Imaging of Community-acquired Pneumonia

A radiomics model utilizing CT for the early detection and diagnosis of severe community-acquired pneumonia

BACKGROUND

Community-Acquired Pneumonia (CAP) remains a significant global health concern, with a subset of cases progressing to Severe Community-Acquired Pneumonia (SCAP). This study aims to develop and validate a CT-based radiomics model for the early detection of SCAP to enable timely intervention and improve patient outcomes.

METHODS

A retrospective study was conducted on 115 CAP and SCAP patients at Southern Medical University Shunde Hospital from January to December 2021. Using the Pyradiomics package, 107 radiomic features were extracted from CT scans, refined via intra-class and inter-class correlation coefficients, and narrowed down using the Least Absolute Shrinkage and Selection Operator (LASSO) regression model. The predictive performance of the radiomics-based model was assessed through receiver operating characteristic (ROC) analysis, employing machine learning classifiers such as k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF), trained and validated on datasets split 7:3, with a training set (n = 80) and a validation set (n = 35).

RESULTS

The radiomics model exhibited robust predictive performance, with the RF classifier achieving superior precision and accuracy compared to LR, SVM, and KNN classifiers. Specifically, the RF classifier demonstrated a precision of 0.977 (training set) and 0.833 (validation set), as well as an accuracy of 0.925 (training set) and 0.857 (validation set), suggesting its superior performance in both metrics. Decision Curve Analysis (DCA) was utilized to evaluate the clinical efficacy of the RF classifier, demonstrating a favorable net benefit within the threshold ranges of 0.1 to 0.8 for the training set and 0.2 to 0.7 for the validation set.

CONCLUSIONS

The radiomics model developed in this study shows promise for early SCAP detection and can improve clinical decision-making.

Analysis of imaging in pediatric bronchopulmonary foregut malformations with literature review: case reports

Background

Bronchopulmonary foregut malformation (BPFM) is an uncommon condition, with few case reports documented in both national and international literature. This scarcity underscores the importance of utilizing effective imaging techniques to improve our understanding and diagnostic precision concerning this disorder.

Case description

In the first case report, a neonate, born at full term and aged 15 days, presented with symptoms including dyspnea, coughing, wheezing, cyanosis, and vomiting. Initial diagnostic evaluations, which included chest radiography and upper gastrointestinal tract radiography, led to an erroneous initial diagnosis of a left-sided diaphragmatic hernia, accompanied by a suspicion of infection. In the second case report, another neonate, also born at full term but aged 5 days, exhibited symptoms such as coughing, choking, and mild vomiting. Utilizing a combination of computed tomography (CT) scans (plain, enhanced, and reconstructed), chest x-ray, and upper gastrointestinal tract radiography, the diagnosis of BPFM was accurately determined.

Conclusion

Comprehensive imaging examinations play a crucial role in reducing misdiagnosis and diagnostic oversights in cases of BPFM. Given its rarity, BPFM often manifests as a sequestered lung accompanied by gastrointestinal abnormalities. Hence, the integration of CT scans with gastrointestinal tract radiography can substantially improve diagnostic precision in such cases.

Retrospective computed tomography assessment of chemotherapy-related pneumonia with severity screening in pediatric acute lymphoblastic leukemia by radiological imaging

Objectives

To evaluate the radiological imaging-guided severity along the pneumonia course and evaluate the chest computed tomography (CT) findings of chemotherapy-related pneumonia in children with acute lymphoblastic leukemia (ALL).

Materials and methods

A retrospective database review of children with ALL was conducted from March 2016 to August 2021 to identify cases with CT images who developed pneumonia during the chemotherapy course. A total of 51 children with ALL developed pneumonia were ultimately included (31 boys and 20 girls, mean age: 6 ± 4 years [standard deviation]). Each child's demographics, medical records, and laboratory results were collected. The CT images were then reviewed and the radiologic severity index (RSI) was calculated based on the regional opacity and implicated volume. A t-test, U test, Pearson's Chi-square test, and Fisher's exact test were performed to compare the clinical or radiologic features between the severe and moderate cases. The linear regression models were employed to analyze the correlation of RSIs with other clinical features.

Results

Eleven children (22 %, 11/51) displayed severe phenotypes associated with respiratory failure. The ground glass opacity (GGO) frequently appeared (65 % of CT images). The baseline RSI was positively associated with the lowest lymphocyte (p = .003), neutrophil (p = .01) counts, and the highest C-reactive protein level (p = .04). The peak RSI may predict severe phenotypes at a cutoff of 4.5 (AUC 0.76 [0.61, 0.91]) with 73 % sensitivity and 63 % specificity.

Conclusion

The chest CT images of children with chemotherapy-related pneumonia displayed clinically related baseline RSI and a peak RSI of >4.5 of 36 predicted severe phenotypes.

Effective processing pipeline PACE 2.0 for enhancing chest x-ray contrast and diagnostic interpretability

Preprocessing is an essential task for the correct analysis of digital medical images. In particular, X-ray imaging might contain artifacts, low contrast, diffractions or intensity inhomogeneities. Recently, we have developed a procedure named PACE that is able to improve chest X-ray (CXR) images including the enforcement of clinical evaluation of pneumonia originated by COVID-19. At the clinical benchmark state of this tool, there have been found some peculiar conditions causing a reduction of details over large bright regions (as in ground-glass opacities and in pleural effusions in bedridden patients) and resulting in oversaturated areas. Here, we have significantly improved the overall performance of the original approach including the results in those specific cases by developing PACE2.0. It combines 2D image decomposition, non-local means denoising, gamma correction, and recursive algorithms to improve image quality. The tool has been evaluated using three metrics: contrast improvement index, information entropy, and effective measure of enhancement, resulting in an average increase of 35% in CII, 7.5% in ENT, 95.6% in EME and 13% in BRISQUE against original radiographies. Additionally, the enhanced images were fed to a pre-trained DenseNet-121 model for transfer learning, resulting in an increase in classification accuracy from 80 to 94% and recall from 89 to 97%, respectively. These improvements led to a potential enhancement of the interpretability of lesion detection in CXRs. PACE2.0 has the potential to become a valuable tool for clinical decision support and could help healthcare professionals detect pneumonia more accurately.

Potential Role of Intrapulmonary Concomitant Lesions in Differentiating Non-Neoplastic and Neoplastic Ground Glass Nodules

Purpose

To determine the value of intrapulmonary concomitant lesions in differentiating non-neoplastic and neoplastic ground-glass nodules (GGNs).

Patients and Methods

From January 2014 to March 2022, 395 and 583 patients with confirmed non-neoplastic and neoplastic GGNs were retrospectively enrolled. Their clinical and chest CT data were evaluated. The CT features of target GGNs and intrapulmonary concomitant lesions in these two groups were analyzed and compared, and the role of intrapulmonary concomitant lesions in improving differentiation was evaluated.

Results

The intrapulmonary concomitant lesions were more common in patients with non-neoplastic GGNs than in those with neoplastic ones (87.88% vs 82.18%, P = 0.015). Specifically, patients with non-neoplastic GGNs had a higher incidence of multiple solid nodules (SNs), patchy ground-glass opacity/consolidation, and fibrosis/calcification in any lung fields (each P < 0.05). Logistic regression analysis indicated that patients < 44 years old, diameter < 7.35 mm, irregular shape, and coarse margin or ill-defined boundary for target GGN, pleural thickening, and concomitant SNs in the same lobe and fibrosis or calcification in any lung field were independent indicators for predicting non-neoplastic GGNs. The AUC of the model for predicting non-neoplastic GGNs increased from 0.894 to 0.926 (sensitivity, 83.10%; specificity, 87.10%) after including the concomitant lesions in the patients' clinical characteristics and CT features of target GGNs (P < 0.0001).

