curve, and confusion matrix were employed to evaluate the model results. Grad-CAM was used for model interpretation. RESULTS: Among the 8533 patients, 15,620 chest X-rays with clearly marked pleural effusion severity were obtained (no effusion, 5685; small effusion, 4877; moderate effusion, 3657; and large effusion, 1401). The error rate of the manual check label was 6.5%, and the error rate of the doctor's relabeling was 11.0%. The highest accuracy rate of the optimized model was 73.07. The micro-average AUCs of the testing and validation cohorts was 0.89 and 0.90, respectively, and their macro-average AUCs were 0.86 and 0.89, respectively. The AUC of the distinguishing results of each class and the other three classes were 0.95 and 0.94, 0.76 and 0.83, 0.85 and 0.83, and 0.87 and 0.93. CONCLUSION: The deep transfer learning model can grade the severity of pleural effusion.

Using a Deep Learning Model to Explore the Impact of Clinical Data on COVID-19 Diagnosis Using Chest X-ray.

The coronavirus pandemic (COVID-19) is disrupting the entire world; its rapid global spread threatens to affect millions of people. Accurate and timely diagnosis of COVID-19 is essential to control the spread and alleviate risk. Due to the promising results achieved by integrating machine learning (ML), particularly deep learning (DL), in automating the multiple disease diagnosis process. In the current study, a model based on deep learning was proposed for the automated diagnosis of COVID-19 using chest X-ray images (CXR) and clinical data of the patient. The aim of this study is to investigate the effects of integrating clinical patient data with the CXR for automated COVID-19 diagnosis. The proposed model used data collected from King Fahad University Hospital, Dammam, KSA, which consists of 270 patient records. The experiments were carried out first with clinical data, second with the CXR, and finally with clinical data and CXR. The fusion technique was used to combine the clinical features and features extracted from images. The study found that integrating clinical data with the CXR improves diagnostic accuracy. Using the clinical data and the CXR, the model achieved an accuracy of 0.970, a recall of 0.986, a precision of 0.978, and an F-score of 0.982. Further validation was performed by comparing the performance of the proposed system with the diagnosis of an expert. Additionally, the results have shown that the proposed system can be used as a tool that can help the doctors in COVID-19 diagnosis.

Study of Different Deep Learning Methods for Coronavirus (COVID-19) Pandemic: Taxonomy, Survey and Insights.

COVID-19 has evolved into one of the most severe and acute illnesses. The number of deaths continues to climb despite the development of vaccines and new strains of the virus have appeared. The early and precise recognition of COVID-19 are key in viably treating patients and containing the pandemic on the whole. Deep learning technology has been shown to be a significant tool in diagnosing COVID-19 and in assisting radiologists to detect anomalies and numerous diseases during this epidemic. This research seeks to provide an overview of novel deep learning-based applications for medical imaging modalities, computer tomography (CT) and chest X-rays (CXR), for the detection and classification COVID-19. First, we give an overview of the taxonomy of medical imaging and present a summary of types of deep learning (DL) methods. Then, utilizing deep learning techniques, we present an overview of systems created for COVID-19 detection and classification. We also give a rundown of the most well-known databases used to train these networks. Finally, we explore the challenges of using deep learning algorithms to detect COVID-19, as well as future research prospects in this field.

Ivermectin induces chicken BCRP/ABCG2 expression and function: Involvement of CXR signaling pathway and mRNA stabilization.

Ivermectin is a macrocyclic lactone antiparasitic drug widely used in human and veterinary medicine. Previous studies indicated that ivermectin could interact with P-glycoprotein, being a good inducer and substrate; however, it is unknown whether ivermectin affects BCRP of chicken. In this study, we found that ivermectin distinctly affected the expression of BCRP in a time- and concentration-dependent up-regulatory way in chicken primary hepatocytes. Subsequent series of experiments showed that the BCRP induction is related with the increase of CXR expression and, promoting CXR translocations to the nucleus and enhancing the stability of Abcg2 mRNA at the post-transcriptional level by ivermectin. Furthermore, we observed that ivermectin also enhanced the stability of Abcg2 mRNA at the post-transcriptional level by Act-D chase assay. We got the similar results by in vivo test that ivermectin-induced BCRP and CXR expression in pharmacologically important tissues, and decreased the apparent permeability coefficient of florfenicol (substrate of chicken BCRP). In conclusion, the results indicated that ivermectin could induce chicken BCRP expression and function through the transcriptional CXR signaling pathway and post-transcriptional mRNA stabilization.

