Imaging of pneumonia: trends and algorithms

The Differential Diagnostic Value of Chest Computed Tomography for the Identification of Pathogens Causing Pulmonary Infections in Patients with Hematological Malignancies

Objective

The role of chest computed tomography (CT) in distinguishing the causative pathogens of pulmonary infections in patients with hematological malignancies (HM) is unclear. The aim of our study was to compare and assess the clinical characteristics, radiologic features and potential differential diagnostic value of CT in HM patients and other different immune statuses patients with pulmonary infections.

Methods

Patients were divided into immunocompetent (105 cases) and immunocompromised groups (99 cases) according to immune status. Immunocompromised patients included the HM group (63 cases) and the non-HM group (42 cases). The basic clinical data and CT findings were collected and statistically analyzed.

Results

Regarding the pathogen distribution, viral, Pneumocystis jirovecii and mixed infections were more common in the immunocompromised group than the immunocompetent (p < 0.01), but viral infections were more common in the HM group than in the non-HM group (p=0.013). Immunocompromised patients had more diverse CT findings and more serious lesions (mostly graded 2-4) than immunocompetent patients. The most common CT findings in HM patients were consolidation and ground-glass opacities (GGO), which were also found in the non-HM group. The overall diagnostic accuracy of CT was lower in immunocompromised patients than in immunocompetent patients (25.7% vs 50.5%, p< 0.01). CT had better diagnostic efficacy for fungi and Pneumocystis jirovecii in HM patients.

Conclusion

CT diagnosis is less efficient in distinguishing the causative pathogens of HM patients. However, CT can help distinguish fungal pneumonia and Pneumocystis jirovecii pneumonia in HM patients.

Clinical Relevance Statement

Our study might facilitate clinical decision-making in fungal pneumonia and Pneumocystis jirovecii pneumonia in HM patients.

Role of artificial intelligence in critical care nutrition support and research

Nutrition plays a key role in the comprehensive care of critically ill patients. Determining optimal nutrition strategy, however, remains a subject of intense debate. Artificial intelligence (AI) applications are becoming increasingly common in medicine, and specifically in critical care, driven by the data-rich environment of intensive care units. In this review, we will examine the evidence regarding the application of AI in critical care nutrition. As of now, the use of AI in critical care nutrition is relatively limited, with its primary emphasis on malnutrition screening and tolerance of enteral nutrition. Despite the current scarcity of evidence, the potential for AI for more personalized nutrition management for critically ill patients is substantial. This stems from the ability of AI to integrate multiple data streams reflecting patients' changing needs while addressing inherent heterogeneity. The application of AI in critical care nutrition holds promise for optimizing patient outcomes through tailored and adaptive nutrition interventions. A successful implementation of AI, however, necessitates a multidisciplinary approach, coupled with careful consideration of challenges related to data management, financial aspects, and patient privacy.

Data-driven classification and explainable-AI in the field of lung imaging

Detecting lung diseases in medical images can be quite challenging for radiologists. In some cases, even experienced experts may struggle with accurately diagnosing chest diseases, leading to potential inaccuracies due to complex or unseen biomarkers. This review paper delves into various datasets and machine learning techniques employed in recent research for lung disease classification, focusing on pneumonia analysis using chest X-ray images. We explore conventional machine learning methods, pretrained deep learning models, customized convolutional neural networks (CNNs), and ensemble methods. A comprehensive comparison of different classification approaches is presented, encompassing data acquisition, preprocessing, feature extraction, and classification using machine vision, machine and deep learning, and explainable-AI (XAI). Our analysis highlights the superior performance of transfer learning-based methods using CNNs and ensemble models/features for lung disease classification. In addition, our comprehensive review offers insights for researchers in other medical domains too who utilize radiological images. By providing a thorough overview of various techniques, our work enables the establishment of effective strategies and identification of suitable methods for a wide range of challenges. Currently, beyond traditional evaluation metrics, researchers emphasize the importance of XAI techniques in machine and deep learning models and their applications in classification tasks. This incorporation helps in gaining a deeper understanding of their decision-making processes, leading to improved trust, transparency, and overall clinical decision-making. Our comprehensive review serves as a valuable resource for researchers and practitioners seeking not only to advance the field of lung disease detection using machine learning and XAI but also from other diverse domains.

CMM: A CNN-MLP Model for COVID-19 Lesion Segmentation and Severity Grading

In this paper, a CNN-MLP model (CMM) is proposed for COVID-19 lesion segmentation and severity grading in CT images. The CMM starts by lung segmentation using UNet, and then segmenting the lesion from the lung region using a multi-scale deep supervised UNet (MDS-UNet), finally implementing the severity grading by a multi-layer preceptor (MLP). In MDS-UNet, shape prior information is fused with the input CT image to reduce the searching space of the potential segmentation outputs. The multi-scale input compensates for the loss of edge contour information in convolution operations. In order to enhance the learning of multiscale features, the multi-scale deep supervision extracts supervision signals from different upsampling points on the network. In addition, it is empirical that the lesion which has a whiter and denser appearance tends to be more severe in the COVID-19 CT image. So, the weighted mean gray-scale value (WMG) is proposed to depict this appearance, and together with the lung and lesion area to serve as input features for the severity grading in MLP. To improve the precision of lesion segmentation, a label refinement method based on the Frangi vessel filter is also proposed. Comparative experiments on COVID-19 public datasets show that our proposed CMM achieves high accuracy on COVID-19 lesion segmentation and severity grading.

Current Diagnostic Techniques for Pneumonia: A Scoping Review

Community-acquired pneumonia is one of the most lethal infectious diseases, especially for infants and the elderly. Given the variety of causative agents, the accurate early detection of pneumonia is an active research area. To the best of our knowledge, scoping reviews on diagnostic techniques for pneumonia are lacking. In this scoping review, three major electronic databases were searched and the resulting research was screened. We categorized these diagnostic techniques into four classes (i.e., lab-based methods, imaging-based techniques, acoustic-based techniques, and physiological-measurement-based techniques) and summarized their recent applications. Major research has been skewed towards imaging-based techniques, especially after COVID-19. Currently, chest X-rays and blood tests are the most common tools in the clinical setting to establish a diagnosis; however, there is a need to look for safe, non-invasive, and more rapid techniques for diagnosis. Recently, some non-invasive techniques based on wearable sensors achieved reasonable diagnostic accuracy that could open a new chapter for future applications. Consequently, further research and technology development are still needed for pneumonia diagnosis using non-invasive physiological parameters to attain a better point of care for pneumonia patients.

Pulmonary Infection

Pneumonia is a significant cause of morbidity and mortality in the community and hospital settings. Bacterial, viral, mycobacterial, and fungal pathogens are all potential causative agents of pulmonary infection. Chest radiographs and computed tomography are frequently utilized in the assessment of pneumonia. Learning the imaging patterns of different potential organisms allows the radiologist to formulate an appropriate differential diagnosis. An organism-based approach is used to discuss the imaging findings of different etiologies of pulmonary infection.

Lung ultrasound and procalcitonin, improving antibiotic management and avoiding radiation exposure in pediatric critical patients with bacterial pneumonia: a randomized clinical trial

BACKGROUND

Pneumonia is a major public health problem with an impact on morbidity and mortality. Its management still represents a challenge. The aim was to determine whether a new diagnostic algorithm combining lung ultrasound (LUS) and procalcitonin (PCT) improved pneumonia management regarding antibiotic use, radiation exposure, and associated costs, in critically ill pediatric patients with suspected bacterial pneumonia (BP).