Conclusion

Besides the patients' clinical characteristics and CT features of target GGNs, the concomitant multiple SNs in the same lobe and fibrosis/calcification in any lung field should be considered in further differentiating non-neoplastic and neoplastic GGNs.

Ten Issues for Updating in Community-Acquired Pneumonia: An Expert Review

Community-acquired pneumonia represents the third-highest cause of mortality in industrialized countries and the first due to infection. Although guidelines for the approach to this infection model are widely implemented in international health schemes, information continually emerges that generates controversy or requires updating its management. This paper reviews the most important issues in the approach to this process, such as an aetiologic update using new molecular platforms or imaging techniques, including the diagnostic stewardship in different clinical settings. It also reviews both the Intensive Care Unit admission criteria and those of clinical stability to discharge. An update in antibiotic, in oxygen, or steroidal therapy is presented. It also analyzes the management out-of-hospital in CAP requiring hospitalization, the main factors for readmission, and an approach to therapeutic failure or rescue. Finally, the main strategies for prevention and vaccination in both immunocompetent and immunocompromised hosts are reviewed.

Pneumonia pattern recognition on ultra-low-dose CT does not allow for a reliable differentiation between viral and bacterial pneumonia: A multicentre observer study

PURPOSE

While a reliable differentiation between viral and bacterial pneumonia is not possible with chest X-ray, this study investigates whether ultra-low-dose chest-CT (ULDCT) could be used for this purpose.

METHODS

In the OPTIMACT trial 281 patients had a final diagnosis of pneumonia, and 96/281 (34%) had one or more positive microbiology results: 60 patients viral pathogens, 48 patients bacterial pathogens. These 96 ULDCT's were blindly and independently evaluated by two chest radiologists, who reported CT findings, pneumonia pattern, and most likely type of pathogen. Differences between groups were analysed for each radiologist separately, diagnostic accuracy was evaluated by calculating sensitivity.

RESULTS

The dominant CT finding significantly differed between the viral and bacterial pathogen groups (p = 0.04; p = 0.04). Consolidation was the most frequent dominant CT finding in both patients with viral and bacterial pathogens, but was observed significantly more often in those with a bacterial pathogen: 32/60 and 22/60 versus 38/48 and 31/48 (p = 0.005; p = 0.004). The lobar pneumonia pattern was more frequently observed in patients with a bacterial pathogen: 23/48 and 18/48, versus 10/60 and 8/60 for viral pathogens (p < 0.001; p = 0.004). For the bronchopneumonia and interstitial pneumonia patterns the proportions of viral and bacterial pathogens were not significantly different. Both radiologists suggested a viral pathogen correctly (sensitivity) in 6/60 (10%), for a bacterial pathogen this was 34/48 (71%).

CONCLUSION

Reliable differentiation between viral and bacterial pneumonia could not be made by pattern recognition on ULDCT, although a lobar pneumonia pattern was significantly more often observed in bacterial infection.

Pulmonary embolism induces pneumonia-like lung injury beyond pulmonary infarction

Patients with pulmonary embolism (PE) commonly manifest concomitant "pneumonia," which is generally believed to be either a cause (infection) or a consequence (infarction) of PE. This study aimed to clarify the relationship between PE and "pneumonia-like" lesions beyond pulmonary infection and infarction. Chest computed tomography (CT) images of patients with PE and deep vein thrombosis (DVT) were retrospectively analyzed to compare the incidence of pneumonia lesions. The pathological damage and wet/dry ratio of lung tissues were observed in PE rats and PE plasma-injected rats. In total, 793 and 914 inpatients were enrolled in the PE and DVT groups, respectively. Pneumonia lesions were observed in 36.9% and 26.3% of patients in the PE and DVT groups, respectively (p < 0.0001). Among PE rats, 33.3% exhibited focal severe lung injury, which closely resembled the pathological damage of community-acquired pneumonia. The wet/dry ratio was significantly higher in the PE group than in the PE-control group (4.98 ± 0.08 vs. 4.39 ± 0.06, p < 0.0001). Among PE plasma-injected rats, individuals with focal proven lung injury were found at all experimental points, with an incidence of 27.6%. The lung wet/dry ratio was significantly higher in the PE plasma group than in the PE-control plasma group at 1 and 2 h postinjection (5.02 ± 0.12 vs. 4.61 ± 0.06 and 4.76 ± 0.16 vs. 4.34 ± 0.09, respectively; p < 0.05). In conclusion, the manifestation of pneumonia lesions in chest CT images was higher among PE patients than among DVT patients. Plasma of PE rats could induce focal pneumonia-like lung injury in healthy rats.

Diagnostic and Prognostic Roles of Procalcitonin and Other Tools in Community-Acquired Pneumonia: A Narrative Review

Community-acquired pneumonia (CAP) is among the most common causes of death and one of the leading healthcare concerns worldwide. It can evolve into sepsis and septic shock, which have a high mortality rate, especially in critical patients and comorbidities. The definitions of sepsis were revised in the last decade as "life-threatening organ dysfunction caused by a dysregulated host response to infection". Procalcitonin (PCT), C-reactive protein (CRP), and complete blood count, including white blood cells, are among the most commonly analyzed sepsis-specific biomarkers also used in pneumonia in a broad range of studies. It appears to be a reliable diagnostic tool to expedite care of these patients with severe infections in the acute setting. PCT was found to be superior to most other acute phase reactants and indicators, including CRP as a predictor of pneumonia, bacteremia, sepsis, and poor outcome, although conflicting results exist. In addition, PCT use is beneficial to judge timing for the cessation of antibiotic treatment in most severe infectious states. The clinicians should be aware of strengths and weaknesses of known and potential biomarkers in expedient recognition and management of severe infections. This manuscript is intended to present an overview of the definitions, complications, and outcomes of CAP and sepsis in adults, with special regard to PCT and other important markers.

Targeted delivery of inhalable drug particles in the tracheobronchial tree model of a pediatric patient with bronchopneumonia: A numerical study

Pneumonia is a common cause of hospitalization and death in children worldwide. Inhalation therapy is one of the methods treating pneumonia However, there are limited studies that distinguish between the physiology of children and adults, especially with respect to targeted drug delivery. A tracheobronchial (TB) tree model of an 11-year-old child with bronchopneumonia is selected as a testbed for in silico trials of targeted drug delivery. The airflow and particle transport are solved by the computational fluid dynamics method at an airflow rate of 15 LPM. The results indicate that the distribution of deposited particles shows aggregation on the particle release map. Point-source aerosol release (PSAR) method can significantly reduce the deposition efficiency (DE) of particles in the TB tree model. Specifically, the PSAR method can reduce the DE of large particles (i.e., 7.5 µm and 10 µm) by 7.57% and 9.61%, respectively. This enables rapid design of patient-specific treatment for different population age groups and different airway diseases.

