For Tuberculosis, Not "To Screen or Not to Screen?" but "Who?" and "How?"

Active case finding leveraging new molecular diagnostics and chest X-rays with automated interpretation algorithms is increasingly being developed for high-risk populations to drive down tuberculosis incidence. We consider why such an approach did not deliver a decline in tuberculosis prevalence in Brazilian prison populations and what to consider next.

Integrating Explainable Machine Learning in Clinical Decision Support Systems: Study Involving a Modified Design Thinking Approach

BACKGROUND

Though there has been considerable effort to implement machine learning (ML) methods for health care, clinical implementation has lagged. Incorporating explainable machine learning (XML) methods through the development of a decision support tool using a design thinking approach is expected to lead to greater uptake of such tools.

OBJECTIVE

This work aimed to explore how constant engagement of clinician end users can address the lack of adoption of ML tools in clinical contexts due to their lack of transparency and address challenges related to presenting explainability in a decision support interface.

METHODS

We used a design thinking approach augmented with additional theoretical frameworks to provide more robust approaches to different phases of design. In particular, in the problem definition phase, we incorporated the nonadoption, abandonment, scale-up, spread, and sustainability of technology in health care (NASSS) framework to assess these aspects in a health care network. This process helped focus on the development of a prognostic tool that predicted the likelihood of admission to an intensive care ward based on disease severity in chest x-ray images. In the ideate, prototype, and test phases, we incorporated a metric framework to assess physician trust in artificial intelligence (AI) tools. This allowed us to compare physicians' assessments of the domain representation, action ability, and consistency of the tool.

RESULTS

Physicians found the design of the prototype elegant, and domain appropriate representation of data was displayed in the tool. They appreciated the simplified explainability overlay, which only displayed the most predictive patches that cumulatively explained 90% of the final admission risk score. Finally, in terms of consistency, physicians unanimously appreciated the capacity to compare multiple x-ray images in the same view. They also appreciated the ability to toggle the explainability overlay so that both options made it easier for them to assess how consistently the tool was identifying elements of the x-ray image they felt would contribute to overall disease severity.

CONCLUSIONS

The adopted approach is situated in an evolving space concerned with incorporating XML or AI technologies into health care software. We addressed the alignment of AI as it relates to clinician trust, describing an approach to wire framing and prototyping, which incorporates the use of a theoretical framework for trust in the design process itself. Moreover, we proposed that alignment of AI is dependent upon integration of end users throughout the larger design process. Our work shows the importance and value of engaging end users prior to tool development. We believe that the described approach is a unique and valuable contribution that outlines a direction for ML experts, user experience designers, and clinician end users on how to collaborate in the creation of trustworthy and usable XML-based clinical decision support tools.

Chest X-ray Features of HIV-Associated Pneumocystis Pneumonia (PCP) in Adults: A Systematic Review and Meta-analysis

Background

The performance of chest x-ray (CXR) features for Pneumocystis pneumonia (PCP) diagnosis has been evaluated in small studies. We conducted a systematic review and meta-analysis to describe CXR changes in adults with HIV-associated laboratory-confirmed PCP, comparing these with non-PCP respiratory disease.

Methods

We searched databases for studies reporting CXR changes in people >15 years old with HIV and laboratory-confirmed PCP and those with non-PCP respiratory disease. CXR features were grouped using consensus terms. Proportions were pooled and odds ratios (ORs) generated using random-effects meta-analysis, with subgroup analyses by CD4 count, study period, radiology review method, and study region.

Results

Fifty-one studies (with 1821 PCP and 1052 non-PCP cases) were included. Interstitial infiltrate (59%; 95% CI, 52%-66%; 36 studies, n = 1380; I2 = 85%) and ground-glass opacification (48%; 95% CI, 15%-83%; 4 studies, n = 57; I2 = 86%) were common in PCP. Cystic lesions, central lymphadenopathy, and pneumothorax were infrequent. Pleural effusion was rare in PCP (0%; 95% CI, 0%-2%). Interstitial infiltrate (OR, 2.3; 95% CI, 1.4-3.9; I2 = 60%), interstitial-alveolar infiltrate (OR, 10.2; 95% CI, 3.2-32.4; I2 = 0%), and diffuse CXR changes (OR, 7.3; 95% CI, 2.7-20.2; I2 = 87%) were associated with PCP diagnosis. There was loss of association with alveolar infiltrate in African studies.

Conclusions

Diffuse CXR changes and interstitial-alveolar infiltrates indicate a higher likelihood of PCP. Pleural effusion, lymphadenopathy, and focal alveolar infiltrates suggest alternative causes. These findings could be incorporated into clinical algorithms to improve diagnosis of HIV-associated PCP.

Comparison of the Discrimination Performance of AI Scoring and the Brixia Score in Predicting COVID-19 Severity on Chest X-Ray Imaging: Diagnostic Accuracy Study

BACKGROUND

The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries.

OBJECTIVE

The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia.

METHODS

We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software.

RESULTS

The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95% CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95% CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95% CI 0.818-0.908).

CONCLUSIONS

The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings.

Pulmonary nodule detection in x-ray images by feature augmentation and context aggregation

Recent developments in x-ray image based pulmonary nodule detection have achieved remarkable results. However, existing methods are focused on transferring off-the-shelf coarse-grained classification models and fine-grained detection models rather than developing a dedicated framework optimized for nodule detection. In this paper, we propose PN-DetX, which as we know is the first dedicated pulmonary nodule detection framework. PN-DetX incorporates feature fusion and self-attention into x-ray based pulmonary nodule detection tasks, achieving improved detection performance. Specifically, PN-DetX adopts CSPDarknet backbone to extract features, and utilizes feature augmentation module to fuse features from different levels followed by context aggregation module to aggregate semantic information. To evaluate the efficacy of our method, we collect aLArge-scalePulmonaryNOduleDetection dataset,LAPNOD, comprising 2954 x-ray images along with expert-annotated ground truths. As we know, this is the first large-scale chest x-ray pulmonary nodule detection dataset. Experiments demonstrates that our method outperforms baseline by 3.8% mAP and 5.1%AP0.5. The generality of our approach is also evaluated on the publicly available dataset NODE21. We aspire for our method to serve as an inspiration for future research in the field of pulmonary nodule detection. The dataset and codes will be made in public.

Tuberculosis Chest X-Ray Image Retrieval System Using Deep Learning Based Biomarker Predictions

The world health organization's global tuberculosis (TB) report for 2022 identifies TB, with an estimated 1.6 million, as a leading cause of death. The number of new cases has risen since 2020, particularly the number of new drug-resistant cases, estimated at 450,000 in 2021. This is concerning, as treatment of patients with drug resistant TB is complex and may not always be successful. The NIAID TB Portals program is an international consortium with a primary focus on patient centric data collection and analysis for drug resistant TB. The data includes images, their associated radiological findings, clinical records, and socioeconomic information. This work describes a TB Portals' Chest X-ray based image retrieval system which enables precision medicine. An input image is used to retrieve similar images and the associated patient specific information, thus facilitating inspection of outcomes and treatment regimens from comparable patients. Image similarity is defined using clinically relevant biomarkers: gender, age, body mass index (BMI), and the percentage of lung affected per sextant. The biomarkers are predicted using variations of the DenseNet169 convolutional neural network. A multi-task approach is used to predict gender, age and BMI incorporating transfer learning from an initial training on the NIH Clinical Center CXR dataset to the TB portals dataset. The resulting gender AUC, age and BMI mean absolute errors were 0.9854, 4.03years and 1.67 k g m 2 . For the percentage of sextant affected by lesions the mean absolute errors ranged between 7% to 12% with higher error values in the middle and upper sextants which exhibit more variability than the lower sextants. The retrieval system is currently available from https://rap.tbportals.niaid.nih.gov/find_similar_cxr.

Technical Quality and Diagnostic Impact of Chest X-rays in Tuberculosis Screening: Insights From a Saudi Teleradiology Cohort

Objectives To assess the standard of chest X-ray techniques in tuberculosis (TB) screening within Saudi Arabian healthcare facilities and evaluate the impact of technical quality on radiological interpretation. Materials and methods Analysis of 250 posteroanterior chest radiographs sourced from a network of five clinics was conducted. These images were scrutinized for technical quality by a radiologist. Results Of the radiographs analyzed, 57% exhibited technical issues, with overexposure and clothing artifacts being the most commonly encountered. Notably, only 14% of these radiographs were deemed to have compromised diagnostic ability. Conclusion The presence of technical issues in most chest X-rays for TB screening highlights a significant area for improvement. However, the relatively low percentage of radiographs impacting diagnostic quality indicates that most issues do not critically hinder the radiologist's interpretative capability. This underscores the importance of balanced quality control measures in radiographic practices for effective TB detection in the region.