METHODS

Randomized, blinded, comparative effectiveness clinical trial. Children < 18y with suspected BP admitted to the PICU from September 2017 to December 2019, were included. PCT was determined at admission. Patients were randomized into the experimental group (EG) and control group (CG) if LUS or chest X-ray (CXR) were done as the first image test, respectively. Patients were classified: 1.LUS/CXR not suggestive of BP and PCT < 1 ng/mL, no antibiotics were recommended; 2.LUS/CXR suggestive of BP, regardless of the PCT value, antibiotics were recommended; 3.LUS/CXR not suggestive of BP and PCT > 1 ng/mL, antibiotics were recommended.

RESULTS

194 children were enrolled, 113 (58.2%) females, median age of 134 (IQR 39-554) days. 96 randomized into EG and 98 into CG. 1. In 75/194 patients the image test was not suggestive of BP with PCT < 1 ng/ml; 29/52 in the EG and 11/23 in the CG did not receive antibiotics. 2. In 101 patients, the image was suggestive of BP; 34/34 in the EG and 57/67 in the CG received antibiotics. Statistically significant differences between groups were observed when PCT resulted < 1 ng/ml (p = 0.01). 3. In 18 patients the image test was not suggestive of BP but PCT resulted > 1 ng/ml, all of them received antibiotics. A total of 0.035 mSv radiation/patient was eluded. A reduction of 77% CXR/patient was observed. LUS did not significantly increase costs.

CONCLUSIONS

Combination of LUS and PCT showed no risk of mistreating BP, avoided radiation and did not increase costs. The algorithm could be a reliable tool for improving pneumonia management.

CLINICAL TRIAL REGISTRATION

NCT04217980.

Approach towards surveillance-based diagnosis of acute respiratory illness in India: Expert recommendations

BACKGROUND

Emerging infectious diseases, often zoonotic, demand a collaborative "One-Health" surveillance approach due to human activities. The need for standardized diagnostic and surveillance algorithms is emphasized to address the difficulty in clinical differentiation and curb antimicrobial resistance.

OBJECTIVE

The present recommendations are comprehensive diagnostic and surveillance algorithm for ARIs, developed by the Indian Council of Medical Research (ICMR), which aims to enhance early detection and treatment with improved surveillance. This algorithm shall be serving as a blueprint for respiratory infections landscape in the country and early detection of surge of respiratory infections in the country.

CONTENT

The ICMR has risen up to the threat of emerging and re-emerging infections. Here, we seek to recommend a structured approach for diagnosing respiratory illnesses. The recommendations emphasize the significance of prioritizing respiratory pathogens based on factors such as the frequency of occurrence (seasonal or geographical), disease severity, ease of diagnosis and public health importance. The proposed surveillance-based diagnostic algorithm for ARI relies on a combination of gold-standard conventional methods, innovative serological and molecular techniques, as well as radiological approaches, which collectively contribute to the detection of various causative agents. The diagnostic part of the integrated algorithm can be dealt at the local microbiology laboratory of the healthcare facility with the few positive and negative specimens shipped to linked viral disease research laboratories (VRDLs) and other ICMR designated laboratories for genome characterisation, cluster identification and identification of novel agents.

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI

Heterogeneous data is endemic due to the use of diverse models and settings of devices by hospitals in the field of medical imaging. However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection without the demand to modify the existing model structures or to share any private data. Here, we proposed PPPML-HMI, a novel open-source learning paradigm for personalized and privacy-preserving federated heterogeneous medical image analysis. To our best knowledge, personalization and privacy protection were discussed simultaneously for the first time under the federated scenario by integrating the PerFedAvg algorithm and designing the novel cyclic secure aggregation with the homomorphic encryption algorithm. To show the utility of PPPML-HMI, we applied it to a simulated classification task namely the classification of healthy people and patients from the RAD-ChestCT Dataset, and one real-world segmentation task namely the segmentation of lung infections from COVID-19 CT scans. Meanwhile, we applied the improved deep leakage from gradients to simulate adversarial attacks and showed the strong privacy-preserving capability of PPPML-HMI. By applying PPPML-HMI to both tasks with different neural networks, a varied number of users, and sample sizes, we demonstrated the strong generalizability of PPPML-HMI in privacy-preserving federated learning on heterogeneous medical images.

Diagnostic significance of HRCT imaging features in adult mycoplasma pneumonia: a retrospective study

Mycoplasma pneumoniae pneumonia (MPP) often overlaps with the clinical manifestations and chest imaging manifestations of other types of community-acquired pneumonia (CAP). We retrospectively analyzed the clinical and imaging data of a group of patients with CAP, summarized their clinical and imaging characteristics, and discussed the diagnostic significance of their certain HRCT findings. The HRCT findings of CAP researched in our study included tree-in-bud sign (TIB), ground-glass opacity (GGO), tree fog sign (TIB + GGO), bronchial wall thickening, air-bronchogram, pleural effusion and cavity. The HRCT findings of all cases were analyzed. Among the 200 cases of MPP, 174 cases showed the TIB, 193 showed the GGO, 175 showed the tree fog sign, 181 lacked air-bronchogram. In case taking the tree fog sign and lack of air-bronchogram simultaneously as an index to distinguish MPP from OCAP, the sensitivity was 87.5%, the specificity was 97.5%, the accuracy was 92.5%. This study showed that that specific HRCT findings could be used to distinguish MPP from OCAP. The combined HRCT findings including the tree fog sign and lacked air-bronchogram simultaneously would contribute to a more accurate diagnosis of MPP.

Diagnosis and detection of pneumonia using weak-label based on X-ray images: a multi-center study

PURPOSE

Development and assessment the deep learning weakly supervised algorithm for the classification and detection pneumonia via X-ray.

METHODS

This retrospective study analyzed two publicly available dataset that contain X-ray images of pneumonia cases and normal cases. The first dataset from Guangzhou Women and Children's Medical Center. It contains a total of 5,856 X-ray images, which are divided into training, validation, and test sets with 8:1:1 ratio for algorithm training and testing. The deep learning algorithm ResNet34 was employed to build diagnostic model. And the second public dataset were collated by researchers from Qatar University and the University of Dhaka along with collaborators from Pakistan and Malaysia and some medical doctors. A total of 1,300 images of COVID-19 positive cases, 1,300 normal images and 1,300 images of viral pneumonia for external validation. Class activation map (CAM) were used to location the pneumonia lesions.

RESULTS

The ResNet34 model for pneumonia detection achieved an AUC of 0.9949 [0.9910-0.9981] (with an accuracy of 98.29% a sensitivity of 99.29% and a specificity of 95.57%) in the test dataset. And for external validation dataset, the model obtained an AUC of 0.9835[0.9806-0.9864] (with an accuracy of 94.62%, a sensitivity of 92.35% and a specificity of 99.15%). Moreover, the CAM can accurately locate the pneumonia area.

CONCLUSION

The deep learning algorithm can accurately detect pneumonia and locate the pneumonia area based on weak supervision information, which can provide potential value for helping radiologists to improve their accuracy of detection pneumonia patients through X-ray images.