Pneumonia Detection Using Enhanced Convolutional Neural Network Model on Chest X-Ray Images

Pneumonia, caused by microorganisms, is a severely contagious disease that damages one or both the lungs of the patients. Early detection and treatment are typically favored to recover infected patients since untreated pneumonia can lead to major complications in the elderly (>65 years) and children (<5 years). The objectives of this work are to develop several models to evaluate big X-ray images (XRIs) of the chest, to determine whether the images show/do not show signs of pneumonia, and to compare the models based on their accuracy, precision, recall, loss, and receiver operating characteristic area under the ROC curve scores. Enhanced convolutional neural network (CNN), VGG-19, ResNet-50, and ResNet-50 with fine-tuning are some of the deep learning (DL) algorithms employed in this study. By training the transfer learning model and enhanced CNN model using a big data set, these techniques are used to identify pneumonia. The data set for the study was obtained from Kaggle. It should be noted that the data set has been expanded to include further records. This data set included 5863 chest XRIs, which were categorized into 3 different folders (i.e., train, val, test). These data are produced every day from personnel records and Internet of Medical Things devices. According to the experimental findings, the ResNet-50 model showed the lowest accuracy, that is, 82.8%, while the enhanced CNN model showed the highest accuracy of 92.4%. Owing to its high accuracy, enhanced CNN was regarded as the best model in this study. The techniques developed in this study outperformed the popular ensemble techniques, and the models showed better results than those generated by cutting-edge methods. Our study implication is that a DL models can detect the progression of pneumonia, which improves the general diagnostic accuracy and gives patients new hope for speedy treatment. Since enhanced CNN and ResNet-50 showed the highest accuracy compared with other algorithms, it was concluded that these techniques could be effectively used to identify pneumonia after performing fine-tuning.

Efficacy of Artificial Intelligence in the Categorisation of Paediatric Pneumonia on Chest Radiographs: A Systematic Review

This study aimed to systematically review the literature to synthesise and summarise the evidence surrounding the efficacy of artificial intelligence (AI) in classifying paediatric pneumonia on chest radiographs (CXRs). Following the initial search of studies that matched the pre-set criteria, their data were extracted using a data extraction tool, and the included studies were assessed via critical appraisal tools and risk of bias. Results were accumulated, and outcome measures analysed included sensitivity, specificity, accuracy, and area under the curve (AUC). Five studies met the inclusion criteria. The highest sensitivity was by an ensemble AI algorithm (96.3%). DenseNet201 obtained the highest level of specificity and accuracy (94%, 95%). The most outstanding AUC value was achieved by the VGG16 algorithm (96.2%). Some of the AI models achieved close to 100% diagnostic accuracy. To assess the efficacy of AI in a clinical setting, these AI models should be compared to that of radiologists. The included and evaluated AI algorithms showed promising results. These algorithms can potentially ease and speed up diagnosis once the studies are replicated and their performances are assessed in clinical settings, potentially saving millions of lives.

High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images

In this study, multiple lung diseases are diagnosed with the help of the Neural Network algorithm. Specifically, Emphysema, Infiltration, Mass, Pleural Thickening, Pneumonia, Pneumothorax, Atelectasis, Edema, Effusion, Hernia, Cardiomegaly, Pulmonary Fibrosis, Nodule, and Consolidation, are studied from the ChestX-ray14 dataset. A proposed fine-tuned MobileLungNetV2 model is employed for analysis. Initially, pre-processing is done on the X-ray images from the dataset using CLAHE to increase image contrast. Additionally, a Gaussian Filter, to denoise images, and data augmentation methods are used. The pre-processed images are fed into several transfer learning models; such as InceptionV3, AlexNet, DenseNet121, VGG19, and MobileNetV2. Among these models, MobileNetV2 performed with the highest accuracy of 91.6% in overall classifying lesions on Chest X-ray Images. This model is then fine-tuned to optimise the MobileLungNetV2 model. On the pre-processed data, the fine-tuned model, MobileLungNetV2, achieves an extraordinary classification accuracy of 96.97%. Using a confusion matrix for all the classes, it is determined that the model has an overall high precision, recall, and specificity scores of 96.71%, 96.83% and 99.78% respectively. The study employs the Grad-cam output to determine the heatmap of disease detection. The proposed model shows promising results in classifying multiple lesions on Chest X-ray images.

DTLCx: An Improved ResNet Architecture to Classify Normal and Conventional Pneumonia Cases from COVID-19 Instances with Grad-CAM-Based Superimposed Visualization Utilizing Chest X-ray Images

COVID-19 is a severe respiratory contagious disease that has now spread all over the world. COVID-19 has terribly impacted public health, daily lives and the global economy. Although some developed countries have advanced well in detecting and bearing this coronavirus, most developing countries are having difficulty in detecting COVID-19 cases for the mass population. In many countries, there is a scarcity of COVID-19 testing kits and other resources due to the increasing rate of COVID-19 infections. Therefore, this deficit of testing resources and the increasing figure of daily cases encouraged us to improve a deep learning model to aid clinicians, radiologists and provide timely assistance to patients. In this article, an efficient deep learning-based model to detect COVID-19 cases that utilizes a chest X-ray images dataset has been proposed and investigated. The proposed model is developed based on ResNet50V2 architecture. The base architecture of ResNet50V2 is concatenated with six extra layers to make the model more robust and efficient. Finally, a Grad-CAM-based discriminative localization is used to readily interpret the detection of radiological images. Two datasets were gathered from different sources that are publicly available with class labels: normal, confirmed COVID-19, bacterial pneumonia and viral pneumonia cases. Our proposed model obtained a comprehensive accuracy of 99.51% for four-class cases (COVID-19/normal/bacterial pneumonia/viral pneumonia) on Dataset-2, 96.52% for the cases with three classes (normal/ COVID-19/bacterial pneumonia) and 99.13% for the cases with two classes (COVID-19/normal) on Dataset-1. The accuracy level of the proposed model might motivate radiologists to rapidly detect and diagnose COVID-19 cases.

Standard Versus Advanced Protective Measures in a COVID-Free Surgical Pathway

Introduction The importance of coronavirus disease (COVID)-free surgical pathways during the coronavirus disease 2019 (COVID-19) pandemic has been demonstrated. However, the extent of protective measures to be applied against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), particularly before vaccines became available, remained unclear. Methods This retrospective study included all SARS-CoV-2-negative patients admitted to the COVID-free pathway of a regional abdominal surgery hub center in Northern Italy over 12 months, before the vaccination campaign. During the first seven months, basic protective measures against SARS-CoV-2 were adopted (surgical masks, swabs for symptomatic patients, and intra- or interhospital transfers), since patients were treated as effectively negative (standard management). During the last five months, advanced measures were implemented (enhanced personal protections and systematic control swabs), as patients were considered potentially positive (advanced management). The aim of this article was to compare SARS-CoV-2 incidence and surgical outcomes in these periods. Results A total of 283 and 194 patients were admitted under standard and advanced management, respectively; pre-admission data differed only in the rate of previous SARS-CoV-2 infection (2.5% versus 6.7%, p= 0.034). The SARS-CoV-2 incidence was 3.9% and 3.1% for standard and advanced periods, respectively (p = 0.835). Two internal outbreaks developed during the standard phase. The advanced protocol significantly increased the rate of patients re-tested for SARS-CoV-2 (83% versus 41.7%, p < 0.001) and allowed early detection of all infections, which remained sporadic. Surgical outcomes were similar. Conclusions Advanced management was instrumental in detecting positive patients early and preventing outbreaks, without affecting surgical results; accordingly, it stands as a reproducible model for future pandemic scenarios.

Strategies for recognizing pneumonia look-alikes

Community-acquired pneumonia is a common diagnosis in children. Among the many children whose symptoms and/or chest X-ray is consistent with community-acquired pneumonia, it can be difficult to distinguish the rare cases of differential diagnoses that require specific management. The aim of this educational article is to provide clinicians with a series of questions to ask themselves in order to detect a possible differential diagnosis of pneumonia in children. The value of this approach is illustrated by 13 real clinical cases in which a child was misdiagnosed as having lobar pneumonia. What is Known: • When a lobar pneumonia is diagnosed, an appropriate antibiotic treatment leads to the resolution of the clinical signs in most cases. • However, several diseases can be look-alikes for pneumonia and mislead the practitioner. What is New: • This article provides a new approach to identify differential diagnoses of pneumonia in children. • It is illustrated by 13 real-life situations of children misdiagnosed as having pneumonia.