Explanatory deep learning to predict elevated pulmonary artery pressure in children with ventricular septal defects using standard chest x-rays: a novel approach

Objective

Early risk assessment of pulmonary arterial hypertension (PAH) in patients with congenital heart disease (CHD) is crucial to ensure timely treatment. We hypothesize that applying artificial intelligence (AI) to chest x-rays (CXRs) could identify the future risk of PAH in patients with ventricular septal defect (VSD).

Methods

A total of 831 VSD patients (161 PAH-VSD, 670 nonPAH-VSD) was retrospectively included. A residual neural networks (ResNet) was trained for classify VSD patients with different outcomes based on chest radiographs. The endpoint of this study was the occurrence of PAH in VSD children before or after surgery.

Results

In the validation set, the AI algorithm achieved an area under the curve (AUC) of 0.82. In an independent test set, the AI algorithm significantly outperformed human observers in terms of AUC (0.81 vs. 0.65). Class Activation Mapping (CAM) images demonstrated the model's attention focused on the pulmonary artery segment.

Conclusion

The preliminary findings of this study suggest that the application of artificial intelligence to chest x-rays in VSD patients can effectively identify the risk of PAH.

An Unusual Case of Severe Atelectasis: Mucus Impaction in a Young Obese Female

Atelectasis is defined as the the loss of lung volume due to collapse of lung tissue and is usually associated with symptoms of respiratory distress, including increased work of breathing and increased oxygen requirements. It is common in hospitalized patients with limited mobility and in patients with underlying lung conditions. Treatment is largely supportive when no underlying condition is identified. It is rare to occur in otherwise healthy individuals. The patient in this case presented to the emergency department with complaints of progressive shortness of breath, productive cough, chest tightness, subjective fever, chills, and nasal congestion for two weeks. Physical exam revealed decreased breath sounds on the left side, raising the suspicion for atelectasis or pneumothorax. Chest X-ray revealed complete white-out of the left lung. Bronchoscopy was performed and revealed mucus impaction in the left mainstem bronchus, which was removed. Repeat chest X-ray revealed resolution of atelectasis. The patient's symptoms improved, and she was discharged with outpatient pulmonary follow-up. The case described below illustrates that even in young patients with no underlying comorbidities, other than obesity, atelectasis as a cause of respiratory complaints should always be considered.

A deep transfer learning approach for COVID-19 detection and exploring a sense of belonging with Diabetes

COVID-19 is an epidemic disease that results in death and significantly affects the older adult and those afflicted with chronic medical conditions. Diabetes medication and high blood glucose levels are significant predictors of COVID-19-related death or disease severity. Diabetic individuals, particularly those with preexisting comorbidities or geriatric patients, are at a higher risk of COVID-19 infection, including hospitalization, ICU admission, and death, than those without Diabetes. Everyone's lives have been significantly changed due to the COVID-19 outbreak. Identifying patients infected with COVID-19 in a timely manner is critical to overcoming this challenge. The Real-Time Polymerase Chain Reaction (RT-PCR) diagnostic assay is currently the gold standard for COVID-19 detection. However, RT-PCR is a time-consuming and costly technique requiring a lab kit that is difficult to get in crises and epidemics. This work suggests the CIDICXR-Net50 model, a ResNet-50-based Transfer Learning (TL) method for COVID-19 detection via Chest X-ray (CXR) image classification. The presented model is developed by substituting the final ResNet-50 classifier layer with a new classification head. The model is trained on 3,923 chest X-ray images comprising a substantial dataset of 1,360 viral pneumonia, 1,363 normal, and 1,200 COVID-19 CXR images. The proposed model's performance is evaluated in contrast to the results of six other innovative pre-trained models. The proposed CIDICXR-Net50 model attained 99.11% accuracy on the provided dataset while maintaining 99.15% precision and recall. This study also explores potential relationships between COVID-19 and Diabetes.

Towards the establishment of national diagnostic reference levels for chest x-ray examinations in Sri Lanka: a multi-centric study

The establishment of diagnostic reference levels (DRLs) is an effective tool for optimising radiation doses delivered to patients during medical imaging procedures. This study aimed to compare the institutional DRLs (IDRLs) and propose a multi-centric diagnostic reference level (MCDRL) for chest x-ray examinations in adult patients in Sri Lanka. A prospective cross-sectional study was conducted with 1091 adult patients across six major tertiary care hospitals. Data on patient characteristics, such as age, sex, weight, and body mass index, and exposure parameters, such as tube voltage (kVp) and the product of tube current and exposure time (mAs), were collected. Patient doses were measured in terms of kerma-area product (PKA) using a PKAmeter mounted on the collimator of the x-ray tube. IDRLs were computed for each hospital according to the International Commission on Radiological Protection guidelines, and the 75th percentile PKAwas used to propose the MCDRL. The relationship between patient weight and exposure parameters was examined using Spearman's rank correlation to investigate the radiographic practice among hospitals. Results showed that IDRLs varied from 0.10 to 0.26 Gy cm2. The proposed MCDRL was 0.23 Gy cm2, substantially higher than the recently published DRLs from other countries. The median kVp ranged from 95 to 104, while mAs ranged from 2.5 to 5.6. Large variations in the PKAand exposure parameters were observed within and among hospitals. The elevated PKAvalues observed in this study were mostly due to the use of high mAs in clinical practice. The weak correlation observed between patient weight and exposure parameters suggests the need to standardise examination protocols concerning patient size. The observed dose variations demonstrate the need for the establishment of national DRLs. Until then, the proposed MCDRL can be considered as the benchmark dose level for chest x-ray examinations in Sri Lanka.

The development and validation of an artificial intelligence-based screening method for atrial septal defect in children's chest x-rays

Purpose

For precise diagnosis and effective management of atrial septal defects, it is of utmost significance to conduct elementary screenings on children. The primary aim of this study is to develop and authenticate an objective methodology for detecting atrial septal defects by employing deep learning (DL) on chest x-ray (CXR) examinations.

Methods

This retrospective study encompassed echocardiographs and corresponding Chest x-rays that were consistently gathered at Qingdao Women's and Children's Hospital from 2018 to 2022. Based on a collaborative diagnosis report by two cardiologists with over 10 years of experience in echocardiography, these radiographs were classified as positive or negative for atrial septal defect, and then divided into training and validation datasets. An artificial intelligence model was formulated by utilizing the training dataset and fine-tuned using the validation dataset. To evaluate the efficacy of the model, an assessment of the area under the curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value was conducted employing the validation dataset.

Results

This research encompassed a total of 420 images from individuals. The screening accuracy and recall rate of the model surpass 90%.

Conclusions

One of profound neural network models predicated on chest x-ray radiographs (a traditional, extensively employed, and economically viable examination) proves highly advantageous in the assessment for atrial septal defect.

From Pixels to Pathology: Employing Computer Vision to Decode Chest Diseases in Medical Images

Radiology has been a pioneer in the healthcare industry's digital transformation, incorporating digital imaging systems like picture archiving and communication system (PACS) and teleradiology over the past thirty years. This shift has reshaped radiology services, positioning the field at a crucial junction for potential evolution into an integrated diagnostic service through artificial intelligence and machine learning. These technologies offer advanced tools for radiology's transformation. The radiology community has advanced computer-aided diagnosis (CAD) tools using machine learning techniques, notably deep learning convolutional neural networks (CNNs), for medical image pattern recognition. However, the integration of CAD tools into clinical practice has been hindered by challenges in workflow integration, unclear business models, and limited clinical benefits, despite development dating back to the 1990s. This comprehensive review focuses on detecting chest-related diseases through techniques like chest X-rays (CXRs), magnetic resonance imaging (MRI), nuclear medicine, and computed tomography (CT) scans. It examines the utilization of computer-aided programs by researchers for disease detection, addressing key areas: the role of computer-aided programs in disease detection advancement, recent developments in MRI, CXR, radioactive tracers, and CT scans for chest disease identification, research gaps for more effective development, and the incorporation of machine learning programs into diagnostic tools.

Integration and evaluation of chest X-ray artificial intelligence in clinical practice

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.