Common and Uncommon CT Findings in CVID-Related GL-ILD: Correlations with Clinical Parameters, Therapeutic Decisions and Potential Implications in the Differential Diagnosis

PURPOSE

To investigate computed tomography (CT) findings of Granulomatous Lymphocytic Interstitial Lung Disease (GL-ILD) in Common Variable Immunodeficiency (CVID), also in comparison with non-GL-ILD abnormalities, correlating GL-ILD features with functional/immunological parameters and looking for GL-ILD therapy predictive elements.

METHODS

CT features of 38 GL-ILD and 38 matched non-GL-ILD subjects were retrospectively described. Correlations of GL-ILD features with functional/immunological features were assessed. A logistic regression was performed to find a predictive model of GL-ILD therapeutic decisions.

RESULTS

Most common GL-ILD CT findings were bronchiectasis, non-perilymphatic nodules, consolidations, Ground Glass Opacities (GGO), bands and enlarged lymphnodes. GL-ILD was usually predominant in lower fields. Multiple small nodules (≤10 mm), consolidations, reticulations and fibrotic ILD are more indicative of GL-ILD. Bronchiectasis, GGO, Reticulations and fibrotic ILD correlated with decreased lung performance. Bronchiectasis, GGO and fibrotic ILD were associated with low IgA levels, whereas high CD4+ T cells percentage was related to GGO. Twenty out of 38 patients underwent GL-ILD therapy. A model combining Marginal Zone (MZ) B cells percentage, IgA levels, lower field consolidations and lymphnodes enlargement showed a good discriminatory capacity with regards to GL-ILD treatment.

CONCLUSIONS

GL-ILD is a lower field predominant disease, commonly characterized by bronchiectasis, non-perilymphatic small nodules, consolidations, GGO and bands. Multiple small nodules, consolidations, reticulations and fibrotic ILD may suggest the presence of GL-ILD in CVID. MZ B cells percentage, IgA levels at diagnosis, lower field consolidations and mediastinal lymphnodes enlargement may predict the need of a specific GL-ILD therapy.

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.

Classification of spinal curvature types using radiography images: deep learning versus classical methods

Scoliosis is a spinal abnormality that has two types of curves (C-shaped or S-shaped). The vertebrae of the spine reach an equilibrium at different times, which makes it challenging to detect the type of curves. In addition, it may be challenging to detect curvatures due to observer bias and image quality. This paper aims to evaluate spinal deformity by automatically classifying the type of spine curvature. Automatic spinal curvature classification is performed using SVM and KNN algorithms, and pre-trained Xception and MobileNetV2 networks with SVM as the final activation function to avoid vanishing gradient. Different feature extraction methods should be used to investigate the SVM and KNN machine learning methods in detecting the curvature type. Features are extracted through the representation of radiographic images. These representations are of two groups: (i) Low-level image representation techniques such as texture features and (ii) local patch-based representations such as Bag of Words (BoW). Such features are utilized by various algorithms for classification by SVM and KNN. The feature extraction process is automated in pre-trained deep networks. In this study, 1000 anterior-posterior (AP) radiographic images of the spine were collected as a private dataset from Shafa Hospital, Tehran, Iran. The transfer learning was used due to the relatively small private dataset of anterior-posterior radiology images of the spine. Based on the results of these experiments, pre-trained deep networks were found to be approximately 10% more accurate than classical methods in classifying whether the spinal curvature is C-shaped or S-shaped. As a result of automatic feature extraction, it has been found that the pre-trained Xception and mobilenetV2 networks with SVM as the final activation function for controlling the vanishing gradient perform better than the classical machine learning methods of classification of spinal curvature types.

Schematic approach to the diagnosis of multifocal lung opacities in the emergency department

Radiologists in the emergency department must be prepared to deal with any type of disease in any organ at any time. Many entities involving the chest can result in patients' presenting at the emergency department. This chapter deals with entities that manifest with multifocal lung opacities and that can be mistaken for pneumonia. To facilitate their identification, this chapter approaches these entities by considering their most characteristic distribution on chest X-rays, the main diagnostic modality used for thoracic problems in the emergency department. Our schematic approach includes the key findings in patients' personal histories, clinical examination, laboratory tests, and imaging studies that can be available during the initial workup.

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.

A Review on Detection of Pneumonia in Chest X-ray Images Using Neural Networks

The health organisation has suffered from the lack of diagnosis support systems and physicians in India. Further, the physicians are struggling to treat many patients, and the hospitals also have the lack of a radiologist especially in rural areas; thus, almost all cases are handled by a single physician, leading to many misdiagnoses. Computer aided diagnostic systems are being developed to address this problem. The current study aimed to review the different methods to detect pneumonia using neural networks and compare their approach and results. For the best comparisons, only papers with the same data set Chest X-ray14 are studied.

Deep Learning Models to Predict Fatal Pneumonia Using Chest X-Ray Images

Background and Aims. Chest X-ray (CXR) is indispensable to the assessment of severity, diagnosis, and management of pneumonia. Deep learning is an artificial intelligence (AI) technology that has been applied to the interpretation of medical images. This study investigated the feasibility of classifying fatal pneumonia based on CXR images using deep learning models on publicly available platforms. Methods. CXR images of patients with pneumonia at diagnosis were labeled as fatal or nonfatal based on medical records. We applied CXR images from 1031 patients with nonfatal pneumonia and 243 patients with fatal pneumonia for training and self-evaluation of the deep learning models. All labeled CXR images were randomly allocated to the training, validation, and test datasets of deep learning models. Data augmentation techniques were not used in this study. We created two deep learning models using two publicly available platforms. Results. The first model showed an area under the precision-recall curve of 0.929 with a sensitivity of 50.0% and a specificity of 92.4% for classifying fatal pneumonia. We evaluated the performance of our deep learning models using sensitivity, specificity, PPV, negative predictive value (NPV), accuracy, and F1 score. Using the external validation test dataset of 100 CXR images, the sensitivity, specificity, accuracy, and F1 score were 68.0%, 86.0%, 77.0%, and 74.7%, respectively. In the original dataset, the performance of the second model showed a sensitivity, specificity, and accuracy of 39.6%, 92.8%, and 82.7%, respectively, while external validation showed values of 38.0%, 92.0%, and 65.0%, respectively. The F1 score was 52.1%. These results were comparable to those obtained by respiratory physicians and residents. Conclusions. The deep learning models yielded good accuracy in classifying fatal pneumonia. By further improving the performance, AI could assist physicians in the severity assessment of patients with pneumonia.

A novel infrasound and audible machine-learning approach for the diagnosis of COVID-19

The COVID-19 outbreak has rapidly spread around the world, causing a global public health and economic crisis. A critical limitation in detecting COVID-19 related pneumonia is that it is often manifested as a “silent pneumonia”, i.e., pulmonary auscultation, using a standard stethoscope, sounds "normal". Chest CT is the gold standard for detecting COVID-19 pneumonia; however, radiation exposure, availability and cost preclude its utilization as a screening tool for COVID-19 pneumonia. In this study we hypothesized that COVID-19 pneumonia, “silent” to the human ear using a standard stethoscope, is detectable using a full spectrum auscultation device that contains a machine-learning analysis.

Lung sounds signals were acquired, using a novel full spectrum (3–2,000Hz) stethoscope, from 164 patients with COVID-19 pneumonia, 61 non-COVID-19 pneumonia and 141 healthy subjects. A machine-learning classifier was constructed, and the data was classified into 3 groups: 1. Normal lung sounds 2. COVID-19 pneumonia 3. Non-COVID-19 pneumonia.