The Accuracy of Lung Ultrasonography Diagnosis of Community-Acquired Pneumonia, in an Adult Cohort

Objective:

Community-acquired pneumonia (CAP) is a common respiratory infection, and diagnosis is frequently performed using a chest radiography (CXR). Sonography is an available method with less radiation exposure, but has not been confirmed for diagnosis of CAP. The objective was to compare the diagnostic accuracy of sonography.

Materials and Methods:

In this cross-sectional study, 90 adult patients (aged >18 years) were admitted to the emergency department of two university-affiliated hospitals in Southwest Iran, from July to December 2019, with a confirmed diagnosis of CAP. The patient symptoms and CXR results were included as part of this study. Within 24 hours after obtaining a CXR, a lung ultrasonogram (LUS) was performed. The diagnostic accuracy of semiquantitative LUS (SQLUS) was compared with CXR results using the Pearson chi-square test and Fisher’s exact test.

Results:

The mean age of participants was 52.98 ± 16.77 years. 51 were men (56.7%). 28 patients (31.1%), who had abnormal SQLUS results, were not associated with CXR findings ( P = .296). SQLUS showed poor diagnostic accuracy for LUS (31.11%).

Conclusion:

This study results could not confirm LUS as an accurate method for diagnosing CAP in adult patients; although due to the convenient sample of adults and clinical-based diagnosis of CAP, any generalization of the results should be made with caution.

Relationship Between Pneumonia and Dysphagia in Patients With Multiple System Atrophy

Introduction

Dysphagia is one of the most clinically significant disabilities in patients with multiple system atrophy (MSA), because it can cause aspiration pneumonia, which is potentially fatal. In this study, the Neuromuscular disease Swallowing Status Scale (NdSSS), which was developed to evaluate dysphagia in patients with neuromuscular diseases, was used to evaluate patients with MSA. In addition, correlation between a history of pneumonia and swallowing function was evaluated.

Methods

Study 1: Reliability, concurrent validity, and responsiveness of the NdSSS in patients with MSA. In 81 patients for whom evaluation items could be collected, the NdSSS was tested for its interrater and intrarater reliability using weighted kappa statistics. Concurrent validity was assessed by correlating the NdSSS with existing scales (Functional Oral Intake Scale (FOIS), Functional Intake LEVEL Scale (FILS), and the unified MSA rating scale (UMSARS)) using Spearman's rank correlation coefficients. Sixty-three patients were evaluated by videofluorographic (VF) swallowing examination. To evaluate concurrent validity, Spearman's rank correlation coefficients were calculated between the NdSSS and VF swallowing assessments. Additionally, scale responsiveness was determined using the standardized response mean (SRM) in 23 patients who could be followed up to assess their long-term course. Study 2: Cross-sectional survey of swallowing function and history of pneumonia. Data regarding history of pneumonia, UMSARS, NdSSS, age, sex, MSA subtype, and disease duration were retrospectively obtained from the medical records of 113 patients with MSA. Differences in these parameters and NdSSS stage between those with and without a history of pneumonia were examined using the Mann-Whitney test or chi-squared test. Furthermore, clinical factors related to a history of pneumonia were examined by binomial logistic regression analysis.

Results

The NdSSS showed satisfactory reliability, concurrent validity, and responsiveness. A history of pneumonia was related to the severity of MSA, age, MSA subtype, and NdSSS stage. Binomial logistic regression analysis showed that NdSSS stage (odds ratio (OR), 0.490; 95% confidence interval (CI), 0.301–0.797, p = 0.001) and MSA subtype (OR, 4.031; 95% CI, 1.225–13.269, p = 0.021) were significantly associated with a history of pneumonia.

Conclusions

In patients with MSA, the NdSSS has sufficient reliability, concurrent validity, and responsiveness for assessing dysphagia. Patients with a history of pneumonia have more severe dysphagia. We found that the pneumonia risk was related to NdSSS stage and MSA-p (predominantly parkinsonism). Meticulous care to prevent aspiration is needed from early stages of the disease.

Fungal infection mimicking COVID-19 infection - A case report

For the last 2 years, one of the most frequent causes of respiratory failure is coronavirus disease 2019 (COVID-19). The symptoms are not specific. Imaging diagnostics, especially high-resolution computed tomography, is a diagnostic method widely used in the diagnosis of this disease. It is important to emphasize that not only SARS-CoV-2 infection may manifest as interstitial pneumonia. Other diseases such as other viral, fungal, atypical bacterial pneumonia, autoimmune process, and even cancer can also manifest as ground-glass opacities or consolidations in the imaging of the lungs. In this case report, we described a patient who manifested many symptoms that seemed to be COVID-19. However, all performed antigen and polymerase chain reaction tests were negative. The diagnostics must have been extended. Microbiological and mycological blood cultures and sputum cultures were performed. Blood cultures were negative but in sputum, Candida albicans and Candida glabrata were identified. Targeted therapy with fluconazole was implemented with a satisfactory result. The patient was discharged from the hospital in a good general condition with no complaints.

Efficacy of Transfer Learning-based ResNet models in Chest X-ray image classification for detecting COVID-19 Pneumonia

Because of COVID-19's effect on pulmonary tissues, Chest X-ray(CXR) and Computed Tomography (CT) images have become the preferred imaging modality for detecting COVID-19 infections at the early diagnosis stages, particularly when the symptoms are not specific. A significant fraction of individuals with COVID-19 have negative polymerase chain reaction (PCR) test results; therefore, imaging studies coupled with epidemiological, clinical, and laboratory data assist in the decision making. With the newer variants of COVID-19 emerging, the burden on diagnostic laboratories has increased manifold. Therefore, it is important to employ beyond laboratory measures to solve complex CXR image classification problems. One such tool is Convolutional Neural Network (CNN), one of the most dominant Deep Learning (DL) architectures. DL entails training a CNN for a task such as classification using extensive datasets. However, the labelled data for COVID-19 is scarce, proving to be a prime impediment to applying DL-assisted analysis. The available datasets are either scarce or too diversified to learn effective feature representations; therefore Transfer Learning (TL) approach is utilized. TL-based ResNet architecture has a powerful representational ability, making it popular in Computer Vision. The aim of this study is two-fold- firstly, to assess the performance of ResNet models for classifying Pneumonia cases from CXR images and secondly, to build a customized ResNet model and evaluate its contribution to the performance improvement. The global accuracies achieved by the five models i.e., ResNet18_v1, ResNet34_v1, ResNet50_v1, ResNet101_v1, ResNet152_v1 are 91.35%, 90.87%, 92.63%, 92.95%, and 92.95% respectively. ResNet50_v1 displayed the highest sensitivity of 97.18%, ResNet101_v1 showed the specificity of 94.02%, and ResNet18_v1 had the highest precision of 93.53%. The findings are encouraging, demonstrating the effectiveness of ResNet in the automatic detection of Pneumonia for COVID-19 diagnosis. The customized ResNet model presented in this study achieved 95% global accuracy, 95.65% precision, 92.74% specificity, and 95.9% sensitivity, thereby allowing a reliable analysis of CXR images to facilitate the clinical decision-making process. All simulations were carried in PyTorch utilizing Quadro 4000 GPU with Intel(R) Xeon(R) CPU E5-1650 v4 @ 3.60 ​GHz processor and 63.9 ​GB useable RAM.