COVID-19 prognosis using limited chest X-ray images.

The COrona VIrus Disease 2019 (COVID-19) pandemic is an ongoing global pandemic that has claimed millions of lives till date. Detecting COVID-19 and isolating affected patients at an early stage is crucial to contain its rapid spread. Although accurate, the primary viral test 'Reverse Transcription Polymerase Chain Reaction' (RT-PCR) for COVID-19 diagnosis has an elaborate test kit, and the turnaround time is high. This has motivated the research community to develop CXR based automated COVID-19 diagnostic methodologies. However, COVID-19 being a novel disease, there is no annotated large-scale CXR dataset for this particular disease. To address the issue of limited data, we propose to exploit a large-scale CXR dataset collected in the pre-COVID era and train a deep neural network in a self-supervised fashion to extract CXR specific features. Further, we compute attention maps between the global and the local features of the backbone convolutional network while finetuning using a limited COVID-19 CXR dataset. We empirically demonstrate the effectiveness of the proposed method. We provide a thorough ablation study to understand the effect of each proposed component. Finally, we provide visualizations highlighting the critical patches instrumental to the predictive decision made by our model. These saliency maps are not only a stepping stone towards explainable AI but also aids radiologists in localizing the infected area.

Deep features to detect pulmonary abnormalities in chest X-rays due to infectious diseaseX: Covid-19, pneumonia, and tuberculosis.

Chest X-ray (CXR) imaging is a low-cost, easy-to-use imaging alternative that can be used to diagnose/screen pulmonary abnormalities due to infectious diseaseX: Covid-19, Pneumonia and Tuberculosis (TB). Not limited to binary decisions (with respect to healthy cases) that are reported in the state-of-the-art literature, we also consider non-healthy CXR screening using a lightweight deep neural network (DNN) with a reduced number of epochs and parameters. On three diverse publicly accessible and fully categorized datasets, for non-healthy versus healthy CXR screening, the proposed DNN produced the following accuracies: 99.87% on Covid-19 versus healthy, 99.55% on Pneumonia versus healthy, and 99.76% on TB versus healthy datasets. On the other hand, when considering non-healthy CXR screening, we received the following accuracies: 98.89% on Covid-19 versus Pneumonia, 98.99% on Covid-19 versus TB, and 100% on Pneumonia versus TB. To further precisely analyze how well the proposed DNN worked, we considered well-known DNNs such as ResNet50, ResNet152V2, MobileNetV2, and InceptionV3. Our results are comparable with the current state-of-the-art, and as the proposed CNN is light, it could potentially be used for mass screening in resource-constraint regions.

Federated learning based Covid-19 detection.

The world is affected by COVID-19, an infectious disease caused by the SARS-CoV-2 virus. Tests are necessary for everyone as the number of COVID-19 affected individual's increases. So, the authors developed a basic sequential CNN model based on deep and federated learning that focuses on user data security while simultaneously enhancing test accuracy. The proposed model helps users detect COVID-19 in a few seconds by uploading a single chest X-ray image. A deep learning-aided architecture that can handle client and server sides efficiently has been proposed in this work. The front-end part has been developed using StreamLit, and the back-end uses a Flower framework. The proposed model has achieved a global accuracy of 99.59% after being trained for three federated communication rounds. The detailed analysis of this paper provides the robustness of this work. In addition, the Internet of Medical Things (IoMT) will improve the ease of access to the aforementioned health services. IoMT tools and services are rapidly changing healthcare operations for the better. Hopefully, it will continue to do so in this difficult time of the COVID-19 pandemic and will help to push the envelope of this work to a different extent.

Comparison of Chest X-rays findings in COVID-19 suspected and confirmed cases at a university teaching hospital: A retrospective comparative study.

OBJECTIVES: To compare Chest X-rays findings in COVID -19 suspected and confirmed patients on RT-PCR, presented at corona filtration center, Benazir Bhutto hospital Rawalpindi. METHODS: In this study, Chest radiographs of 100 COVID-19 RT-PCR positive confirmed patients were compared with 100 RT-PCR negative suspected COVID-19 patients screened at corona filtration center, Benazir Bhutto Hospital Rawalpindi from November 2020 to December 2020. Data on demographics, presenting complaints, co-morbid, lesion characteristic, distribution and attenuation, lobar involvement, pleural effusion and lymphadenopathy were collected. Associations between imaging characteristics and COVID-19 pneumonia were analyzed with univariate and multivariate logistic regression modals. RESULTS: Chest X-rays findings revealed bilateral lung consolidation with peripheral and diffuse distribution, involving middle and lower lobe to be statistically significant (p<0.05) between RT-PCR positives and negative patients. Peripheral distribution was associated with an 11.08-fold risk in COVID-19 positive patients than diffuse distribution. Middle lobe involvement had four folds risk and lower lobe involvement had 11.04 folds risk in COVID-19 cases as compared to upper lobe involvement. Consolidation had 2.6 folds risk in COVID-19 positive cases. CONCLUSIONS: Bilateral, peripheral distribution of middle and lower lobes ground glass haze or consolidation with no pleural effusion is significantly related to COVID-19 pneumonia. Overlapping imaging features of the infectious and non-infectious COVID mimickers can be further excluded by detailed clinical evaluation and further radiological workup.