Standard auscultation found that 72% of the non-COVID-19 pneumonia patients had abnormal lung sounds, compared to only 25% for the COVID-19 pneumonia patients. The classifier's sensitivity and specificity for the detection of COVID-19 pneumonia were 97% and 93%, respectively, when analyzing the sound and infrasound data, and they were reduced to 93% and 80% without the infrasound data (p<0.01 difference in ROC with and without infrasound).

This study reveals that useful clinical information exists in the infrasound spectrum of COVID-19 related pneumonia, and machine-learning analysis applied to the full spectrum of lung sounds is useful in its detection.

Unmet needs in pneumonia research: a comprehensive approach by the CAPNETZ study group

Introduction

Despite improvements in medical science and public health, mortality of community-acquired pneumonia (CAP) has barely changed throughout the last 15 years. The current SARS-CoV-2 pandemic has once again highlighted the central importance of acute respiratory infections to human health. The “network of excellence on Community Acquired Pneumonia” (CAPNETZ) hosts the most comprehensive CAP database worldwide including more than 12,000 patients. CAPNETZ connects physicians, microbiologists, virologists, epidemiologists, and computer scientists throughout Europe. Our aim was to summarize the current situation in CAP research and identify the most pressing unmet needs in CAP research.

Methods

To identify areas of future CAP research, CAPNETZ followed a multiple-step procedure. First, research members of CAPNETZ were individually asked to identify unmet needs. Second, the top 100 experts in the field of CAP research were asked for their insights about the unmet needs in CAP (Delphi approach). Third, internal and external experts discussed unmet needs in CAP at a scientific retreat.

Results

Eleven topics for future CAP research were identified: detection of causative pathogens, next generation sequencing for antimicrobial treatment guidance, imaging diagnostics, biomarkers, risk stratification, antiviral and antibiotic treatment, adjunctive therapy, vaccines and prevention, systemic and local immune response, comorbidities, and long-term cardio-vascular complications.

Conclusion

Pneumonia is a complex disease where the interplay between pathogens, immune system and comorbidities not only impose an immediate risk of mortality but also affect the patients’ risk of developing comorbidities as well as mortality for up to a decade after pneumonia has resolved. Our review of unmet needs in CAP research has shown that there are still major shortcomings in our knowledge of CAP.

Advancement of deep learning in pneumonia/Covid-19 classification and localization: A systematic review with qualitative and quantitative analysis

Around 450 million people are affected by pneumonia every year, which results in 2.5 million deaths. Coronavirus disease 2019 (Covid-19) has also affected 181 million people, which led to 3.92 million casualties. The chances of death in both of these diseases can be significantly reduced if they are diagnosed early. However, the current methods of diagnosing pneumonia (complaints + chest X-ray) and Covid-19 (real-time polymerase chain reaction) require the presence of expert radiologists and time, respectively. With the help of deep learning models, pneumonia and Covid-19 can be detected instantly from chest X-rays or computerized tomography (CT) scans. The process of diagnosing pneumonia/Covid-19 can become faster and more widespread. In this paper, we aimed to elicit, explain, and evaluate qualitatively and quantitatively all advancements in deep learning methods aimed at detecting community-acquired pneumonia, viral pneumonia, and Covid-19 from images of chest X-rays and CT scans. Being a systematic review, the focus of this paper lies in explaining various deep learning model architectures, which have either been modified or created from scratch for the task at hand. For each model, this paper answers the question of why the model is designed the way it is, the challenges that a particular model overcomes, and the tradeoffs that come with modifying a model to the required specifications. A grouped quantitative analysis of all models described in the paper is also provided to quantify the effectiveness of different models with a similar goal. Some tradeoffs cannot be quantified and, hence, they are mentioned explicitly in the qualitative analysis, which is done throughout the paper. By compiling and analyzing a large quantum of research details in one place with all the data sets, model architectures, and results, we aimed to provide a one-stop solution to beginners and current researchers interested in this field.

CXGNet: A tri-phase chest X-ray image classification for COVID-19 diagnosis using deep CNN with enhanced grey-wolf optimizer

The coronavirus disease 2019 (COVID-19) epidemic had a significant impact on daily life in many nations and global public health. COVID's quick spread has become one of the biggest disruptive calamities in the world. In the fight against COVID-19, it's critical to keep a close eye on the initial stage of infection in patients. Furthermore, early COVID-19 discovery by precise diagnosis, especially in patients with no evident symptoms, may reduce the patient's death rate and can stop the spread of COVID-19. When compared to CT images, chest X-ray (CXR) images are now widely employed for COVID-19 diagnosis since CXR images contain more robust features of the lung. Furthermore, radiologists can easily diagnose CXR images because of its operating speed and low cost, and it is promising for emergency situations and therapy. This work proposes a tri-stage CXR image based COVID-19 classification model using deep learning convolutional neural networks (DLCNN) with an optimal feature selection technique named as enhanced grey-wolf optimizer with genetic algorithm (EGWO-GA), which is denoted as CXGNet. The proposed CXGNet is implemented as multiple classes, such as 4-class, 3-class, and 2-class models based on the diseases. Extensive simulation outcome discloses the superiority of the proposed CXGNet model with enhanced classification accuracy of 94.00% for the 4-class model, 97.05% of accuracy for the 3-class model, and 100% accuracy for the 2-class model as compared to conventional methods.

An efficient deep learning-based framework for tuberculosis detection using chest X-ray images

Early diagnosis of tuberculosis (TB) is an essential and challenging task to prevent disease, decrease mortality risk, and stop transmission to other people. The chest X-ray (CXR) is the top choice for lung disease screening in clinics because it is cost-effective and easily accessible in most countries. However, manual screening of CXR images is a heavy burden for radiologists, resulting in a high rate of inter-observer variances. Hence, proposing a cost-effective and accurate computer aided diagnosis (CAD) system for TB diagnosis is challenging for researchers. In this research, we proposed an efficient and straightforward deep learning network called TBXNet, which can accurately classify a large number of TB CXR images. The network is based on five dual convolutions blocks with varying filter sizes of 32, 64, 128, 256 and 512, respectively. The dual convolution blocks are fused with a pre-trained layer in the fusion layer of the network. In addition, the pre-trained layer is utilized for transferring pre-trained knowledge into the fusion layer. The proposed TBXNet has achieved an accuracy of 98.98%, and 99.17% on Dataset A and Dataset B, respectively. Furthermore, the generalizability of the proposed work is validated against Dataset C, which is based on normal, tuberculous, pneumonia, and COVID-19 CXR images. The TBXNet has obtained the highest results in Precision (95.67%), Recall (95.10%), F1-score (95.38%), and Accuracy (95.10%), which is comparatively better than all other state-of-the-art methods.

Severe influenza A in a Tunisian ICU sentinel SARI centre: Epidemiological and clinical features

Introduction

Influenza A virus infection is a contagious acute respiratory infection which mostly evolves in an epidemic form, less frequently as pandemic outbreaks. It can take a severe clinical form that needs to be managed in intensive care unit (ICU). The aim of this study was to describe the epidemiological and clinical aspects of influenza A, then to determine independent predictive factors of ICU mortality in Abderrahmen Mami hospital, Ariana, Tunisia.

Methods

It was a single-center study, including all hospitalized patients in intensive care, between November 1^st, 2009 and October 31^st, 2019, with influenza A virus infection. We recorded demographic, clinical and biological data, evolving features; then multivariate analysis of the predictive factors of ICU mortality was realized.