The Effects of Various Teaching Methods on Chest X-ray Interpretation Skills Among Medical Students and Interns: A Systematic Review

Chest X-ray (CXR) is a common tool used in medical practice. Medical students and interns should acquire knowledge of CXR interpretation, as it is an essential diagnostic tool for a large spectrum of diseases. This systematic review aimed to compare the effect of different intervention techniques on the competency of medical students and interns to demonstrate the level of confidence and competence in interpreting common presentations of CXRs. The population, intervention, comparison, and outcomes (PICO) framework was used to formulate the review question. All related articles in five databases (PubMed, Web of Science, Scopus, Medline, and Embase) were retrieved and the search was completed in March 2023 with no limiters on date and time. The number of relevant studies was 469. A multi-level approach through the Rayyan platform was used for the screening and exclusion processes. Eleven articles were included in the systematic review consisting of eight randomized controlled trials, one quasi-experimental study, one cross-sectional study, and one interventional cohort. Results showed significant effects of teaching methods utilizing deductive or inductive approach, clinical history, patient care comfort survey, and SAFMEDS (Say-All-Fast-Minute-Every-Day-Shuffled). Contrarily, no significant effect was shown by flipped classroom models and mixed and blocked practice, peer-assisted learning vs. expert-assisted learning, and Chester, an artificial intelligence tool. This review identified beneficial approaches that may enhance the learning outcomes of interpreting CXRs for medical students and interns, highlighting the remarkable impact of SAFMEDS on medical students' ability to identify CXR findings as well as the availability and practicality of online and e-learning resources for students.

MTMC-AUR2CNet: Multi-textural multi-class attention recurrent residual convolutional neural network for COVID-19 classification using chest X-ray images

Coronavirus disease (COVID-19) has infected over 603 million confirmed cases as of September 2022, and its rapid spread has raised concerns worldwide. More than 6.4 million fatalities in confirmed patients have been reported. According to reports, the COVID-19 virus causes lung damage and rapidly mutates before the patient receives any diagnosis-specific medicine. Daily increasing COVID-19 cases and the limited number of diagnosis tool kits encourage the use of deep learning (DL) models to assist health care practitioners using chest X-ray (CXR) images. The CXR is a low radiation radiography tool available in hospitals to diagnose COVID-19 and combat this spread. We propose a Multi-Textural Multi-Class (MTMC) UNet-based Recurrent Residual Convolutional Neural Network (MTMC-UR2CNet) and MTMC-UR2CNet with attention mechanism (MTMC-AUR2CNet) for multi-class lung lobe segmentation of CXR images. The lung lobe segmentation output of MTMC-UR2CNet and MTMC-AUR2CNet are mapped individually with their input CXRs to generate the region of interest (ROI). The multi-textural features are extracted from the ROI of each proposed MTMC network. The extracted multi-textural features from ROI are fused and are trained to the Whale optimization algorithm (WOA) based DeepCNN classifier on classifying the CXR images into normal (healthy), COVID-19, viral pneumonia, and lung opacity. The experimental result shows that the MTMC-AUR2CNet has superior performance in multi-class lung lobe segmentation of CXR images with an accuracy of 99.47%, followed by MTMC-UR2CNet with an accuracy of 98.39%. Also, MTMC-AUR2CNet improves the multi-textural multi-class classification accuracy of the WOA-based DeepCNN classifier to 97.60% compared to MTMC-UR2CNet.

Evaluation of 2 Artificial Intelligence Software for Chest X-Ray Screening and Pulmonary Tuberculosis Diagnosis: Protocol for a Retrospective Case-Control Study

BACKGROUND

According to the World Bank, Malaysia reported an estimated 97 tuberculosis cases per 100,000 people in 2021. Chest x-ray (CXR) remains the best conventional method for the early detection of pulmonary tuberculosis (PTB) infection. The intervention of artificial intelligence (AI) in PTB diagnosis could efficiently aid human interpreters and reduce health professionals' work burden. To date, no AI studies have been evaluated in Malaysia.

OBJECTIVE

This study aims to evaluate the performance of Putralytica and Qure.ai software for CXR screening and PTB diagnosis among the Malaysian population.

METHODS

We will conduct a retrospective case-control study at the Respiratory Medicine Institute, National Cancer Institute, and Sungai Buloh Health Clinic. A total of 1500 CXR images of patients who completed treatments or check-ups will be selected and categorized into three groups: (1) abnormal PTB cases, (2) abnormal non-PTB cases, and (3) normal cases. These CXR images, along with their clinical findings, will be the reference standard in this study. All patient data, including sociodemographic characteristics and clinical history, will be collected prior to screening via Putralytica and Qure.ai software and readers' interpretation, which are the index tests for this study. Interpretation from all 3 index tests will be compared with the reference standard, and significant statistical analysis will be computed.

RESULTS

Data collection is expected to commence in August 2023. It is anticipated that 1 year will be needed to conduct the study.

CONCLUSIONS

This study will measure the accuracy of Putralytica and Qure.ai software and whether their findings will concur with readers' interpretation and the reference standard, thus providing evidence toward the effectiveness of implementing AI in the medical setting.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/36121.

Deep learning approach for analyzing chest x-rays to predict cardiac events in heart failure

Background

A deep learning (DL) model based on a chest x-ray was reported to predict elevated pulmonary artery wedge pressure (PAWP) as heart failure (HF).

Objectives

The aim of this study was to (1) investigate the role of probability of elevated PAWP for the prediction of clinical outcomes in association with other parameters, and (2) to evaluate whether probability of elevated PAWP based on DL added prognostic information to other conventional clinical prognostic factors in HF.

Methods

We evaluated 192 patients hospitalized with HF. We used a previously developed AI model to predict HF and calculated probability of elevated PAWP. Readmission following HF and cardiac mortality were the primary endpoints.

Results

Probability of elevated PAWP was associated with diastolic function by echocardiography. During a median follow-up period of 58 months, 57 individuals either died or were readmitted. Probability of elevated PAWP appeared to be associated with worse clinical outcomes. After adjustment for readmission score and laboratory data in a Cox proportional-hazards model, probability of elevated PAWP at pre-discharge was associated with event free survival, independent of elevated left atrial pressure (LAP) based on echocardiographic guidelines (p < 0.001). In sequential Cox models, a model based on clinical data was improved by elevated LAP (p = 0.005), and increased further by probability of elevated PAWP (p < 0.001). In contrast, the addition of pulmonary congestion interpreted by a doctor did not statistically improve the ability of a model containing clinical variables (compared p = 0.086).

Conclusions

This study showed the potential of using a DL model on a chest x-ray to predict PAWP and its ability to add prognostic information to other conventional clinical prognostic factors in HF. The results may help to enhance the accuracy of prediction models used to evaluate the risk of clinical outcomes in HF, potentially resulting in more informed clinical decision-making and better care for patients.

Development of lung segmentation method in x-ray images of children based on TransResUNet

Background

Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems.

Objective

In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images.

Methods

The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation.

Results

Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.

Conclusions

This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.

Acute Recreational Cannabis-Induced Hypersensitivity Pneumonitis: A Case Report

Hypersensitivity pneumonitis (HP) is a lung disease in which foreign matter is inhaled and exposed to lung parenchymal and interstitial tissue. Such matter may include pollen, molds, chemicals, and smoke. HP leads to widespread inflammation and even fibrosis in chronic forms; the main route of treatment usually involves corticosteroids and antifibrotics as needed. We describe a patient case in which HP was diagnosed after using recreational marijuana, and her chest x-ray had a complete resolution after one day of a corticosteroid regimen. As recreational marijuana use increases, clinicians need to keep HP on the differential diagnosis in patients that frequently utilize recreational marijuana obtained through illicit business.

Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays

Before the recent success of deep learning methods for automated medical image analysis, practitioners used handcrafted radiomic features to quantitatively describe local patches of medical images. However, extracting discriminative radiomic features relies on accurate pathology localization, which is difficult to acquire in real-world settings. Despite advances in disease classification and localization from chest X-rays, many approaches fail to incorporate clinically-informed domainspecific radiomic features. For these reasons, we propose a Radiomics-Guided Transformer (RGT) that fuses global image information with local radiomics-guided auxiliary information to provide accurate cardiopulmonary pathology localization and classification without any bounding box annotations. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomics information. Using the learned self-attention of its image branch, RGT extracts a bounding box for which to compute radiomic features, which are further processed by the radiomics branch; learned image and radiomic features are then fused and mutually interact via cross-attention layers. Thus, RGT utilizes a novel end-to-end feedback loop that can bootstrap accurate pathology localization only using image-level disease labels. Experiments on the NIH ChestXRay dataset demonstrate that RGT outperforms prior works in weakly supervised disease localization (by an average margin of 3.6% over various intersection-over-union thresholds) and classification (by 1.1% in average area under the receiver operating characteristic curve). We publicly release our codes and pre-trained models at https://github.com/VITAGroup/chext.

CoVSeverity-Net: an efficient deep learning model for COVID-19 severity estimation from Chest X-Ray images

Purpose

COVID-19 is not going anywhere and is slowly becoming a part of our life. The World Health Organization declared it a pandemic in 2020, and it has affected all of us in many ways. Several deep learning techniques have been developed to detect COVID-19 from Chest X-Ray images. COVID-19 infection severity scoring can aid in establishing the optimum course of treatment and care for a positive patient, as all COVID-19 positive patients do not require special medical attention. Still, very few works are reported to estimate the severity of the disease from the Chest X-Ray images. The unavailability of the large-scale dataset might be a reason.