Chest X-ray Findings and Hyponatremia in COVID-19 Pneumonia Patients.

BACKGROUND: The World Health Organization declared the coronavirus disease-2019 (COVID-19) a pandemic in December 2019. COVID-19 can affect most organs of the body but predominantly affects the lungs. Chest infection is associated with hyponatremia primarily due to inappropriate ectopic secretion of antidiuretic hormone. We conducted a six-month retrospective observational study to evaluate the relationship between chest X-ray (CXR) radiological findings and serum sodium levels. Our secondary goal was to assess the relationship between CXR findings and patient outcomes. AIM OF THE STUDY: To assess the relationship between the initial CXR findings, hyponatremia severity, and outcome in COVID-19 infected patients. MATERIALS AND METHODS: We conducted a retrospective review of CXR findings of COVID-19 patients aged > 18 years. The patients were healthy and had no history of hyponatremia before COVID-19 infection. All recruited patients were admitted to one of four hospitals in Qatar (Hazm Mebaireek General Hospital, Communicable Disease Center, and all affiliated quarantine centers managed under the Communicable Disease Centre, Mesaieed Hospital, and Ras Laffan Hospital) between March and June 2020. We excluded patients with factors that contributed to hyponatremia. Three score grades were established to describe the CXR findings. Patients were divided into three groups by the principal researcher according to their serum sodium levels. A radiologist evaluated the CXR findings with the patient and group information obscured. The principal researcher collected the X-ray scores for analysis with the serum sodium levels. We used SPSS for Windows, Version 15.0. (SPSS Inc., Chicago, IL, USA) and STATA Package Version 12.0 (StataCorp, College Station, TX, USA) to analyze the data. A p-value ≤  0.05 was considered significant. RESULTS: A total of 414 CXR patients with COVID-19 were recruited; 275 patients had hyponatremia and 139 had normal sodium levels and were used as the control group. Patients with normal serum sodium and hyponatremia were classified into three categories based on the CXR findings. Grade 0 (95), Grade 1 (43), and Grade 2 (137) hyponatremic patients were reported. The mean sodium levels were 133.6, 131.3, and 127.2 mmol/L for Grades 0, 1, and 2, respectively (p < 0.001). More than 95% of the patients who developed hyponatremia were >30 years. Moderate and severe hyponatremia was more prevalent in patients with Grade 1 or Grade 2 CXR findings and were >30 years. CONCLUSION: Serum sodium levels in COVID-19 patients correlated well with the severity of the CXR findings observed at the early disease stage. Furthermore, simple CXR scores can be used to identify COVID-19 patients at a higher risk of hyponatremia, length of hospital stay, medical care support type, and mortality.

Issues with implementing a high-quality lung cancer screening program.

After a comprehensive review of the evidence, the United States Preventive Services Task Force recently endorsed screening with low-dose computed tomography as an early detection approach that has the potential to significantly reduce deaths due to lung cancer. Prudent implementation of lung cancer screening as a high-quality preventive health service is a complex challenge. The clinical evaluation and management of high-risk cohorts in the absence of symptoms mandates an approach that differs significantly from that of symptom-detected lung cancer. As with other cancer screenings, it is essential to provide to informed at-risk individuals a safe, high-quality, cost-effective, and accessible service. In this review, the components of a successful screening program are discussed as we begin to disseminate lung cancer screening as a national resource to improve outcomes with this lethal cancer. This information about lung cancer screening will assist clinicians with communications about the potential benefits and harms of this service for high-risk individuals considering participation in the screening process.

Observational study of clinico-radiological follow-up of COVID-19 pneumonia: a district general hospital experience in the UK.