Results

During the study period (10 consecutive seasons), 120 patients having severe Influenza A were admitted (Proportion = 2.5%) from all hospitalized patients, with a median age of 48 years and a gender-ratio of 1.14. Among women, 14 were pregnant. Only 7 patients (5.8%) have had seasonal flu vaccine during the year before ICU admission. The median values of the Simplified Acute Physiology Score II, Acute Physiologic and Chronic Health Evaluation II and Sepsis-related Organ Failure Assessment were respectively 26, 10 and 3. Virus strains identified with polymerase chain reaction were H₁N₁ pdm09 (84.2%) and H₃N₂ (15.8%). Antiviral therapy was prescribed in 88 (73.3%) patients. A co-infection was recorded in 19 cases: bacterial (n = 17) and aspergillaire (n = 2). An acute respiratory distress syndrome (ARDS) was diagnosed in 82 patients. Non-invasive ventilation (NIV) was conducted for 72 (60%) patients with success in 34 cases. Endotracheal intubation was performed in 59 patients with median duration of invasive mechanical ventilation 8 [3.25–13] days. The most frequent complications were acute kidney injury (n = 50, 41.7%), shock (n = 48, 40%), hospital-acquired infections (n = 46, 38.8%) and thromboembolic events (n = 19, 15.8%). The overall ICU mortality rate was of 31.7% (deceased n = 38). Independent predictive factors of ICU mortality identified were: age above 56 years (OR = 7.417; IC_95% [1.474–37.317]; p = 0.015), PaO₂/FiO₂ ≤ 95 mmHg (OR = 9.078; IC_95% [1.636–50.363]; p = 0.012) and lymphocytes count ≤ 1.325 10⁹/L (OR = 10.199; IC_95% [1.550–67.101]; p = 0.016).

Conclusion

Influenza A in ICU is not uncommon, even in A(H1N1) dominant seasons; its management is highly demanding. It is responsible for considerable morbi-mortality especially in elderly patients.

Fungal colonization and infections in patients with COVID-19 in intensive care units: A real-life experience at a tertiary-care hospital

PURPOSE

To evaluate the management of patients with COVID-19 in the intensive care units (ICUs) with fungal infection/colonization and to highlight diagnostic problems in these patients.

METHODS

We included all patients with a COVID-19 diagnosis who were aged ≥18 years and followed in the ICU for the first 8 months. Patient data were obtained from medical records. We compared the risk factors, laboratory data, and outcomes of patients with fungal infection/colonization.

RESULTS

A total of 118 patients (81 men and 37 women) were included. The mean age was 70.3 ± 14.8 (35-94) years. Of the patients, 79 (66.9%) patients were ≥65 years old. Fungal infection/colonization was detected in 39 (33.1%) patients. Fungi were isolated from 34 (28.8%) patients. Ten fungal species were isolated from 51 samples (the most common being Candida albicans). Three patients (2.5%) had proven candidemia. We observed two (1.7%) possible cases of COVID-19-associated pulmonary aspergillosis (CAPA). Eighteen patients (15.3%) underwent antifungal therapy. The risk of fungal infection/colonization increased as the duration of invasive mechanical ventilation increased. The fatality rate was 61.9% and increased with age and the use of mechanical ventilation. The fatality rate was 4.2-times-higher and the use of mechanical ventilation was 35.9-times-higher in the patients aged ≥65 years than in the patients aged <65 years. No relationship was found between fungal colonization/infection, antifungal treatment, and the fatality rate.

CONCLUSION

During the pandemic, approximately one-third of the patients in ICUs exhibited fungal infection/colonization. Candida albicans was the most common species of fungal infection as in the pre-pandemic area. Because of the cross-contamination risk, we performed diagnostic bronchoscopy and control thorax computed tomography during the ICU stay, and our patients mainly received empirical antifungal therapy.

Alert Germ Infections: Chest X-ray and CT Findings in Hospitalized Patients Affected by Multidrug-Resistant Acinetobacter baumannii Pneumonia

Acinetobacter baumannii (Ab) is an opportunistic Gram-negative pathogen intrinsically resistant to many antimicrobials. The aim of this retrospective study was to describe the imaging features on chest X-ray (CXR) and computed tomography (CT) scans in hospitalized patients with multidrug-resistant (MDR) Ab pneumonia. CXR and CT findings were graded on a three-point scale: 1 represents normal attenuation, 2 represents ground-glass attenuation, and 3 represents consolidation. For each lung zone, with a total of six lung zones in each patient, the extent of disease was graded using a five-point scale: 0, no involvement; 1, involving 25% of the zone; 2, 25−50%; 3, 50−75%; and 4, involving >75% of the zone. Points from all zones were added for a final total cumulative score ranging from 0 to 72. Among 94 patients who tested positive for MDR Ab and underwent CXR (males 52.9%, females 47.1%; mean age 64.2 years; range 1−90 years), 68 patients underwent both CXR and chest CT examinations. The percentage of patients with a positive CT score was significantly higher than that obtained on CXR (67.65% > 35.94%, p-value = 0.00258). CT score (21.88 ± 15.77) was significantly (p-value = 0.0014) higher than CXR score (15.06 ± 18.29). CXR and CT revealed prevalent bilateral abnormal findings mainly located in the inferior and middle zones of the lungs. They primarily consisted of peripheral ground-glass opacities and consolidations which predominated on CXR and CT, respectively.

Ultra-low-dose CT versus chest X-ray for patients suspected of pulmonary disease at the emergency department: a multicentre randomised clinical trial

BACKGROUND

Chest CT displays chest pathology better than chest X-ray (CXR). We evaluated the effects on health outcomes of replacing CXR by ultra-low-dose chest-CT (ULDCT) in the diagnostic work-up of patients suspected of non-traumatic pulmonary disease at the emergency department.

METHODS

Pragmatic, multicentre, non-inferiority randomised clinical trial in patients suspected of non-traumatic pulmonary disease at the emergency department. Between 31 January 2017 and 31 May 2018, every month, participating centres were randomly allocated to using ULDCT or CXR. Primary outcome was functional health at 28 days, measured by the Short Form (SF)-12 physical component summary scale score (PCS score), non-inferiority margin was set at 1 point. Secondary outcomes included hospital admission, hospital length of stay (LOS) and patients in follow-up because of incidental findings.

RESULTS

2418 consecutive patients (ULDCT: 1208 and CXR: 1210) were included. Mean SF-12 PCS score at 28 days was 37.0 for ULDCT and 35.9 for CXR (difference 1.1; 95% lower CI: 0.003). After ULDCT, 638/1208 (52.7%) patients were admitted (median LOS of 4.8 days; IQR 2.1-8.8) compared with 659/1210 (54.5%) patients after CXR (median LOS 4.6 days; IQR 2.1-8.8). More ULDCT patients were in follow-up because of incidental findings: 26 (2.2%) versus 4 (0.3%).

CONCLUSIONS

Short-term functional health was comparable between ULDCT and CXR, as were hospital admissions and LOS, but more incidental findings were found in the ULDCT group. Our trial does not support routine use of ULDCT in the work-up of patients suspected of non-traumatic pulmonary disease at the emergency department.

TRIAL REGISTRATION NUMBER

NTR6163.