Methods

We aim to propose CoVSeverity-Net, a deep learning-based architecture for predicting the severity of COVID-19 from Chest X-ray images. CoVSeverity-Net is trained on a public COVID-19 dataset, curated by experienced radiologists for severity estimation. For that, a large publicly available dataset is collected and divided into three levels of severity, namely Mild, Moderate, and Severe.

Results

An accuracy of 85.71% is reported. Conducting 5-fold cross-validation, we have obtained an accuracy of 87.82 ± 6.25%. Similarly, conducting 10-fold cross-validation we obtained accuracy of 91.26 ± 3.42. The results were better when compared with other state-of-the-art architectures.

Conclusion

We strongly believe that this study has a high chance of reducing the workload of overworked front-line radiologists, speeding up patient diagnosis and treatment, and easing pandemic control. Future work would be to train a novel deep learning-based architecture on a larger dataset for severity estimation.

Chest x-ray feature of venous air embolism in orthopedic surgery in prone position: A case report

Background

Venous air embolism (VAE) is a life-threatening event characterized as a series of clinical features of the disease caused by gas entering the venous circulation in the body.

Case presentation

A 72-year-old male patient with an ankle fracture after trauma was admitted, and complained of chest pain and dyspnea after the ankle fracture resection and internal fixation. His heart rate and blood pressure dropped, and the patient was diagnosed with VAE according to a chest x-ray and clinical features. Cardiopulmonary resuscitation was carried out and the patient's heartbeat recovered; his blood pressure rose to a normal level. The patient was still unconscious and sent to the intensive care unit for continued monitoring and treatment. Unfortunately, the patient discharged himself from the hospital and died 24 h later.

Conclusion

This case suggests that x-ray may be a potential method for the rapid diagnosis of VAE in a resource-limited setting.

The deep learning algorithm estimates chest radiograph-based sex and age as independent risk factors for future cardiovascular outcomes

Objectives

Chest X-rays (CXRs) convey much illegible physiological information that deep learning model (DLM) has been reported interpreting successfully. Since the electrocardiogram age established by DLM was revealed as a heart biological marker, we hypothesize that CXR age has similar potential to describe the heart and lung states. Therefore, we developed a DLM to predict sex and age through CXR and analyzed its relation with future cardiovascular diseases (CVD).

Methods

A total of 90,396 CXRs aged 20 to 90 were collected and separated into a development set with 53,102 CXRs and demographic information pairs, a tuning set with 7073 pairs, an internal validation set with 17,364 pairs, and an external validation set with 12,857 pairs. The study trained DLM with development set for estimating age and sex and compared them to actual information.

Results

The mean absolute errors of predicted age were 4.803 and 4.313 years in the internal and external validation sets, respectively. The area under the curve of sex analysis was 0.9993 and 0.9988 in the internal and external validation sets, respectively. Patients whose CXR age was 5 years older than chronologic age lead to higher risk of all-cause mortality (hazard ratio (HR): 2.42, 95% confidence interval (CI): 2.00-2.92), cardiovascular (CV)-cause mortality (HR: 7.57, 95% CI: 4.55-12.60), new-onset heart failure (HR: 2.07, 95% CI: 1.56-2.76), new-onset chronic kidney disease (HR: 1.73, 95% CI: 1.46-2.05), new-onset acute myocardial infarction (HR: 1.80, 95% CI: 1.12-2.92), new-onset stroke (HR: 1.45, 95% CI: 1.10-1.90), new-onset coronary artery disease (HR: 1.26, 95% CI: 1.04-1.52), and new-onset atrial fibrillation (HR: 1.43, 95% CI: 1.01-2.02).

Conclusions

Using DLM to predict CXR age provided additional information for future CVDs. Older CXR age is an accessible risk classification tool for clinician use.

Centralized contrastive loss with weakly supervised progressive feature extraction for fine-grained common thorax disease retrieval in chest x-ray

BACKGROUND

Medical images have already become an essential tool for the diagnosis of many diseases. Thus a large number of medical images are being generated due to the daily routine inspection. An efficient image-based disease retrieval system will not only make full use of existing data, but also help physicians to prognosis the diseases. Medical image retrieval is represented by the classification and localization of common thorax diseases in x-ray images. Although extensive efforts have been put into this field, there are still many challenges.

PURPOSE

Most of the existing fine-grained image research methods just apply existing deep learning frameworks in extracting the image features. However, these high-level features mainly focus on the global representations of the object, rather than simultaneously considering the local ones. It requires fine-grained details to classify the images with similar lesion areas. Thus, it is necessary to combine the global features and local ones to make the features more discriminative. On the other hand, training CNN models based on current existing strategies have a high time complexity, and is hard to get the discriminative features mentioned above. In addition, the visual retrieval method of fine-grained medical images still has the problem of insufficient sample data with accurate annotation information.

METHODS

To address above challenges, we introduced a novel fine-grained medical images retrieval method. First, a centralized contrastive loss (CCLoss) is proposed as our metric learning loss function. Parameters are updated by using the center point, which not only improves the distinguishing performance of features, but also effectively reduces the time complexity of the algorithm. In addition, a weakly supervised progressive feature extraction method is proposed to gradually extract the combined features. And the attention mechanism module is applied to screen the target information after the initial positioning for fine refinement, so as to separate the features with a high degree of discrimination. The retrieval of 14 different chest diseases is evaluated on the chest x-ray datasets.

RESULTS

Compared with the existing research methods, the proposed method shows a better retrieval result for Recall@8 by 2.26 % ∼ 4.6 % $\%{\sim }4.6\%$ and achieves a very efficient training speed which is 100 times faster than the pair-wise loss-based training strategy. We also assessed the effects of Recall@k (k = 2, 4, 6, 8) for progressive features extracted from different steps to obtain a model with the best retrieval performance.

CONCLUSIONS

The proposed model is capable of learning discriminative representations from chest x-ray datasets, and it achieves better performance compared with other state-of-the-art methods. Therefore, the developed model would be useful in the diagnosis of common thorax disease or unknown chest disease.

Comparison of pre-trained deep learning model classification performance of COVID-19 and normal chest X-ray images

Introduction

The aim of this study was to compare the accuracy and performance of 12 pre-trained deep learning models for classifying covid-19 and normal chest X-ray images from Kaggle.

Materials

a desktop computer with an Intel CPU i9-10900 2.80GHz and NVIDIA GPU GeForce RTX2070 SUPER, Anaconda3 software with 12 pre-trained models including VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, RestNet50V2, RestNet101V2, RestNet152V2, InceptionRestnetV2, InceptionV3, XceptionV1 and MobileNetV2, covid-19 and normal chest X-ray from Kaggle website.

Methods

the images were divided into three sets of train, test, and validation sets using a ratio of 70:20:10, respectively. The performance was recorded for each pre-train model with hyperparameters of epoch, batch size, and learning rate as 16, 16 and 0.0001 respectively. The prediction results of each model were recorded and compared.

Results

from the results of all 12 pre-trained deep learning model, five models that have highest validation accuracy were DenseNet169, DenseNet201, InceptionV3, DenseNet121 and InceptionRestNetV2, respectively.

Conclusion

The top-5 highest accuracy models for classifying the COVID-19 were DenseNet169, DenseNet201, InceptionV3, DenseNet121 and InceptionRestnetV2 with accuracies of 95.4%, 95.07%, 94.73%, 94.51% and 93.61% respectively.

Early-stage lung cancer associated with higher frequency of chest x-ray up to three years prior to diagnosis

OBJECTIVES

Symptom awareness campaigns have contributed to improved early detection of lung cancer. Previous research suggests that this may have been achieved partly by diagnosing lung cancer in those who were not experiencing symptoms of their cancer. This study aimed to explore the relationship between frequency of chest x-ray in the three years prior to diagnosis and stage at diagnosis.

SETTINGS

Lung cancer service in a UK teaching hospital.

PARTICIPANTS

Patients diagnosed with lung cancer between 2010 and 2013 were identified. The number of chest x-rays for each patient in the three years prior to diagnosis was recorded. Statistical analysis of chest x-ray frequency comparing patients with early- and late-stage disease was performed.

RESULTS

One-thousand seven-hundred fifty patients were included - 589 (33.7%) with stage I/II and 1,161 (66.3%) with stage III/IV disease. All patients had at least one chest x-ray in the six months prior to diagnosis. Those with early-stage disease had more chest x-rays in this period (1.32 vs 1.15 radiographs per patient, P = 0.009). In the period 36 months to six months prior to lung cancer diagnosis, this disparity was even greater (1.70 vs 0.92, radiographs per patient, P < 0.001).