Multi-drug resistant gram-negative bacterial pneumonia: etiology, risk factors, and drug resistance patterns

Bacterial pneumonia is one of the most serious public health issues owing to its medical and economic costs, which result in increased morbidity and mortality in people of all ages around the world. Furthermore, antimicrobial resistance has risen over time, and the advent of multi-drug resistance in GNB complicates therapy and has a detrimental impact on patient outcomes. The current review aimed to summarize bacterial pneumonia with an emphasis on gram-negative etiology, pathogenesis, risk factors, resistance mechanisms, treatment updates, and vaccine concerns to tackle the problem before it causes a serious consequence. In conclusion, the global prevalence of GNB in CAP was reported 49.7% to 83.1%, whereas in VAP patients ranged between 76.13% to 95.3%. The most commonly reported MDR-GNB causes of pneumonia were A. baumannii, K. pneumoniae, and P. aeruginosa, with A. baumannii isolated particularly in VAP patients and the elderly. In most studies, ampicillin, tetracyclines, amoxicillin-clavulanic acid, cephalosporins, and carbapenems were shown to be highly resistant. Prior MDR-GNB infection, older age, previous use of broad-spectrum antibiotics, high frequency of local antibiotic resistance, prolonged hospital stays, ICU admission, mechanical ventilation, and immunosuppression are associated with the MDR-GNB colonization. S. maltophilia was reported as a severe cause of HAP/VAP in patients with mechanically ventilated and having hematologic malignancy due to its ability of biofilm formation, site adhesion in respiratory devices, and its intrinsic and acquired drug resistance mechanisms. Effective combination therapies targeting PDR strains and drug-resistant genes, antibiofilm agents, gene-based vaccinations, and pathogen-specific lymphocytes should be developed in the future.

GANterfactual—Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning

With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art tools to explain such classifiers rely on visual highlighting of important areas of the input data. Contrary, counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image in a way such that the classifier would have made a different prediction. By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information. However, methods for generating realistic counterfactual explanations for image classifiers are still rare. Especially in medical contexts, where relevant information often consists of textural and structural information, high-quality counterfactual images have the potential to give meaningful insights into decision processes. In this work, we present GANterfactual, an approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Additionally, we conduct a user study to evaluate our approach in an exemplary medical use case. Our results show that, in the chosen medical use-case, counterfactual explanations lead to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems that work with saliency maps, namely LIME and LRP.

A methodological approach to validate pneumonia encounters from radiology reports using Natural Language Processing (NLP)

INTRODUCTION

Pneumonia is caused by microbes that establish an infectious process in the lungs. The gold standard for pneumonia diagnosis is radiologist-documented pneumonia-related features in radiology notes that are captured in electronic health records in an unstructured format.

OBJECTIVE

The study objective was to develop a methodological approach for assessing validity of a pneumonia diagnosis based on identifying presence or absence of key radiographic features in radiology reports with subsequent rendering of diagnostic decisions into a structured format.

METHODS

A pneumonia-specific Natural Language Processing (NLP) pipeline was strategically developed applying cTAKES to validate pneumonia diagnoses following development of a pneumonia feature-specific lexicon. Radiographic reports of study-eligible subjects identified by International Classification of Diseases (ICD) codes were parsed through the NLP pipeline. Classification rules were developed to assign each pneumonia episode into one of three categories: "positive", "negative" or "not classified: requires manual review" based on tagged concepts that support or refute diagnostic codes.

RESULTS

A total of 91,998 pneumonia episodes diagnosed in 65,904 patients were retrieved retrospectively. Approximately 89% (81,707/91,998) of the total pneumonia episodes were documented by 225,893 chest x-ray reports. NLP classified and validated 33% (26,800/81,707) of pneumonia episodes classified as 'Pneumonia-positive', 19% as (15401/81,707) as 'Pneumonia-negative' and 48% (39,209/81,707) as ''episode classification pending further manual review'. NLP pipeline performance metrics included accuracy (76.3%), sensitivity (88%), and specificity (75%).

CONCLUSION

The pneumonia-specific NLP pipeline exhibited good performance comparable to other pneumonia-specific NLP systems developed to date.

Fine-Tuned Siamese Network with Modified Enhanced Super-Resolution GAN Plus Based on Low-Quality Chest X-ray Images for COVID-19 Identification

Coronavirus disease has rapidly spread globally since early January of 2020. With millions of deaths, it is essential for an automated system to be utilized to aid in the clinical diagnosis and reduce time consumption for image analysis. This article presents a generative adversarial network (GAN)-based deep learning application for precisely regaining high-resolution (HR) CXR images from low-resolution (LR) CXR correspondents for COVID-19 identification. Respectively, using the building blocks of GAN, we introduce a modified enhanced super-resolution generative adversarial network plus (MESRGAN+) to implement a connected nonlinear mapping collected from noise-contaminated low-resolution input images to produce deblurred and denoised HR images. As opposed to the latest trends of network complexity and computational costs, we incorporate an enhanced VGG19 fine-tuned twin network with the wavelet pooling strategy in order to extract distinct features for COVID-19 identification. We demonstrate our proposed model on a publicly available dataset of 11,920 samples of chest X-ray images, with 2980 cases of COVID-19 CXR, healthy, viral and bacterial cases. Our proposed model performs efficiently both on the binary and four-class classification. The proposed method achieves accuracy of 98.8%, precision of 98.6%, sensitivity of 97.5%, specificity of 98.9%, an F1 score of 97.8% and ROC AUC of 98.8% for the multi-class task, while, for the binary class, the model achieves accuracy of 99.7%, precision of 98.9%, sensitivity of 98.7%, specificity of 99.3%, an F1 score of 98.2% and ROC AUC of 99.7%. Our method obtains state-of-the-art (SOTA) performance, according to the experimental results, which is helpful for COVID-19 screening. This new conceptual framework is proposed to play an influential role in addressing the issues facing COVID-19 examination and other diseases.

Deep diagnostic agent forest (DDAF): A deep learning pathogen recognition system for pneumonia based on CT

BACKGROUND

Even though antibiotics agents are widely used, pneumonia is still one of the most common causes of death around the world. Some severe, fast-spreading pneumonia can even cause huge influence on global economy and life security. In order to give optimal medication regimens and prevent infectious pneumonia's spreading, recognition of pathogens is important.

METHOD

In this single-institution retrospective study, 2,353 patients with their CT volumes are included, each of whom was infected by one of 12 known kinds of pathogens. We propose Deep Diagnostic Agent Forest (DDAF) to recognize the pathogen of a patient based on ones' CT volume, which is a challenging multiclass classification problem, with large intraclass variations and small interclass variations and very imbalanced data.

RESULTS

The model achieves 0.899 ± 0.004 multi-way area under curves of receiver (AUC) for level-I pathogen recognition, which are five rough groups of pathogens, and 0.851 ± 0.003 AUC for level-II recognition, which are 12 fine-level pathogens. The model also outperforms the average result of seven human readers in level-I recognition and outperforms all readers in level-II recognition, who can only reach an average result of 7.71 ± 4.10% accuracy.

CONCLUSION

Deep learning model can help in recognition pathogens using CTs only, which might help accelerate the process of etiological diagnosis.

Management of pneumonia in critically ill patients

Severe pneumonia is associated with high mortality (short and long term), as well as pulmonary and extrapulmonary complications. Appropriate diagnosis and early initiation of adequate antimicrobial treatment for severe pneumonia are crucial in improving survival among critically ill patients. Identifying the underlying causative pathogen is also critical for antimicrobial stewardship. However, establishing an etiological diagnosis is challenging in most patients, especially in those with chronic underlying disease; those who received previous antibiotic treatment; and those treated with mechanical ventilation. Furthermore, as antimicrobial therapy must be empiric, national and international guidelines recommend initial antimicrobial treatment according to the location's epidemiology; for patients admitted to the intensive care unit, specific recommendations on disease management are available. Adherence to pneumonia guidelines is associated with better outcomes in severe pneumonia. Yet, the continuing and necessary research on severe pneumonia is expansive, inviting different perspectives on host immunological responses, assessment of illness severity, microbial causes, risk factors for multidrug resistant pathogens, diagnostic tests, and therapeutic options.