Imaging Approach to Pulmonary Infections in the Immunocompromised Patient

Pulmonary infections are the major cause of morbidity and mortality in immunocompromised patients and almost one-third of intensive care unit patients with pulmonary infections belong to the immunocompromised category. Multiple organisms may simultaneously infect an immunocompromised patient and the overwhelming burden of mixed infections further predisposes critically ill patients to acute hypoxemic respiratory failure. Notwithstanding that lung ultrasound is coming into vogue, the primary imaging investigation is a chest radiograph, followed by thoracic CT scan. This review based on our experience at tertiary care teaching hospitals provides insights into the spectrum of imaging features of various pulmonary infections occurring in immunocompromised patients. This review is unique as, firstly, the imaging spectrum described by us is categorized on basis of the etiological infective agent, comprehensively and emphatically correlated with the clinical setting of the patient. Secondly, a characteristic imaging pattern is emphasized in the clinical setting-imaging-pattern conglomerate, to highlight the most likely diagnosis possible in such a combination. Thirdly, the simulating conditions for a relevant differential diagnosis are discussed in each section. Fourthly, not only are the specific diagnostic and tissue sampling techniques for confirmation of the suspected etiological agent described, but the recommended pharmaco-therapeutic agents are also enumerated, so as to provide a more robust insight to the radiologist. Last but not the least, we summarize and conclude with a diagnostic algorithm, derived by us from the characteristic illustrative cases. The proposed algorithm, illustrated as a flowchart, emphasizes a diagnostic imaging approach comprising: correlation of the imaging pattern with clinical setting and with associated abnormalities in the thorax and in other organs/systems, which is comprehensively analyzed in arriving at the most likely diagnosis. Since a rapid evaluation and emergent management of such patients is of pressing concern not only to the radiologist, but also for the general physicians, pulmonologists, critical care specialists, oncologists and transplant surgery teams, we believe our review is very informative to a wide spectrum reader audience.

Deep learning based fusion model for COVID-19 diagnosis and classification using computed tomography images

Recently, the COVID-19 pandemic becomes increased in a drastic way, with the availability of a limited quantity of rapid testing kits. Therefore, automated COVID-19 diagnosis models are essential to identify the existence of disease from radiological images. Earlier studies have focused on the development of Artificial Intelligence (AI) techniques using X-ray images on COVID-19 diagnosis. This paper aims to develop a Deep Learning Based MultiModal Fusion technique called DLMMF for COVID-19 diagnosis and classification from Computed Tomography (CT) images. The proposed DLMMF model operates on three main processes namely Weiner Filtering (WF) based pre-processing, feature extraction and classification. The proposed model incorporates the fusion of deep features using VGG16 and Inception v4 models. Finally, Gaussian Naïve Bayes (GNB) based classifier is applied for identifying and classifying the test CT images into distinct class labels. The experimental validation of the DLMMF model takes place using open-source COVID-CT dataset, which comprises a total of 760 CT images. The experimental outcome defined the superior performance with the maximum sensitivity of 96.53%, specificity of 95.81%, accuracy of 96.81% and F-score of 96.73%.

An algorithm combining procalcitonin and lung ultrasound improves the diagnosis of bacterial pneumonia in critically ill children: The PROLUSP study, a randomized clinical trial

BACKGROUND

Lung ultrasound (LUS) and procalcitonin (PCT) are independently used to improve accuracy when diagnosing lung infections. The aim of the study was to evaluate the accuracy of a new algorithm combining LUS and PCT for the diagnosis of bacterial pneumonia.

METHODS

Randomized, blinded, comparative effectiveness clinical trial. Children <18 years old with suspected pneumonia admitted to pediatric intensive care unit were included, and randomized into experimental group (EG) or control group (CG) if LUS or chest X-Ray (CXR) were done as the first pulmonary image, respectively. PCT was determined. In patients with bacterial pneumonia, sensitivity, specificity, and predictive values of LUS, CXR, and of both combined with PCT were analyzed and compared. Concordance between the final diagnosis and the diagnosis concluded through the imaging test was assessed.

RESULTS

A total of 194 children, with a median age of 134 (interquartile range [IQR]: 39-554) days, were enrolled, 96 randomized into the EG and 98 into the CG. Bacterial pneumonia was diagnosed in 97 patients. Sensitivity and specificity for bacterial pneumonia diagnosis were 78% (95% confidence interval [CI]: 70-85) and 98% (95% CI: 93-99) for LUS, 85% (95% CI: 78-90) and 53% (95% CI: 43-62) for CXR, 90% (95% CI: 83-94) and 85% (95% CI: 76-91) when combining LUS and PCT, and 95% (95% CI: 90-98) and 41% (95% CI: 31-52) when combining CXR and PCT. The positive predictive value for LUS and PCT was 88% (95% C:I 79%-93%) versus 68% (95% CI: 60-75) for CXR and PCT. The concordance between the final diagnosis and LUS had a kappa value of 0.69 (95% CI: 0.62-0.75) versus 0.34 (95% CI: 0.21-0.45) for CXR, (p < 0.001).

CONCLUSIONS

The combination of LUS and PCT presented a better accuracy for bacterial pneumonia diagnosis than combining CXR and PCT. Therefore, its implementation could be a reliable tool for pneumonia diagnosis in critically ill children.

Padrões tomográficos de agentes etiológicos da pneumonia durante o primeiro ano após transplante renal

Objetivo

Avaliar os padrões tomográficos relacionados aos agentes etiológicos da pneumonia em pacientes durante o primeiro ano após transplante renal.

Materiais e Métodos

Foram analisados dados de prontuários de 956 pacientes submetidos a transplante renal, no período de 2013 a 2018, em um centro transplantador renal do nordeste do Brasil. Nos pacientes que desenvolveram pneumonia, os agentes etiológicos foram classificados em bactérias piogênicas, micobactérias, fungos, vírus e pneumonia polimicrobiana, enquanto os padrões tomográficos foram classificados em consolidação, broncopneumonia, pneumonia intersticial e nódulos e massas. Para verificar associação estatística entre micro-organismos e padrões tomográficos, foi utilizado o teste exato de Fisher, com p < 0,001.

Resultados

Foram encontrados 101 casos de pneumonia, dos quais 60 (59,4%) tiveram agente etiológico identificado, sendo as bactérias piogênicas as mais frequentes, detectadas em 22 (36,7%) dos casos. Entre os pacientes com agente causal identificado, o padrão tomográfico predominante foi o de nódulos e massas, identificado em 25 (41,7%) casos. Foi observada associação entre bactérias piogênicas e o padrão de consolidação, fungos com nódulos e massas, bem como entre agentes virais e padrão intersticial.

Conclusão

Foi demonstrada associação estatística entre micro-organismos causadores de pneumonia e padrões tomográficos, informação que pode contribuir para o planejamento da terapia de pacientes transplantados renais.

Automated detection of COVID-19 through convolutional neural network using chest x-ray images

The COVID-19 epidemic has a catastrophic impact on global well-being and public health. More than 27 million confirmed cases have been reported worldwide until now. Due to the growing number of confirmed cases, and challenges to the variations of the COVID-19, timely and accurate classification of healthy and infected patients is essential to control and treat COVID-19. We aim to develop a deep learning-based system for the persuasive classification and reliable detection of COVID-19 using chest radiography. Firstly, we evaluate the performance of various state-of-the-art convolutional neural networks (CNNs) proposed over recent years for medical image classification. Secondly, we develop and train CNN from scratch. In both cases, we use a public X-Ray dataset for training and validation purposes. For transfer learning, we obtain 100% accuracy for binary classification (i.e., Normal/COVID-19) and 87.50% accuracy for tertiary classification (Normal/COVID-19/Pneumonia). With the CNN trained from scratch, we achieve 93.75% accuracy for tertiary classification. In the case of transfer learning, the classification accuracy drops with the increased number of classes. The results are demonstrated by comprehensive receiver operating characteristics (ROC) and confusion metric analysis with 10-fold cross-validation.