CONCLUSIONS

Increased rates of chest x-ray are likely to contribute to earlier detection. Given the known symptom lead time many patients diagnosed through chest x-ray may not have been experiencing symptoms caused by their cancer. The number of chest x-rays performed could reflect patient and/or clinician behaviours in response to symptoms.

Deep viewing for the identification of Covid-19 infection status from chest X-Ray image using CNN based architecture

In recent years, coronavirus (Covid-19) has evolved into one of the world’s leading life-threatening severe viral illnesses. A self-executing accord system might be a better option to stop Covid-19 from spreading due to its quick diagnostic option. Many researches have already investigated various deep learning techniques, which have a significant impact on the quick and precise early detection of Covid-19. Most of the existing techniques, though, have not been trained and tested using a significant amount of data. In this paper, we purpose a deep learning technique enabled Convolutional Neural Network (CNN) to automatically diagnose Covid-19 from chest x-rays. To train and test our model, 10,293 x-rays, including 2875 x-rays of Covid-19, were collected as a data set. The applied dataset consists of three groups of chest x-rays: Covid-19, pneumonia, and normal patients. The proposed approach achieved 98.5% accuracy, 98.9% specificity, 99.2% sensitivity, 99.2% precision, and 98.3% F1-score. Distinguishing Covid-19 patients from pneumonia patients using chest x-ray, particularly for human eyes is crucial since both diseases have nearly identical characteristics. To address this issue, we have categorized Covid-19 and pneumonia using x-rays, achieving a 99.60% accuracy rate. Our findings show that the proposed model might aid clinicians and researchers in rapidly detecting Covid-19 patients, hence facilitating the treatment of Covid-19 patients.

The Diagnostic Accuracy of Chest Radiographic Features for Pediatric Intrathoracic Tuberculosis

INTRODUCTION

The chest radiograph (CR) remains a key tool in the diagnosis of pediatric tuberculosis (TB). In children with presumptive intrathoracic TB, we aimed to identify CR features that had high specificity for, and were strongly associated with, bacteriologically confirmed TB.

METHODS

We analyzed CR data from children with presumptive intrathoracic TB prospectively enrolled in a cohort study in a high-TB burden setting and who were classified using standard clinical case definitions as "confirmed," "unconfirmed," or "unlikely" TB. We report the CR features and inter-reader agreement between expert readers who interpreted the CRs. We calculated the sensitivity and specificity of the CR features with at least moderate inter-reader agreement and analyzed the relationship between these CR 
features and the classification of TB in a multivariable regression model.

RESULTS

Of features with at least moderate inter-reader agreement, enlargement of perihilar and/or paratracheal lymph nodes, bronchial deviation/compression, cavities, expansile pneumonia, and pleural effusion had a specificity of > 90% for confirmed TB, compared with unlikely TB. Enlargement of perihilar (adjusted odds ratio [aOR]: 6.6; 95% confidence interval [CI], 3.80-11.72) and/or paratracheal lymph nodes (aOR: 5.14; 95% CI, 2.25-12.58), bronchial deviation/compression (aOR: 6.22; 95% CI, 2.70-15.69), pleural effusion (aOR: 2.27; 95% CI, 1.04-4.78), and cavities (aOR: 7.45; 95% CI, 3.38-17.45) were associated with confirmed TB in the multivariate regression model, whereas alveolar opacification (aOR: 1.16; 95% CI, .76-1.77) and expansile pneumonia (aOR: 4.16; 95% CI, .93-22.34) were not.

CONCLUSIONS

In children investigated for intrathoracic TB enlargement of perihilar or paratracheal lymph nodes, bronchial compression/deviation, pleural effusion, or cavities on CR strongly support the diagnosis.

Ultra-low dose computed tomography of the chest in an emergency setting: A prospective agreement study

Ultra-low dose computed tomography (ULD-CT) assessed by non-radiologists in a medical Emergency Department (ED) has not been examined in previous studies. To (i) investigate intragroup agreement among attending physicians caring for ED patients (i.e., radiologists, senior- and junior clinicians) and medical students for the detection of acute lung conditions on ULD-CT and supine chest X-ray (sCXR), and (ii) evaluate the accuracy of interpretation compared to the reference standard. In this prospective study, non-traumatic patients presenting to the ED, who received an sCXR were included. Between February and July 2019, 91 patients who underwent 93 consecutive examinations were enrolled. Subsequently, a ULD-CT and non-contrast CT were performed. The ULD-CT and sCXR were assessed by 3 radiologists, 3 senior clinicians, 3 junior clinicians, and 3 medical students for pneumonia, pneumothorax, pleural effusion, and pulmonary edema. The non-contrast CT, assessed by a chest radiologist, was used as the reference standard. The results of the assessments were compared within each group (intragroup agreement) and with the reference standard (accuracy) using kappa statistics. Accuracy and intragroup agreement improved for pneumothorax on ULD-CT compared with the sCXR for all groups. Accuracy and intragroup agreement improved for pneumonia on ULD-CT when assessed by radiologists and for pleural effusion when assessed by medical students. In patients with acute lung conditions ULD-CT offers improvement in the detection of pneumonia by radiologists and the detection of pneumothorax by radiologists as well as non-radiologists compared to sCXR. Therefore, ULD-CT may be considered as an alternative first-line imaging modality to sCXR for non-traumatic patients who present to EDs.

ImageGCN: Multi-Relational Image Graph Convolutional Networks for Disease Identification With Chest X-Rays

Image representation is a fundamental task in computer vision. However, most of the existing approaches for image representation ignore the relations between images and consider each input image independently. Intuitively, relations between images can help to understand the images and maintain model consistency over related images, leading to better explainability. In this paper, we consider modeling the image-level relations to generate more informative image representations, and propose ImageGCN, an end-to-end graph convolutional network framework for inductive multi-relational image modeling. We apply ImageGCN to chest X-ray images where rich relational information is available for disease identification. Unlike previous image representation models, ImageGCN learns the representation of an image using both its original pixel features and its relationship with other images. Besides learning informative representations for images, ImageGCN can also be used for object detection in a weakly supervised manner. The experimental results on 3 open-source x-ray datasets, ChestX-ray14, CheXpert and MIMIC-CXR demonstrate that ImageGCN can outperform respective baselines in both disease identification and localization tasks and can achieve comparable and often better results than the state-of-the-art methods.

Chest Radiograph Severity and Its Association With Outcomes in Subjects With COVID-19 Presenting to the Emergency Department

BACKGROUND

Severity of radiographic abnormalities on chest radiograph in subjects with COVID-19 has been shown to be associated with worse outcomes, but studies are limited by different scoring systems, sample size, subject age, and study duration. Data regarding the longitudinal evolution of radiographic abnormalities and its association with outcomes are scarce. We sought to evaluate these questions using a well-validated scoring system (the Radiographic Assessment of Lung Edema [RALE] score) using data over 6 months from a large, multihospital health care system.

METHODS

We collected clinical and demographic data and quantified radiographic edema on chest radiograph obtained in the emergency department (ED) as well as on days 1-2 and 3-5 (in those admitted) in subjects with a nasopharyngeal swab positive for SARS-CoV-2 by polymerase chain reaction (PCR) visiting the ED for coronavirus disease 2019 (COVID)-19-related complaints between March-September 2020. We examined the association of baseline and longitudinal evolution of radiographic edema with severity of hypoxemia and clinical outcomes.

RESULTS

Eight hundred and seventy subjects were included (median age 53.6; 50.8% female). Inter-rate agreement for RALE scores was excellent (interclass correlation coefficient 0.84 [95% CI 0.82-0.87], P < .001). RALE scores correlated with hypoxemia as quantified by S_pO2 /F_IO2 (r = -0.42, P < .001). Admitted subjects had higher RALE scores than those discharged (6 [2-11] vs 0 [0-3], P < .001). An increase of RALE score ≥ 4 was associated with worse 30-d survival (P = .006). Larger increases in the RALE score were associated with worse survival.

CONCLUSIONS

The RALE score was reproducible and easily implementable in adult subjects presenting to the ED with COVID-19. Its association with physiologic parameters and outcomes at baseline and longitudinally makes it a readily available tool for prognostication and early ICU triage, particularly in patients with worsening radiographic edema.