BACKGROUND: The British Thoracic Society (BTS) recommends that all patients admitted with COVID-19 pneumonia should have a chest X-ray (CXR) and clinical follow-up at 6 or 12 weeks, depending on the disease severity. Little data is available on long-term CXR follow-up for moderate and severe COVID-19 pneumonia. This study aims to evaluate compliance with clinico-radiological follow-up of patients recovering from COVID-19 pneumonia at a local hospital in the UK, as per the BTS guidance, and to analyse radiological changes at clinical follow-up at 12 weeks, in order to risk-stratify and improve patient outcomes. METHODS: This is a single-centre retrospective audit of 255 consecutive COVID-19 positive patients admitted to a local hospital in the UK over 5 months between May and October 2020. All CXRs and clinic follow-up at 12 ± 8 weeks were checked on an electronic database. RESULTS: Over one in two (131/255) patients had CXR evidence of COVID-19 pneumonia during the initial hospital admission. Half of the patients (60/131) died before CXR or clinic follow-up. Fifty-eight percent (41/71) of the surviving patients had a follow-up CXR, and only two developed respiratory complications- one had residual lung fibrosis, another a pulmonary embolism. Eighty-eight percent (36/41) of the patients had either resolution or improved radiological changes at follow-up. Most patients who had abnormal follow-up CXR were symptomatic (6/8), and many asymptomatic patients at follow-up had a normal CXR (10/12). CONCLUSIONS: Although there were concerns about interstitial lung disease (ILD) incidence in patients with COVID-19 pneumonia, most of our patients with COVID-19 pneumonia had no pulmonary complications at follow-up with CXR. This emphasises that CXR, a cost-effective investigation, can be used to risk-stratify patients for long term pulmonary complications following their COVID-19 pneumonia. However, we acknowledge the limitations of a low CXR and clinic follow-up rate in our cohort.

Determination of the value of albumin, anti-thrombin III, fibrinogen and D-dimer factors in the diagnosis of asymptomatic pulmonary embolism in patients with nephrotic syndrome.

BACKGROUND: Thromboembolism is one of the most important and dangerous complications of nephrotic syndrome. This study aimed to determine the value of albumin, anti-thrombin III, fibrinogen and D-dimer factors in the prediction of asymptomatic pulmonary embolism in patients with nephrotic syndrome in non-remission period. METHODS: Plasma levels of albumin, anti-thrombin III, fibrinogen and D-dimer were assessed in 30 nephrotic children in non-remission period (including new case-patient or relapse period), and the results were compared with chest X-ray and lung perfusion scintigraphy (Q scan). RESULTS: The mean age of patients was 6.22 ± 3.5 years (range 2-12 years). Of patients, 23.3% had abnormal findings in perfusion scan suggestive of pulmonary emboli despite absence of any respiratory manifestations. Median plasma albumin and anti-thrombin III levels in patients with asymptomatic pulmonary embolism were lower than in patients without pulmonary embolism. Also, median fibrinogen and D-dimer levels in patients with asymptomatic pulmonary embolism were higher than in patients without pulmonary embolism, with no statistically significant differences between sex, age, hemoglobin and hematocrit of patients and lung perfusion scan results. CONCLUSION: Patients with abnormal blood levels of albumin (< 3.5 g/dl), anti-thrombin III (< 80 ml/dl), fibrinogen (> 400 ml/dl) and D-dimer (> 0.5 µg/dl) underwent CXR/Q scan and were treated with heparin if there was pulmonary embolism.

MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients.

Various AI functionalities such as pattern recognition and prediction can effectively be used to diagnose (recognize) and predict coronavirus disease 2019 (COVID-19) infections and propose timely response (remedial action) to minimize the spread and impact of the virus. Motivated by this, an AI system based on deep meta learning has been proposed in this research to accelerate analysis of chest X-ray (CXR) images in automatic detection of COVID-19 cases. We present a synergistic approach to integrate contrastive learning with a fine-tuned pre-trained ConvNet encoder to capture unbiased feature representations and leverage a Siamese network for final classification of COVID-19 cases. We validate the effectiveness of our proposed model using two publicly available datasets comprising images from normal, COVID-19 and other pneumonia infected categories. Our model achieves 95.6% accuracy and AUC of 0.97 in diagnosing COVID-19 from CXR images even with a limited number of training samples.

Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays.