Imaging of Pulmonary Superinfections and Co-Infections in COVID-19

New challenges in imaging and management of COVID-19 pneumonia emerge as the pandemic continues across the globe. These arise not only due to the COVID-19 pneumonia but also related to various superinfections and co-infections. Limited use of bronchoscopic and other aerosol generating procedures to obtain representative lower respiratory samples from these patient groups for accurate identification of organism, increases the responsibility of radiologists in suggesting the most likely cause of secondary infection. Imaging features of many of these infections overlap with features of COVID-19 pneumonia. In this review, we highlight imaging findings that can aid in the diagnosis of superinfections and co-infections in patients with COVID-19 pneumonia, and also help in predicting the likely causative organism.

Weakly supervised pneumonia localization in chest X-rays using generative adversarial networks

PURPOSE

Automatic localization of pneumonia on chest X-rays (CXRs) is highly desirable both as an interpretive aid to the radiologist and for timely diagnosis of the disease. However, pneumonia's amorphous appearance on CXRs and complexity of normal anatomy in the chest present key challenges that hinder accurate localization. Existing studies in this area are either not optimized to preserve spatial information of abnormality or depend on expensive expert-annotated bounding boxes. We present a novel generative adversarial network (GAN)-based machine learning approach for this problem, which is weakly supervised (does not require any location annotations), was trained to retain spatial information, and can produce pixel-wise abnormality maps highlighting regions of abnormality (as opposed to bounding boxes around abnormality).

METHODS

Our method is based on the Wasserstein GAN framework and, to the best of our knowledge, the first application of GANs to this problem. Specifically, from an abnormal CXR as input, we generated the corresponding pseudo normal CXR image as output. The pseudo normal CXR is the "hypothetical" normal, if the same abnormal CXR were not to have any abnormalities. We surmise that the difference between the pseudo normal and the abnormal CXR highlights the pixels suspected to have pneumonia and hence is our output abnormality map. We trained our algorithm on an "unpaired" data set of abnormal and normal CXRs and did not require any location annotations such as bounding boxes/segmentations of abnormal regions. Furthermore, we incorporated additional prior knowledge/constraints into the model and showed that they help improve localization performance. We validated the model on a data set consisting of 14 184 CXRs from the Radiological Society of North America pneumonia detection challenge.

RESULTS

We evaluated our methods by comparing the generated abnormality maps with radiologist annotated bounding boxes using receiver operating characteristic (ROC) analysis, image similarity metrics such as normalized cross-correlation/mutual information, and abnormality detection rate.We also present visual examples of the abnormality maps, covering various scenarios of abnormality occurrence. Results demonstrate the ability to highlight regions of abnormality with the best method achieving an ROC area under the curve (AUC) of 0.77 and a detection rate of 85%.The GAN tended to perform better as prior knowledge/constraints were incorporated into the model.

CONCLUSIONS

We presented a novel GAN based approach for localizing pneumonia on CXRs that (1) does not require expensive hand annotated location ground truth; and (2) was trained to produce abnormality maps at the pixel level as opposed to bounding boxes. We demonstrated the efficacy of our methods via quantitative and qualitative results.

Application of deep learning to identify COVID-19 infection in posteroanterior chest X-rays

Introduction

The objective of this study was to assess seven configurations of six convolutional deep neural network architectures for classification of chest X-rays (CXRs) as COVID-19 positive or negative.

Methods

The primary dataset consisted of 294 COVID-19 positive and 294 COVID-19 negative CXRs, the latter comprising roughly equally many pneumonia, emphysema, fibrosis, and healthy images. We used six common convolutional neural network architectures, VGG16, DenseNet121, DenseNet201, MobileNet, NasNetMobile and InceptionV3. We studied six models (one for each architecture) which were pre-trained on a vast repository of generic (non-CXR) images, as well as a seventh DenseNet121 model, which was pre-trained on a repository of CXR images. For each model, we replaced the output layers with custom fully connected layers for the task of binary classification of images as COVID-19 positive or negative. Performance metrics were calculated on a hold-out test set with CXRs from patients who were not included in the training/validation set.

Results

When pre-trained on generic images, the VGG16, DenseNet121, DenseNet201, MobileNet, NasNetMobile, and InceptionV3 architectures respectively produced hold-out test set areas under the receiver operating characteristic (AUROCs) of 0.98, 0.95, 0.97, 0.95, 0.99, and 0.96 for the COVID-19 classification of CXRs. The X-ray pre-trained DenseNet121 model, in comparison, had a test set AUROC of 0.87.

Discussion

Common convolutional neural network architectures with parameters pre-trained on generic images yield high-performance and well-calibrated COVID-19 CXR classification.

Interobserver agreement in interpretation of chest radiographs for pediatric community acquired pneumonia: Findings of the pedCAPNETZ-cohort

Although chest radiograph (CXR) is commonly used in diagnosing pediatric community acquired pneumonia (pCAP), limited data on interobserver agreement among radiologists exist. PedCAPNETZ is a prospective, observational, and multicenter study on pCAP. N = 233 CXR from patients with clinical diagnosis of pCAP were retrieved and n = 12 CXR without pathological findings were added. All CXR were interpreted by a radiologist at the site of recruitment and by two external, blinded pediatric radiologists. To evaluate interobserver agreement, the reporting of presence or absence of pCAP in CXR was analyzed, and prevalence and bias-adjusted kappa (PABAK) statistical testing was applied. Overall, n = 190 (82%) of CXR were confirmed as pCAP by two external pediatric radiologists. Compared with patients with pCAP negative CXR, patients with CXR-confirmed pCAP displayed higher C-reactive protein levels and a longer duration of symptoms before enrollment (p < .007). Further parameters, that is, age, respiratory rate, and oxygen saturation showed no significant difference. The interobserver agreement between the onsite radiologists and each of the two independent pediatric radiologists for the presence of pCAP was poor to fair (69%; PABAK = 0.39% and 76%; PABAK = 0.53, respectively). The concordance between the external radiologists was fair (81%; PABAK = 0.62). With regard to typical CXR findings for pCAP, chance corrected interrater agreement was highest for pleural effusions, infiltrates, and consolidations and lowest for interstitial patterns and peribronchial thickening. Our data show a poor interobserver agreement in the CXR-based diagnosis of pCAP and emphasized the need for harmonized interpretation standards.

Pro-coagulant imbalance in patients with community acquired pneumonia assessed on admission and one month after hospital discharge

OBJECTIVES

Patients hospitalized because of community-acquired-pneumonia (CAP) are at risk of cardiovascular diseases. Although plasma procoagulant imbalance play a role, mechanisms are not completely understood. We aimed to investigate whether there is a measurable state of procoagulant imbalance following inflammation determined by CAP.

METHODS

We analyzed blood from 51 CAP patients at admission and 51 healthy subjects (HS) for (i) pro and anticoagulants, (ii) thrombin generation (TG) with or without thrombomodulin (TM), which is the physiologic activator of the protein C anticoagulant pathway and(iii) by assessing the ratio between von Willebrand-factor (VWF) and its protease ADAMTS13. Thirty patients were re-analyzed one month after discharge when CAP was resolved.

RESULTS

Median levels of TG parameters, including the endogenous thrombin potential (ETP), the ETP-TM-ratio (with/without TM), peak-thrombin and velocity index were higher in patients at baseline than HS. In particular, the median (IQR) ETP-TM-ratio in patients vs. HS was 0.88 (0.83-0.91) vs. 0.63 (0.48-0.71), p<0.001. Factor (F)VIII, a potent procoagulant involved in TG was higher in patients at baseline than HS [195 U/dL (100-388) vs. 127(108-145)], p<0.001]. The ratio of VWF/ADAMTS13 was higher at baseline than HS. Cumulatively, the findings indicate a state of pro-coagulant imbalance, which (although reduced), remained high [i.e., ETP-TM-ratio, 0.80 (0.74-0.84); FVIII, 152 U/dL (122-190)] one month after discharge when the infection was resolved.