Tuberculosis Screening via Chest X-Ray is Financially Burdensome in Previously Independently Living Elective Total Knee Arthroplasty Patients

BACKGROUND

In 1995, to reduce the transmission of Tuberculosis (TB) the Centers for Disease Control and Prevention recommended that all patients discharged from hospitals be required to have chest x-rays (i.e., radiography) performed before admission to long term care facilities (LTCFs). Previously independently living patients (PILPs) who undergo elective total knee replacement (TKA) surgery are a population at higher risk to end up in LTCFs for rehabilitation. By 2017, the incidence of TB was 9,105 cases compared to 22,762 in 1995. However, the recommendations that hospitals be required to perform a chest x-ray in all patients (including PILPs) being transferred to LTCF's have remained in place. The purposes of this study were to: a) determine the incidence of TB-positive chest x-rays in PILPS discharged to LTCFs after undergoing elective TKA surgery, and b) assess the cost (i.e., both financial and possible exposure to unnecessary radiation) of mandated chest x-rays before hospital discharge to LTCF for PILPs.

METHODS

Retrospective 2012-2017 patient chart data were collected from the Michigan Arthroplasty Registry Collaborative Quality Initiative (MARCQI) to identify all elective TKAs for PILPs performed at two Ascension participating centers. Study data included sex, age, body mass index (BMI), length of stay, comorbidities, and chest x-ray results before discharge. Patients who underwent surgery for fracture, infection, trauma, or malignancy were excluded from the study. Categorical data were analyzed using Fisher's exact test and Student's t-test were used for continuous data.

RESULTS

The authors identified 4,041 total elective TKA's, from which 500 PILPs were discharged to a LTCF due to functional, medical and/or social concerns. Chest x-rays were associated with 500 (100%) negative findings for TB. Overall hospital costs for chest x-rays for patient's being discharged to an extended care facility totaled $90,848.

CONCLUSIONS

The mandated use of chest x-rays for TB screening of PILPs undergoing elective surgery TKA prior to discharge to LTCFs appear to place an unnecessary financial burden on the healthcare system. The mandatory use of x-rays for assessment of possible TB infection before transfer to LTCFs appears to also expose PILPs unnecessarily to radiation. Although further studies are needed to verify these results, the authors recommend that perhaps instead chest x-rays should be reserved for patients with specific comorbidities (e.g., patients on immunosuppressive therapy, with HIV, etc.) or for those patients residing in LTCFs prior to surgery.

Probiotic improves symptomatic and viral clearance in Covid19 outpatients: a randomized, quadruple-blinded, placebo-controlled trial

Intestinal bacteria may influence lung homeostasis via the gut-lung axis. We conducted a single-center, quadruple-blinded, randomized trial in adult symptomatic Coronavirus Disease 2019 (Covid19) outpatients. Subjects were allocated 1:1 to probiotic formula (strains Lactiplantibacillus plantarum KABP022, KABP023, and KAPB033, plus strain Pediococcus acidilactici KABP021, totaling 2 × 109 colony-forming units (CFU)) or placebo, for 30 days. Co-primary endpoints included: i) proportion of patients in complete symptomatic and viral remission; ii) proportion progressing to moderate or severe disease with hospitalization, or death; and iii) days on Intensive Care Unit (ICU). Three hundred subjects were randomized (median age 37.0 years [range 18 to 60], 161 [53.7%] women, 126 [42.0%] having known metabolic risk factors), and 293 completed the study (97.7%). Complete remission was achieved by 78 of 147 (53.1%) in probiotic group compared to 41 of 146 (28.1%) in placebo (RR: 1.89 [95 CI 1.40-2.55]; P < .001), significant after multiplicity correction. No hospitalizations or deaths occurred during the study, precluding the assessment of remaining co-primary outcomes. Probiotic supplementation was well-tolerated and reduced nasopharyngeal viral load, lung infiltrates and duration of both digestive and non-digestive symptoms, compared to placebo. No significant compositional changes were detected in fecal microbiota between probiotic and placebo, but probiotic supplementation significantly increased specific IgM and IgG against Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV2) compared to placebo. It is thus hypothesized this probiotic primarily acts by interacting with the host's immune system rather than changing colonic microbiota composition. Future studies should replicate these findings and elucidate its mechanism of action (Registration: NCT04517422).Abbreviations: AE: Adverse Event; BMI: Body Mass Index; CONSORT: CONsolidated Standards of Reporting Trials; CFU: Colony-Forming Units; eDRF: Electronic Daily Report Form; GLA: Gut-Lung Axis; GSRS: Gastrointestinal Symptoms Rating Scale; hsCRP: High-sensitivity C-Reactive Protein; HR: Hazard Ratio; ICU: Intensive Care Unit; OR: Odds Ratio; PCoA: Principal Coordinate Analysis; RR: Relative Risk; RT-qPCR: Real-Time Quantitative Polymerase Chain Reaction; SARS-CoV2: Severe acute respiratory syndrome coronavirus 2; SpO2: Peripheral Oxygen Saturation; WHO: World Health Organization.

Delayed Diagnosis of an Atypical Pneumonia Resembling a Solitary Pulmonary Nodule

Atypical pneumonia shows clinical features that are different from those of typical pneumonia, and it can mimic other entities. We report the case of a 42-year-old male with a solitary pulmonary nodule found in an X-ray for a preoperative evaluation. Our patient was asymptomatic, and a pulmonary neoplasm was the first diagnostic suspicion. The round-shaped nodule seen in the X-ray turned out to be a linear ground glass opacity in a thoracic CT scan. Viral pneumonia due to SARS-CoV-2 was diagnosed. We emphasize here the educational value of this case report. We do not report a new radiological finding because lung nodules resembling neoplasms have already been reported in the medical literature. However, some clinical features of COVID-19 are relatively new and can mimic other entities, and the results of some investigations and clinicians' interpretations of them can be misleading. Atypical radiological findings make it necessary to widen the spectrum of alternative diagnoses.

AFCM-LSMA: New intelligent model based on Lévy slime mould algorithm and adaptive fuzzy C-means for identification of COVID-19 infection from chest X-ray images

Problem

A worldwide challenge is to provide medical resources required for COVID-19 detection. They must be effective tools for fast detection and diagnose of the virus using a large number of tests; besides, they should be low-cost developments. While a chest X-ray scan is a powerful candidate tool, if several tests are carried out, the images produced by the devices must be interpreted accurately and rapidly. COVID-19 induces longitudinal pulmonary parenchymal ground-glass and consolidates pulmonary opacity, in some cases with rounded morphology and peripheral lung distribution, which is very difficult to predict in an early stage.

Aim

In this paper, we aim to develop a robust model to extract high-level features of COVID-19 from chest X-ray (CXR) images to help in rapid diagnosis. In specific, this paper proposes an optimization model for COVID-19 diagnosis based on adaptive Fuzzy C-means (AFCM) and improved Slime Mould Algorithm (SMA) based on Lévy distribution, namely AFCM-LSMA.

Methods

The SMA optimizer is proposed to adapt weights in oscillation mode and to mimic the process of generating positive and negative feedback from the propagation wave to shape the optimum path for food connectivity. Lévy motion is used as a permutation to perform a local search and to adapt SMA optimizer (LSMA) by generating several solutions that are apart from current candidates. Furthermore, it permits the optimizer to escape from local minima, examine large search areas and reach optimal solutions in fewer iterations with high convergence speed. The FCM algorithm is used to segment pulmonary regions from CXR images and is adapted to reduce time and amount of computations using histogram of the image intensities during the clustering process.

Results

The performance of the proposed AFCM-LSMA has been validated on CXR images and compared with different conventional machine learning and deep learning techniques, meta-heuristics methods, and different chaotic maps. The accuracies achieved by the proposed model are around (ACC = 0.96, RMSE = 0.23, Prec. = 0.98, F1_score = 0.98, MCC = 0.79, and Kappa = 0.79).

Conclusion

The experimental findings indicate that the proposed new method outperforms all other methods, which will be beneficial to the clinical practitioner for the early identification of infected COVID-19 patients.

Long-Term X-ray Findings in Patients With Coronavirus Disease-2019

INTRODUCTION

Reverse transcription-polymerase chain reaction (RT-PCR) and chest X-ray (CXR) are commonly used techniques for diagnosing and assessing prognosis in patients with coronavirus disease-2019 (COVID-19). This study aims to highlight the long-term radiological findings observed on CXR after recovery, in patients with COVID-19. This will help identify patients suffering from long-term consequences of COVID-19 and help them provide adequate care.

METHODS

This study was conducted in the COVID-19 unit of a tertiary care hospital, Pakistan from August 2020 to February 2021. CXR of patients who were being discharged after negative PCR was done. Participants with positive X-ray findings, which included consolidation, reticular thickening, ground-glass opacities (GGO), pulmonary nodules, and pleural effusions, were enrolled in the study after getting informed consent. All findings were recorded in a self-structured questionnaire. Participants were scheduled to come for follow-up on day 30 after their initial CXR, where their CXR was repeated.