The COVID-19 outbreak continues to threaten the health and life of people worldwide. It is an immediate priority to develop and test a computer-aided detection (CAD) scheme based on deep learning (DL) to automatically localize and differentiate COVID-19 from community-acquired pneumonia (CAP) on chest X-rays. Therefore, this study aims to develop and test an efficient and accurate deep learning scheme that assists radiologists in automatically recognizing and localizing COVID-19. A retrospective chest X-ray image dataset was collected from open image data and the Xiangya Hospital, which was divided into a training group and a testing group. The proposed CAD framework is composed of two steps with DLs: the Discrimination-DL and the Localization-DL. The first DL was developed to extract lung features from chest X-ray radiographs for COVID-19 discrimination and trained using 3548 chest X-ray radiographs. The second DL was trained with 406-pixel patches and applied to the recognized X-ray radiographs to localize and assign them into the left lung, right lung or bipulmonary. X-ray radiographs of CAP and healthy controls were enrolled to evaluate the robustness of the model. Compared to the radiologists' discrimination and localization results, the accuracy of COVID-19 discrimination using the Discrimination-DL yielded 98.71%, while the accuracy of localization using the Localization-DL was 93.03%. This work represents the feasibility of using a novel deep learning-based CAD scheme to efficiently and accurately distinguish COVID-19 from CAP and detect localization with high accuracy and agreement with radiologists.

Identification and Localization of Endotracheal Tube on Chest Radiographs Using a Cascaded Convolutional Neural Network Approach.

Rapid and accurate assessment of endotracheal tube (ETT) location is essential in the intensive care unit (ICU) setting, where timely identification of a mispositioned support device may prevent significant patient morbidity and mortality. This study proposes a series of deep learning-based algorithms which together iteratively identify and localize the position of an ETT relative to the carina on chest radiographs. Using the open-source MIMIC Chest X-Ray (MIMIC-CXR) dataset, a total of 16,000 patients were identified (8000 patients with an ETT and 8000 patients without an ETT). Three different convolutional neural network (CNN) algorithms were created. First, a regression loss function CNN was trained to estimate the coordinate location of the carina, which was then used to crop the original radiograph to the distal trachea and proximal bronchi. Second, a classifier CNN was trained using the cropped inputs to determine the presence or absence of an ETT. Finally, for radiographs containing an ETT, a third regression CNN was trained to both refine the coordinate location of the carina and identify the location of the distal ETT tip. Model accuracy was assessed by comparing the absolute distance of prediction and ground-truth coordinates as well as CNN predictions relative to measurements documented in original radiologic reports. Upon five-fold cross validation, binary classification for the presence or absence of ETT demonstrated an accuracy, sensitivity, specificity, PPV, NPV, and AUC of 97.14%, 97.37%, 96.89%, 97.12%, 97.15%, and 99.58% respectively. CNN predicted coordinate location of the carina, and distal ETT tip was estimated within a median error of 0.46 cm and 0.60 cm from ground-truth annotations respectively. Overall final CNN assessment of distance between the carina and distal ETT tip was predicted within a median error of 0.60 cm from manual ground-truth annotations, and a median error of 0.66 cm from measurements documented in the original radiology reports. A serial cascaded CNN approach demonstrates high accuracy for both identification and localization of ETT tip and carina on chest radiographs. High performance of the proposed multi-step strategy is in part related to iterative refinement of coordinate localization as well as explicit image cropping which focuses algorithm attention to key anatomic regions of interest.

Deep Learning on Chest X-ray Images to Detect and Evaluate Pneumonia Cases at the Era of COVID-19.

Coronavirus disease 2019 (COVID-19) is an infectious disease with first symptoms similar to the flu. COVID-19 appeared first in China and very quickly spreads to the rest of the world, causing then the 2019-20 coronavirus pandemic. In many cases, this disease causes pneumonia. Since pulmonary infections can be observed through radiography images, this paper investigates deep learning methods for automatically analyzing query chest X-ray images with the hope to bring precision tools to health professionals towards screening the COVID-19 and diagnosing confirmed patients. In this context, training datasets, deep learning architectures and analysis strategies have been experimented from publicly open sets of chest X-ray images. Tailored deep learning models are proposed to detect pneumonia infection cases, notably viral cases. It is assumed that viral pneumonia cases detected during an epidemic COVID-19 context have a high probability to presume COVID-19 infections. Moreover, easy-to-apply health indicators are proposed for estimating infection status and predicting patient status from the detected pneumonia cases. Experimental results show possibilities of training deep learning models over publicly open sets of chest X-ray images towards screening viral pneumonia. Chest X-ray test images of COVID-19 infected patients are successfully diagnosed through detection models retained for their performances. The efficiency of proposed health indicators is highlighted through simulated scenarios of patients presenting infections and health problems by combining real and synthetic health data.