CONCLUSIONS

Patients with CAP possess a state of pro-coagulant imbalance, which remains substantially high, even when the infection is resolved. The findings suggest CAP patients as candidates for antithrombotic prophylaxis even after the resolution of infection. Clinical trials are warranted to assess the benefit/risk ratio of prophylaxis extension.

AI-driven deep CNN approach for multi-label pathology classification using chest X-Rays

Artificial intelligence (AI) has played a significant role in image analysis and feature extraction, applied to detect and diagnose a wide range of chest-related diseases. Although several researchers have used current state-of-the-art approaches and have produced impressive chest-related clinical outcomes, specific techniques may not contribute many advantages if one type of disease is detected without the rest being identified. Those who tried to identify multiple chest-related diseases were ineffective due to insufficient data and the available data not being balanced. This research provides a significant contribution to the healthcare industry and the research community by proposing a synthetic data augmentation in three deep Convolutional Neural Networks (CNNs) architectures for the detection of 14 chest-related diseases. The employed models are DenseNet121, InceptionResNetV2, and ResNet152V2; after training and validation, an average ROC-AUC score of 0.80 was obtained competitive as compared to the previous models that were trained for multi-class classification to detect anomalies in x-ray images. This research illustrates how the proposed model practices state-of-the-art deep neural networks to classify 14 chest-related diseases with better accuracy.

Pneumonia

Pneumonia is a common acute respiratory infection that affects the alveoli and distal airways; it is a major health problem and associated with high morbidity and short-term and long-term mortality in all age groups worldwide. Pneumonia is broadly divided into community-acquired pneumonia or hospital-acquired pneumonia. A large variety of microorganisms can cause pneumonia, including bacteria, respiratory viruses and fungi, and there are great geographical variations in their prevalence. Pneumonia occurs more commonly in susceptible individuals, including children of <5 years of age and older adults with prior chronic conditions. Development of the disease largely depends on the host immune response, with pathogen characteristics having a less prominent role. Individuals with pneumonia often present with respiratory and systemic symptoms, and diagnosis is based on both clinical presentation and radiological findings. It is crucial to identify the causative pathogens, as delayed and inadequate antimicrobial therapy can lead to poor outcomes. New antibiotic and non-antibiotic therapies, in addition to rapid and accurate diagnostic tests that can detect pathogens and antibiotic resistance will improve the management of pneumonia.

Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia

We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.

Differential diagnoses of COVID-19 pneumonia: the current challenge for the radiologist-a pictorial essay

BACKGROUND

COVID-19 pneumonia represents the most severe pandemic of the twenty-first century and has crucial clinical, social and economical implications. The scientific community has focused attention and resources on clinical and radiological features of COVID-19 pneumonia. Few papers analysing the vast spectrum of differential diagnoses have been published.

MAIN BODY

Complexity of differential diagnosis lays in the evidence of similar radiological findings as ground-glass opacities, crazy paving pattern and consolidations in COVID-19 pneumonia and a multitude of other lung diseases. Differential diagnosis is and will be extremely important during and after the pandemic peak, when there are fewer COVID-19 pneumonia cases. The aim of our pictorial essay is to schematically present COVID-19 pneumonia most frequent differential diagnoses to help the radiologist face the current COVID-19 pneumonia challenge.

CONCLUSIONS

Clinical data, laboratory tests and imaging are pillars of a trident, which allows to reach a correct diagnosis in order to grant an excellent allocation of human and economical resources. The radiologist has a pivotal role in the early diagnosis of COVID-19 pneumonia because he may raise suspicion of the pathology and help to avoid COVID-19 virus spread.

When pneumonia is not COVID-19

During the COVID-19 epidemic, the prevalence of the disease means that practically any lung opacity on an X-ray could represent pneumonia due to infection with SARS-CoV-2. Nevertheless, atypical radiologic findings add weight to negative microbiological or serological tests. Likewise, outside the epidemic wave and with the return of other respiratory diseases, radiologists can play an important role in decision making about diagnoses, treatment, or preventive measures (isolation), provided they know the key findings for entities that can simulate COVID-19 pneumonia. Unifocal opacities or opacities located in upper lung fields and predominant airway involvement, in addition to other key radiologic and clinical findings detailed in this paper, make it necessary to widen the spectrum of possible diagnoses.

Infections in the older population: what do we know?

The incidence of infections increases with age and results in a higher risk of morbidity and mortality. This rise is not mainly related to chronological age per se but has been linked mostly to individual factors such as immunosenescence; the presence of comorbidities; the occurrence of geriatric syndromes such as poor nutrition, polypharmacy, and cognitive disorders; and the presence of functional impairment concomitant with environmental, healthcare-related and microbiological factors such as the increasing risk of multidrug-resistant microorganisms. The geriatric concept of frailty introduces a new approach for considering the risk of infection; this concept highlights the importance of functional status and is a more comprehensive and multicomponent approach that may help to reverse the vulnerability to stress. The aim of this article is to provide some typical hallmarks of infections among older adults in comparison to younger individuals. The main differences among the older population that are presented are an increased prevalence of infections and potential risk factors, a higher risk of carrying multidrug-resistant microorganisms, an increase in barriers to a prompt diagnosis related to atypical presentations and challenges with diagnostic tools, a higher risk of under- and over-diagnosis, a worse prognosis with a higher risk of acute and chronic complications and a particular need for better communication among all healthcare sectors as they are closely linked together.

When pneumonia is not COVID-19

During the COVID-19 epidemic, the prevalence of the disease means that practically any lung opacity on an X-ray could represent pneumonia due to infection with SARS-CoV-2. Nevertheless, atypical radiologic findings add weight to negative microbiological or serological tests. Likewise, outside the epidemic wave and with the return of other respiratory diseases, radiologists can play an important role in decision making about diagnoses, treatment, or preventive measures (isolation), provided they know the key findings for entities that can simulate COVID-19 pneumonia. Unifocal opacities or opacities located in upper lung fields and predominant airway involvement, in addition to other key radiologic and clinical findings detailed in this paper, make it necessary to widen the spectrum of possible diagnoses.

Multi-View Ensemble Convolutional Neural Network to Improve Classification of Pneumonia in Low Contrast Chest X-Ray Images

Pneumonia is one of the leading causes of childhood mortality worldwide. Chest x-ray (CXR) can aid the diagnosis of pneumonia, but in the case of low contrast images, it is important to include computational tools to aid specialists. Deep learning is an alternative because it can identify patterns automatically, even in low-resolution images. We propose herein a convolutional neural network (CNN) architecture with different training strategies towards detecting pneumonia on CXRs and distinguishing its subforms of bacteria and virus. We also evaluated different image pre-processing methods to improve the classification. This study used CXRs from pediatric patients from a public pneumonia CXR dataset. The pre-processing methods evaluated were image cropping and histogram equalization. To classify the images, we adopted the VGG16 CNN and replaced its fully-connected layers with a customized multilayer perceptron. With this architecture, we proposed and evaluated four different training strategies: original CXR image (baseline), chest-cavity-cropped image (A), and histogram-equalized segmented image (B). The last strategy method (C) implemented is based on ensemble between strategies A and B. The performance was assessed by the area under the ROC curve (AUC) with 95% confidence interval (CI), accuracy, sensitivity, specificity, and F1-score. The ensemble model C yielded the highest performances: AUC of 0.97 (CI: 0.96-0.99) to classify pneumonia vs. normal, and AUC of 0.91 (CI: 0.88-0.94) to classify bacterial vs. viral cases. All models that used pre-processed images showed higher AUC than baseline, which used the original CXR image. Image cropping and histogram equalization reduced irrelevant information from the exam, enhanced contrast, and was able to identify fine CXR texture details. The proposed ensemble model increased the representation of inflammatory patterns from bacteria and viruses with few epochs to train the deep CNNs.Clinical relevance- Deep learning can identify complex radiographic patterns in low contrast images due to pneumonia and distinguish its subforms of bacteria and virus. The correlation of imaging with lab results could accelerate the adoption of complementary exams to confirm the disease's cause.