A case of haemoptysis and bilateral areas of lung consolidation sparing the right lower lobe

Multiple primary lung cancers (MPLC) are often neglected. Obtaining pre-operative specimens through bronchoscopy could play a role. It is important to distinguish aerogenous metastasis from MPLC in the adenocarcinoma spectrum due to the different prognosis.https://bit.ly/3zbdVrw

Explainable Machine Learning for COVID-19 Pneumonia Classification With Texture-Based Features Extraction in Chest Radiography

Both reverse transcription-PCR (RT-PCR) and chest X-rays are used for the diagnosis of the coronavirus disease-2019 (COVID-19). However, COVID-19 pneumonia does not have a defined set of radiological findings. Our work aims to investigate radiomic features and classification models to differentiate chest X-ray images of COVID-19-based pneumonia and other types of lung patterns. The goal is to provide grounds for understanding the distinctive COVID-19 radiographic texture features using supervised ensemble machine learning methods based on trees through the interpretable Shapley Additive Explanations (SHAP) approach. We use 2,611 COVID-19 chest X-ray images and 2,611 non-COVID-19 chest X-rays. After segmenting the lung in three zones and laterally, a histogram normalization is applied, and radiomic features are extracted. SHAP recursive feature elimination with cross-validation is used to select features. Hyperparameter optimization of XGBoost and Random Forest ensemble tree models is applied using random search. The best classification model was XGBoost, with an accuracy of 0.82 and a sensitivity of 0.82. The explainable model showed the importance of the middle left and superior right lung zones in classifying COVID-19 pneumonia from other lung patterns.

[Chest X-ray: implementation and indication : Recommendations of the thoracic imaging working group of the German Radiological Society]

BACKGROUND

Even after more than 100 years, the chest X‑ray is still an important technique to detect important pathological changes of lungs, heart and vessels in a fast and low-dose manner. For the German-speaking regions, there are only recommendations available published by the "Ständigen Strahlenschutzkommission (SSK)" regarding the indication. These recommendations are not updated on a regular basis and more recent developments are only integrated with delayed.

METHODS

The chest division of the German Radiological Society has summarized their expertise for the usage and indication of the chest X‑ray. Especially within the field of oncology the usage of chest X‑ray is evaluated differently to the aforementioned recommendations; here chest computed tomography (CT) is much more sensitive for evaluation of metastasis and local invasion of tumors. Also, within the area of infectious diseases in non-immunocompetent patients, CT is the method of choice. Based on the structure of the current recommendations, many current guidelines and indications are summarized and presented within the context of the usage of chest X‑ray.

Imaging Primer on Chimeric Antigen Receptor T-Cell Therapy for Radiologists

Chimeric antigen receptor (CAR) T-cell therapy is a recently approved breakthrough treatment that has become a new paradigm in treatment of recurrent or refractory B-cell lymphomas and pediatric or adult acute lymphoid leukemia. CAR T cells are a type of cellular immunotherapy that artificially enhances T cells to boost eradication of malignancy through activation of the native immune system. The CAR construct is a synthetically created functional cell receptor grafted onto previously harvested patient T cells, which bind to preselected tumor-associated antigens and thereby activate host immune signaling cascades to attack tumor cells. Advantages include a single treatment episode of 2-3 weeks and durable disease elimination, with remission rates of over 80%. Responses to therapy are more rapid than with conventional chemotherapy or immunotherapy, with intervening short-interval edema. CAR T-cell administration is associated with therapy-related toxic effects in a large percentage of patients, notably cytokine release syndrome, immune effect cell-associated neurotoxicity syndrome, and infections related to immunosuppression. Knowledge of the expected evolution of therapy response and potential adverse events in CAR T-cell therapy and correlation with the timeline of treatment are important to optimize patient care. Some toxic effects are radiologically evident, and familiarity with their imaging spectrum is key to avoiding misinterpretation. Other clinical toxic effects may be occult at imaging and are diagnosed on the basis of clinical assessment. Future directions for CAR T-cell therapy include new indications and expanded tumor targets, along with novel ways to capture T-cell activation with imaging. An invited commentary by Ramaiya and Smith is available online. Online supplemental material is available for this article. ^©RSNA, 2022.

Diagnostic Approach for Accurate Diagnosis of COVID-19 Employing Deep Learning and Transfer Learning Techniques through Chest X-ray Images Clinical Data in E-Healthcare

COVID-19 is a transferable disease that is also a leading cause of death for a large number of people worldwide. This disease, caused by SARS-CoV-2, spreads very rapidly and quickly affects the respiratory system of the human being. Therefore, it is necessary to diagnosis this disease at the early stage for proper treatment, recovery, and controlling the spread. The automatic diagnosis system is significantly necessary for COVID-19 detection. To diagnose COVID-19 from chest X-ray images, employing artificial intelligence techniques based methods are more effective and could correctly diagnosis it. The existing diagnosis methods of COVID-19 have the problem of lack of accuracy to diagnosis. To handle this problem we have proposed an efficient and accurate diagnosis model for COVID-19. In the proposed method, a two-dimensional Convolutional Neural Network (2DCNN) is designed for COVID-19 recognition employing chest X-ray images. Transfer learning (TL) pre-trained ResNet-50 model weight is transferred to the 2DCNN model to enhanced the training process of the 2DCNN model and fine-tuning with chest X-ray images data for final multi-classification to diagnose COVID-19. In addition, the data augmentation technique transformation (rotation) is used to increase the data set size for effective training of the R2DCNNMC model. The experimental results demonstrated that the proposed (R2DCNNMC) model obtained high accuracy and obtained 98.12% classification accuracy on CRD data set, and 99.45% classification accuracy on CXI data set as compared to baseline methods. This approach has a high performance and could be used for COVID-19 diagnosis in E-Healthcare systems.

CapsCovNet: A Modified Capsule Network to Diagnose COVID-19 From Multimodal Medical Imaging

Since the end of 2019, novel coronavirus disease (COVID-19) has brought about a plethora of unforeseen changes to the world as we know it. Despite our ceaseless fight against it, COVID-19 has claimed millions of lives, and the death toll exacerbated due to its extremely contagious and fast-spreading nature. To control the spread of this highly contagious disease, a rapid and accurate diagnosis can play a very crucial part. Motivated by this context, a parallelly concatenated convolutional block-based capsule network is proposed in this article as an efficient tool to diagnose the COVID-19 patients from multimodal medical images. Concatenation of deep convolutional blocks of different filter sizes allows us to integrate discriminative spatial features by simultaneously changing the receptive field and enhances the scalability of the model. Moreover, concatenation of capsule layers strengthens the model to learn more complex representation by presenting the information in a fine to coarser manner. The proposed model is evaluated on three benchmark datasets, in which two of them are chest radiograph datasets and the rest is an ultrasound imaging dataset. The architecture that we have proposed through extensive analysis and reasoning achieved outstanding performance in COVID-19 detection task, which signifies the potentiality of the proposed model.