RESULT

Our results showed that n=429 (60.2%) participants had positive CXR at the time of discharge. After 30 days, n=371 participants returned for a follow-up X-ray. Out of the 371 participants, after 30 days, 123 participants still had positive CXR. Fatigue (41.4%) was the common symptom after 30 days. The most common finding was consolidation (82.1%), followed by reticular thickening (23.5%) on day 30.

CONCLUSION

In this study, although most of the patients completely recovered serologically from COVID-19, they still had radiological findings in their chest X-rays. Radiological findings are especially important in predicting the clinical course of the disease and may be used to monitor long-term complications.

Estimating lung cancer risk from chest X-ray and symptoms: a prospective cohort study

Background

Chest X-ray (CXR) is the first-line investigation for lung cancer in many countries but previous research has suggested that the disease is not detected by CXR in approximately 20% of patients. The risk of lung cancer, with particular symptoms, following a negative CXR is not known.

Aim

To establish the sensitivity and specificity of CXR requested by patients who are symptomatic; determine the positive predictive values (PPVs) of each presenting symptom of lung cancer following a negative CXR; and determine whether symptoms associated with lung cancer are different in those who had a positive CXR result compared with those who had a negative CXR result.

Design and setting

A prospective cohort study was conducted in Leeds, UK, based on routinely collected data from a service that allowed patients with symptoms of lung cancer to request CXR.

Method

Symptom data were combined with a diagnostic category (positive or negative) for each CXR, and the sensitivity and specificity of CXR for lung cancer were calculated. The PPV of lung cancer associated with each symptom or combination of symptoms was estimated for those patients with a negative CXR.

Results

In total, 114 (1.3%) of 8996 patients who requested a CXR were diagnosed with lung cancer within 1 year. Sensitivity was 75.4% and specificity was 90.2%. The PPV of all symptoms for a diagnosis of lung cancer within 1 year of CXR was <1% for all individual symptoms except for haemoptysis, which had a PPV of 2.9%. PPVs for a diagnosis of lung cancer within 2 years of CXR was <1.5% for all single symptoms except for haemoptysis, which had a PPV of 3.9%.

Conclusion

CXR has limited sensitivity; however, in a population with a low prevalence of lung cancer, its high specificity and negative predictive value means that lung cancer is very unlikely to be present following a negative result. Findings also support guidance that unexplained haemoptysis warrants urgent referral, regardless of CXR result.

Unintentional exposure and incidental findings during conventional chest radiography in the pediatric intensive care unit

Radiation overexposure is common in chest X-ray (CXRs) of pediatric patients. However, overexposure may reveal incidental findings that can help to guide patient management or warrant quality improvement.To assess the prevalence of overexposure in CXRs in pediatric intensive care unit (PICU); and identify the incidental findings within overexposed areas, we conducted a retrospective cohort study of children who were admitted to PICU. Two independent evaluators reviewed patient's charts and digital CXRs according to the American College of Radiology standards; to evaluate overexposure of the anatomical parameters and incidental findings.A total of 400 CXRs of 85 patients were reviewed. The mean number of CXRs per patient was 4.7. Almost all (99.75%) CXRs met the criteria for overexposure, with the most common being upper abdomen (99.2%), upper limbs (97%) and neck (95.7%). In addition, 43% of these X-rays were cropped by the radiology technician to appear within the requested perimeter. There was a significant association between field cropping and overexposure (t-test: t = 9.8, P < .001). Incidental findings were seen in 41.5% of the radiographs; with the most common being gaseous abdominal distension (73.1%), low-positioned nasogastric tube (24.6%), and constipation (10.3%).Anatomical overexposure in routine CXRs remains high and raises a concern in PICU practice. Appropriate collimation of the X-ray beam, rather than electronically cropping the image, is highly recommended to minimize hiding incidental findings in the cropped-out areas. Redefining the anatomic boundaries of CXR in critically ill infants and children may need further studies and consideration. Quality improvement initiatives to minimize radiation overexposure in PICU are recommended, especially in younger children and those with more severe illness upon PICU admission.

Viral Pneumonia Screening on Chest X-Rays Using Confidence-Aware Anomaly Detection

Clusters of viral pneumonia occurrences over a short period may be a harbinger of an outbreak or pandemic. Rapid and accurate detection of viral pneumonia using chest X-rays can be of significant value for large-scale screening and epidemic prevention, particularly when other more sophisticated imaging modalities are not readily accessible. However, the emergence of novel mutated viruses causes a substantial dataset shift, which can greatly limit the performance of classification-based approaches. In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into a one-class classification-based anomaly detection problem. We therefore propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module. If the anomaly score produced by the anomaly detection module is large enough, or the confidence score estimated by the confidence prediction module is small enough, the input will be accepted as an anomaly case (i.e., viral pneumonia). The major advantage of our approach over binary classification is that we avoid modeling individual viral pneumonia classes explicitly and treat all known viral pneumonia cases as anomalies to improve the one-class model. The proposed model outperforms binary classification models on the clinical X-VIRAL dataset that contains 5,977 viral pneumonia (no COVID-19) cases, 37,393 non-viral pneumonia or healthy cases. Moreover, when directly testing on the X-COVID dataset that contains 106 COVID-19 cases and 107 normal controls without any fine-tuning, our model achieves an AUC of 83.61% and sensitivity of 71.70%, which is comparable to the performance of radiologists reported in the literature.

Fast and Accurate Detection of COVID-19 Along With 14 Other Chest Pathologies Using a Multi-Level Classification: Algorithm Development and Validation Study

BACKGROUND

COVID-19 has spread very rapidly, and it is important to build a system that can detect it in order to help an overwhelmed health care system. Many research studies on chest diseases rely on the strengths of deep learning techniques. Although some of these studies used state-of-the-art techniques and were able to deliver promising results, these techniques are not very useful if they can detect only one type of disease without detecting the others.

OBJECTIVE

The main objective of this study was to achieve a fast and more accurate diagnosis of COVID-19. This study proposes a diagnostic technique that classifies COVID-19 x-ray images from normal x-ray images and those specific to 14 other chest diseases.

METHODS

In this paper, we propose a novel, multilevel pipeline, based on deep learning models, to detect COVID-19 along with other chest diseases based on x-ray images. This pipeline reduces the burden of a single network to classify a large number of classes. The deep learning models used in this study were pretrained on the ImageNet dataset, and transfer learning was used for fast training. The lungs and heart were segmented from the whole x-ray images and passed onto the first classifier that checks whether the x-ray is normal, COVID-19 affected, or characteristic of another chest disease. If it is neither a COVID-19 x-ray image nor a normal one, then the second classifier comes into action and classifies the image as one of the other 14 diseases.

RESULTS

We show how our model uses state-of-the-art deep neural networks to achieve classification accuracy for COVID-19 along with 14 other chest diseases and normal cases based on x-ray images, which is competitive with currently used state-of-the-art models. Due to the lack of data in some classes such as COVID-19, we applied 10-fold cross-validation through the ResNet50 model. Our classification technique thus achieved an average training accuracy of 96.04% and test accuracy of 92.52% for the first level of classification (ie, 3 classes). For the second level of classification (ie, 14 classes), our technique achieved a maximum training accuracy of 88.52% and test accuracy of 66.634% by using ResNet50. We also found that when all the 16 classes were classified at once, the overall accuracy for COVID-19 detection decreased, which in the case of ResNet50 was 88.92% for training data and 71.905% for test data.

CONCLUSIONS

Our proposed pipeline can detect COVID-19 with a higher accuracy along with detecting 14 other chest diseases based on x-ray images. This is achieved by dividing the classification task into multiple steps rather than classifying them collectively.

COVID-19 and Adenovirus Multi-Lobar Pneumonia on CT Scan in a Patient with Repeatedly Normal Chest X-Rays Despite Severe Hypoxia and the Need for Non-Invasive Ventilation

The British Society of Thoracic Imaging (BSTI) has published clear guidance on the classification of chest X-ray (CXR) findings in coronavirus disease 2019 (COVID-19) patients, which are summarised in four main categories: COVID-classical, COVID-indeterminate, COVID-normal, or non-COVID. We report the case of a 34-year-old lady who is otherwise fit and well. She presented with typical COVID-19 symptoms requiring supplemental oxygen, with normal CXR and COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR) swab on admission. Her condition deteriorated after 24 hours with severe hypoxia requiring up to 60% oxygen. Repeat CXR was normal, which was followed by computed tomography pulmonary angiogram (CTPA) that ruled out pulmonary embolism; however, CTPA confirmed multi-lobar pneumonia consistent with COVID-19. The patient was admitted to the intensive care unit for non-invasive ventilation (NIV) and ongoing care. Extended respiratory screening confirmed positive COVID-19 antibodies and positive adenovirus swabs. The patient also developed COVID-19 related hepatocellular injury and myocarditis in the absence of other causes. These were treated by a multidisciplinary team, and the patient achieved full recovery after three weeks. This case highlights the fact that normal CXR does not rule out COVID-19 pneumonia even in the severely hypoxic patient requiring NIV. Also, it is important to investigate for other potential causes of hypoxia in a deteriorating patient, such as pulmonary embolism and non-COVID causes of pneumonia.