Multimodality imaging of COVID-19 pneumonia: from diagnosis to follow-up. A comprehensive review

Due to its pandemic diffusion, SARS- CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) infection represents a global threat. Despite a multiorgan involvement has been described, pneumonia is the most common manifestation of COVID-19 (Coronavirus disease 2019) and it is associated with a high morbidity and a considerable mortality. Especially in the areas with high disease burden, chest imaging plays a crucial role to speed up the diagnostic process and to aid the patient management. The purpose of this comprehensive review is to understand the diagnostic capabilities and limitations of chest X-ray (CXR) and high-resolution computed tomography (HRCT) in defining the common imaging features of COVID-19 pneumonia and correlating them with the underlying pathogenic mechanisms. The evolution of lung abnormalities over time, the uncommon findings, the possible complications, and the main differential diagnosis occurring in the pandemic phase of SARS-CoV-2 infection are also discussed.

Dual-Sampling Attention Network for Diagnosis of COVID-19 From Community Acquired Pneumonia

The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has infected more than 1,436,000 people in more than 200 countries and territories as of April 9, 2020. Detecting COVID-19 at early stage is essential to deliver proper healthcare to the patients and also to protect the uninfected population. To this end, we develop a dual-sampling attention network to automatically diagnose COVID-19 from the community acquired pneumonia (CAP) in chest computed tomography (CT). In particular, we propose a novel online attention module with a 3D convolutional network (CNN) to focus on the infection regions in lungs when making decisions of diagnoses. Note that there exists imbalanced distribution of the sizes of the infection regions between COVID-19 and CAP, partially due to fast progress of COVID-19 after symptom onset. Therefore, we develop a dual-sampling strategy to mitigate the imbalanced learning. Our method is evaluated (to our best knowledge) upon the largest multi-center CT data for COVID-19 from 8 hospitals. In the training-validation stage, we collect 2186 CT scans from 1588 patients for a 5-fold cross-validation. In the testing stage, we employ another independent large-scale testing dataset including 2796 CT scans from 2057 patients. Results show that our algorithm can identify the COVID-19 images with the area under the receiver operating characteristic curve (AUC) value of 0.944, accuracy of 87.5%, sensitivity of 86.9%, specificity of 90.1%, and F1-score of 82.0%. With this performance, the proposed algorithm could potentially aid radiologists with COVID-19 diagnosis from CAP, especially in the early stage of the COVID-19 outbreak.

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.

CT differential diagnosis of COVID-19 and non-COVID-19 in symptomatic suspects: a practical scoring method

BACKGROUND

Although typical and atypical CT image findings of COVID-19 are reported in current studies, the CT image features of COVID-19 overlap with those of viral pneumonia and other respiratory diseases. Hence, it is difficult to make an exclusive diagnosis.

METHODS

Thirty confirmed cases of COVID-19 and forty-three cases of other aetiology or clinically confirmed non-COVID-19 in a general hospital were included. The clinical data including age, sex, exposure history, laboratory parameters and aetiological diagnosis of all patients were collected. Seven positive signs (posterior part/lower lobe predilection, bilateral involvement, rounded GGO, subpleural bandlike GGO, crazy-paving pattern, peripheral distribution, and GGO +/- consolidation) from significant COVID-19 CT image features and four negative signs (only one lobe involvement, only central distribution, tree-in-bud sign, and bronchial wall thickening) from other non-COVID-19 pneumonia were used. The scoring analysis of CT features was compared between the two groups (COVID-19 and non-COVID-19).

RESULTS

Older age, symptoms of diarrhoea, exposure history related to Wuhan, and a lower white blood cell and lymphocyte count were significantly suggestive of COVID-19 rather than non-COVID-19 (p < 0.05). The receiver operating characteristic (ROC) curve of the combined CT image features analysis revealed that the area under the curve (AUC) of the scoring system was 0.854. These cut-off values yielded a sensitivity of 56.67% and a specificity of 95.35% for a score > 4, a sensitivity of 100% and a specificity of 23.26% for a score > 0, and a sensitivity of 86.67% and a specificity of 67.44% for a score >  2.

CONCLUSIONS

With a simple and practical scoring system based on CT imaging features, we can make a hierarchical diagnosis of COVID-19 and non-COVID-19 with different management suggestions.

Attention-Guided Convolutional Neural Network for Detecting Pneumonia on Chest X-Rays

Pneumonia is a common infectious disease in the world. Its main diagnostic method is chest X-ray (CXR) examination. However, the high visual similarity between a large number of pathologies in CXR makes the interpretation and differentiation of pneumonia a challenge. In this paper, we propose an improved convolutional neural network (CNN) model for pneumonia detection. In order to guide the CNN to focus on disease-specific attended region, the pneumonia area of image is erased and marked as a non-pneumonia sample. In addition, transfer learning is used to segment the interest region of lungs to suppress background interference. The experimental results show that the proposed method is superior to the state-of-the-art object detection model in terms of accuracy and false positive rate.

Survey on deep learning for pulmonary medical imaging

As a promising method in artificial intelligence, deep learning has been proven successful in several domains ranging from acoustics and images to natural language processing. With medical imaging becoming an important part of disease screening and diagnosis, deep learning-based approaches have emerged as powerful techniques in medical image areas. In this process, feature representations are learned directly and automatically from data, leading to remarkable breakthroughs in the medical field. Deep learning has been widely applied in medical imaging for improved image analysis. This paper reviews the major deep learning techniques in this time of rapid evolution and summarizes some of its key contributions and state-of-the-art outcomes. The topics include classification, detection, and segmentation tasks on medical image analysis with respect to pulmonary medical images, datasets, and benchmarks. A comprehensive overview of these methods implemented on various lung diseases consisting of pulmonary nodule diseases, pulmonary embolism, pneumonia, and interstitial lung disease is also provided. Lastly, the application of deep learning techniques to the medical image and an analysis of their future challenges and potential directions are discussed.

Respiratory Virus Infections in Hematopoietic Cell Transplant Recipients

Highly immunocompromised pediatric and adult hematopoietic cell transplant (HCT) recipients frequently experience respiratory infections caused by viruses that are less virulent in immunocompetent individuals. Most of these infections, with the exception of rhinovirus as well as adenovirus and parainfluenza virus in tropical areas, are seasonal variable and occur before and after HCT. Infectious disease management includes sampling of respiratory specimens from nasopharyngeal washes or swabs as well as sputum and tracheal or tracheobronchial lavages. These are subjected to improved diagnostic tools including multiplex PCR assays that are routinely used allowing for expedient detection of all respiratory viruses. Disease progression along with high mortality is frequently associated with respiratory syncytial virus, parainfluenza virus, influenza virus, and metapneumovirus infections. In this review, we discuss clinical findings and the appropriate use of diagnostic measures. Additionally, we also discuss treatment options and suggest new drug formulations that might prove useful in treating respiratory viral infections. Finally, we shed light on the role of the state of immune reconstitution and on the use of immunosuppressive drugs on the outcome of infection.