Pediatric Lower Respiratory Tract Infections: Imaging Guidelines and Recommendations

Lower respiratory tract infection (LRTI) remains a major cause of morbidity and mortality in children. Various organisms cause LRTI, including viruses, bacteria, fungi, and parasites, among others. Infections caused by 2 or more organisms also occur, sometimes enhancing the severity of the infection. Medical imaging helps confirm a diagnosis but also plays a role in the evaluation of acute and chronic sequelae. Medical imaging tests help evaluate underlying pathology in pediatric patients with recurrent or long-standing symptoms as well as the immunocompromised.

COVID-19 Detection Using Deep Learning Algorithm on Chest X-ray Images

COVID-19, regarded as the deadliest virus of the 21st century, has claimed the lives of millions of people around the globe in less than two years. Since the virus initially affects the lungs of patients, X-ray imaging of the chest is helpful for effective diagnosis. Any method for automatic, reliable, and accurate screening of COVID-19 infection would be beneficial for rapid detection and reducing medical or healthcare professional exposure to the virus. In the past, Convolutional Neural Networks (CNNs) proved to be quite successful in the classification of medical images. In this study, an automatic deep learning classification method for detecting COVID-19 from chest X-ray images is suggested using a CNN. A dataset consisting of 3616 COVID-19 chest X-ray images and 10,192 healthy chest X-ray images was used. The original data were then augmented to increase the data sample to 26,000 COVID-19 and 26,000 healthy X-ray images. The dataset was enhanced using histogram equalization, spectrum, grays, cyan and normalized with NCLAHE before being applied to CNN models. Initially using the dataset, the symptoms of COVID-19 were detected by employing eleven existing CNN models; VGG16, VGG19, MobileNetV2, InceptionV3, NFNet, ResNet50, ResNet101, DenseNet, EfficientNetB7, AlexNet, and GoogLeNet. From the models, MobileNetV2 was selected for further modification to obtain a higher accuracy of COVID-19 detection. Performance evaluation of the models was demonstrated using a confusion matrix. It was observed that the modified MobileNetV2 model proposed in the study gave the highest accuracy of 98% in classifying COVID-19 and healthy chest X-rays among all the implemented CNN models. The second-best performance was achieved from the pre-trained MobileNetV2 with an accuracy of 97%, followed by VGG19 and ResNet101 with 95% accuracy for both the models. The study compares the compilation time of the models. The proposed model required the least compilation time with 2 h, 50 min and 21 s. Finally, the Wilcoxon signed-rank test was performed to test the statistical significance. The results suggest that the proposed method can efficiently identify the symptoms of infection from chest X-ray images better than existing methods.

Transfer Learning for the Detection and Diagnosis of Types of Pneumonia including Pneumonia Induced by COVID-19 from Chest X-ray Images

Accurate early diagnosis of COVID-19 viral pneumonia, primarily in asymptomatic people, is essential to reduce the spread of the disease, the burden on healthcare capacity, and the overall death rate. It is essential to design affordable and accessible solutions to distinguish pneumonia caused by COVID-19 from other types of pneumonia. In this work, we propose a reliable approach based on deep transfer learning that requires few computations and converges faster. Experimental results demonstrate that our proposed framework for transfer learning is a potential and effective approach to detect and diagnose types of pneumonia from chest X-ray images with a test accuracy of 94.0%.

S-CCCapsule: Pneumonia detection in chest X-ray images using skip-connected convolutions and capsule neural network

The squash function in capsule networks (CapsNets) dynamic routing is less capable of performing discrimination of non-informative capsules which leads to abnormal activation value distribution of capsules. In this paper, we propose vertical squash (VSquash) to improve the original squash by preventing the activation values of capsules in the primary capsule layer to shrink non-informative capsules, promote discriminative capsules and avoid high information sensitivity. Furthermore, a new neural network, (i) skip-connected convolutional capsule (S-CCCapsule), (ii) Integrated skip-connected convolutional capsules (ISCC) and (iii) Ensemble skip-connected convolutional capsules (ESCC) based on CapsNets are presented where the VSquash is applied in the dynamic routing. In order to achieve uniform distribution of coupling coefficient of probabilities between capsules, we use the Sigmoid function rather than Softmax function. Experiments on Guangzhou Women and Children’s Medical Center (GWCMC), Radiological Society of North America (RSNA) and Mendeley CXR Pneumonia datasets were performed to validate the effectiveness of our proposed methods. We found that our proposed methods produce better accuracy compared to other methods based on model evaluation metrics such as confusion matrix, sensitivity, specificity and Area under the curve (AUC). Our method for pneumonia detection performs better than practicing radiologists. It minimizes human error and reduces diagnosis time.

[Imaging in respiratory infections]

The conventional X‑ray image is the method of choice for suspected pneumonia. Computed tomography (CT) is indicated for treatment refractory or recurrent infiltrates, difficult differential diagnostics, suspected complications and in immunocompromised patients. Thoracic sonography can be used as an alternative method for initial diagnostics and in the intensive care unit to monitor progress. In addition to the detection of infiltrates the radiological classification can help to limit the pathogen spectrum. Radiologically, three forms of pneumonia can principally be differentiated: lobar pneumonia, bronchopneumonia and interstitial pneumonia. Furthermore, there are special forms of pneumonia with certain pathogens, such as aspergilloma, invasive mycosis, postprimary tuberculosis and nontuberculous mycobacteriosis or in a specific clinical context, such as aspiration pneumonia, postinfarction pneumonia, retention pneumonia and septic emboli. The most frequent complications of pneumonia are lung abscesses and pleural empyema. Both can sometimes but not always be seen in the X‑ray image. If clinically suspected the indications for CT should be generously applied. Certain pre-existing diseases, such as immunodeficiency or structural alterations of the lungs can predispose to pulmonary infections, frequently with unusual pathogens or manifestation forms and must be taken into account in the diagnostics.

[Management of Adult Community-Acquired Pneumonia and Prevention - Update 2021 - Guideline of the German Respiratory Society (DGP), the Paul-Ehrlich-Society for Chemotherapy (PEG), the German Society for Infectious Diseases (DGI), the German Society of Medical Intensive Care and Emergency Medicine (DGIIN), the German Viological Society (DGV), the Competence Network CAPNETZ, the German College of General Practitioneers and Family Physicians (DEGAM), the German Society for Geriatric Medicine (DGG), the German Palliative Society (DGP), the Austrian Society of Pneumology Society (ÖGP), the Austrian Society for Infectious and Tropical Diseases (ÖGIT), the Swiss Respiratory Society (SGP) and the Swiss Society for Infectious Diseases Society (SSI)]

The present guideline provides a new and updated concept of the management of adult patients with community-acquired pneumonia. It replaces the previous guideline dating from 2016.The guideline was worked out and agreed on following the standards of methodology of a S3-guideline. This includes a systematic literature search and grading, a structured discussion of recommendations supported by the literature as well as the declaration and assessment of potential conflicts of interests.The guideline has a focus on specific clinical circumstances, an update on severity assessment, and includes recommendations for an individualized selection of antimicrobial treatment.The recommendations aim at the same time at a structured assessment of risk for adverse outcome as well as an early determination of treatment goals in order to reduce mortality in patients with curative treatment goal and to provide palliation for patients with treatment restrictions.