Improving Uncertainty Estimation With Semi-Supervised Deep Learning for COVID-19 Detection Using Chest X-Ray Images

In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.

Detection of COVID-19 from chest x-ray images using transfer learning

Purpose: The objective of this study is to develop and evaluate a fully automated, deep learning-based method for detection of COVID-19 infection from chest x-ray images. Approach: The proposed model was developed by replacing the final classifier layer in DenseNet201 with a new network consisting of global averaging layer, batch normalization layer, a dense layer with ReLU activation, and a final classification layer. Then, we performed an end-to-end training using the initial pretrained weights on all the layers. Our model was trained using a total of 8644 images with 4000 images each in normal and pneumonia cases and 644 in COVID-19 cases representing a large real dataset. The proposed method was evaluated based on accuracy, sensitivity, specificity, ROC curve, and F 1 -score using a test dataset comprising 1729 images (129 COVID-19, 800 normal, and 800 pneumonia). As a benchmark, we also compared the results of our method with those of seven state-of-the-art pretrained models and with a lightweight CNN architecture designed from scratch. Results: The proposed model based on DenseNet201 was able to achieve an accuracy of 94% in detecting COVID-19 and an overall accuracy of 92.19%. The model was able to achieve an AUC of 0.99 for COVID-19, 0.97 for normal, and 0.97 for pneumonia. The model was able to outperform alternative models in terms of overall accuracy, sensitivity, and specificity. Conclusions: Our proposed automated diagnostic model yielded an accuracy of 94% in the initial screening of COVID-19 patients and an overall accuracy of 92.19% using chest x-ray images.

COVID-19 detection and heatmap generation in chest x-ray images

Purpose: The outbreak of COVID-19 or coronavirus was first reported in 2019. It has widely and rapidly spread around the world. The detection of COVID-19 cases is one of the important factors to stop the epidemic, because the infected individuals must be quarantined. One reliable way to detect COVID-19 cases is using chest x-ray images, where signals of the infection are located in lung areas. We propose a solution to automatically classify COVID-19 cases in chest x-ray images. Approach: The ResNet-101 architecture is adopted as the main network with more than 44 millions parameters. The whole net is trained using the large size of 1500 × 1500 x-ray images. The heatmap under the region of interest of segmented lung is constructed to visualize and emphasize signals of COVID-19 in each input x-ray image. Lungs are segmented using the pretrained U-Net. The confidence score of being COVID-19 is also calculated for each classification result. Results: The proposed solution is evaluated based on COVID-19 and normal cases. It is also tested on unseen classes to validate a regularization of the constructed model. They include other normal cases where chest x-ray images are normal without any disease but with some small remarks, and other abnormal cases where chest x-ray images are abnormal with some other diseases containing remarks similar to COVID-19. The proposed method can achieve the sensitivity, specificity, and accuracy of 97%, 98%, and 98%, respectively. Conclusions: It can be concluded that the proposed solution can detect COVID-19 in a chest x-ray image. The heatmap and confidence score of the detection are also demonstrated, such that users or human experts can use them for a final diagnosis in practical usages.

Mobile chest X-ray manifestations of 54 deceased patients with coronavirus disease 2019: Retrospective study

To describe the mobile chest X-ray manifestations of deceased patients with coronavirus disease 2019 (COVID-19).In this retrospective study, we analyzed in patients with COVID-19 from Tongji Hospital (Wuhan, China), who had been died between February 18 and March 25, 2020. Two radiologists analyzed the radiologic characteristics of mobile chest X-ray, and analyzed the serial X-ray changes.Fifty-four deceased patients with COVID-19 were included in the study. We found that 50 (93%) patients with lesions occurred in the bilateral lung, 4 (7%) patients occurred in the right lung, 54 (100%) patients were multifocal involvement. The number of lung fields involved was 42 (78%) patients in 6 fields, 3 (6%) patients in 5 lung fields, 4 (7%) patients in 4 lung fields, and 5 (9%) patients in 3 lung fields. Fifty-three (98%) patients had patchy opacities, 3 (6%) patients had round or oval solid nodules, 9 (17%) patients had fibrous stripes, 13 (24%) patients had pleural effusion, 8 (15%) patients had pleural thickening, 6 (11%) patients had pneumothorax, 3 (6%) patients had subcutaneous emphysema. Among the 24 patients who had serial mobile chest X-rays, 16 (67%) patients had the progression of the lesions, 8 (33%) patients had no significant change of the lesions, and there was no case of reduction of the lesions.The mobile chest X-ray manifestations of deceased patients with COVID-19 were mostly bilateral lung, multifocal involvement, and extensive lung field, and pleural effusion, pleural thickening, and pneumothorax probably could be observed. The serial mobile chest X-ray showed that the chest lesions were progressive with a high probability.

Hazardous Removal of a Misplaced Nasogastric Tube

Teaching point: Careful analysis of tubes positioning on chest X-ray not only reveals misplacement but also helps to plan a safe removal.

Heart and Lung Multimodality Imaging in COVID-19

The severe acute respiratory syndrome-coronavirus-2 outbreak has rapidly reached pandemic proportions and has become a major threat to global health. Although the predominant clinical feature of coronavirus disease-2019 (COVID-19) is an acute respiratory syndrome of varying severity, ranging from mild symptomatic interstitial pneumonia to acute respiratory distress syndrome, the cardiovascular system can be involved in several ways. As many as 40% of patients hospitalized with COVID-19 have histories of cardiovascular disease, and current estimates report a proportion of myocardial injury in patients with COVID-19 of up to 12%. Multiple pathways have been suggested to explain this finding and the related clinical scenarios, encompassing local and systemic inflammatory responses and oxygen supply-demand imbalance. From a clinical point of view, cardiac involvement during COVID-19 may present a wide spectrum of severity, ranging from subclinical myocardial injury to well-defined clinical entities (myocarditis, myocardial infarction, pulmonary embolism, and heart failure), whose incidence and prognostic implications are currently largely unknown because of a significant lack of imaging data. Integrated heart and lung multimodality imaging plays a central role in different clinical settings and is essential in the diagnosis, risk stratification, and management of patients with COVID-19. The aims of this review are to summarize imaging-oriented pathophysiological mechanisms of lung and cardiac involvement in COVID-19 and to provide a guide for integrated imaging assessment in these patients.

Predicting COVID-19 Pneumonia Severity on Chest X-ray With Deep Learning

Introduction

The need to streamline patient management for coronavirus disease-19 (COVID-19) has become more pressing than ever. Chest X-rays (CXRs) provide a non-invasive (potentially bedside) tool to monitor the progression of the disease. In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge the severity of COVID-19 lung infections (and pneumonia in general) that can be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU.

Methods

Images from a public COVID-19 database were scored retrospectively by three blinded experts in terms of the extent of lung involvement as well as the degree of opacity. A neural network model that was pre-trained on large (non-COVID-19) chest X-ray datasets is used to construct features for COVID-19 images which are predictive for our task.

Results

This study finds that training a regression model on a subset of the outputs from this pre-trained chest X-ray model predicts our geographic extent score (range 0-8) with 1.14 mean absolute error (MAE) and our lung opacity score (range 0-6) with 0.78 MAE.

Conclusions

These results indicate that our model’s ability to gauge the severity of COVID-19 lung infections could be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU. To enable follow up work, we make our code, labels, and data available online.

Radiological diagnosis of Coronavirus Disease 2019 (COVID-19): a Practical Guide

Novel beta-coronavirus (2019-nCoV) is the cause of Coronavirus disease-19 (COVID-19), and on March 12th 2020, the World Health Organization defined COVID-19 as a controllable pandemic. Currently, the 2019 novel coronavirus (SARS-CoV-2) can be identified by virus isolation or viral nucleic acid detection; however, false negatives associated with the nucleic acid detection provide a clinical challenge. Imaging examination has become the indispensable means not only in the early detection and diagnosis but also in monitoring the clinical course, evaluating the disease severity, and may be presented as an important warning signal preceding the negative RT-PCR test results. Different radiological modalities can be used in different disease settings. Radiology Departments must be nimble in implementing operational changes to ensure continued radiology services and protect patients and staff health.