Radiology of pneumonia

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-Ray Images

Coronavirus disease 2019 (COVID-19) is one of the most destructive pandemic after millennium, forcing the world to tackle a health crisis. Automated lung infections classification using chest X-ray (CXR) images could strengthen diagnostic capability when handling COVID-19. However, classifying COVID-19 from pneumonia cases using CXR image is a difficult task because of shared spatial characteristics, high feature variation and contrast diversity between cases. Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models. To address these challenges, Multiscale Attention Guided deep network with Soft Distance regularization (MAG-SD) is proposed to automatically classify COVID-19 from pneumonia CXR images. In MAG-SD, MA-Net is used to produce prediction vector and attention from multiscale feature maps. To improve the robustness of trained model and relieve the shortage of training data, attention guided augmentations along with a soft distance regularization are posed, which aims at generating meaningful augmentations and reduce noise. Our multiscale attention model achieves better classification performance on our pneumonia CXR image dataset. Plentiful experiments are proposed for MAG-SD which demonstrates its unique advantage in pneumonia classification over cutting-edge models. The code is available at https://github.com/JasonLeeGHub/MAG-SD.

Imaging of Community-acquired Pneumonia

Community-acquired pneumonia refers to an acute infection of the lung in patients who did not meet any of the criteria for health care-acquired pneumonia, and is associated with at least some symptoms of acute infection, accompanied by the presence of an acute infiltrate on a chest radiograph. Chest radiography remains an important component of the evaluation of a patient with a suspicion of pneumonia, and is usually the first examination to be obtained. The diagnosis of community-acquired pneumonia is based on the presence of select clinical features and is supported by imaging of the lung, usually by chest radiography. Infection of the lower respiratory tract typically presents radiologically as one of 3 patterns: (a) focal nonsegmental or lobar pneumonia, (b) multifocal bronchopneumonia or lobular pneumonia, and (c) focal or diffuse "interstitial" pneumonia. High-resolution computed tomography allows a better depiction of the pattern and distribution of pneumonia than the radiograph but is seldom required in the evaluation of patients with suspected or proven bacterial pneumonia. However, high-resolution computed tomography is a useful adjunct to conventional radiography in selected cases.

Critical Care Aspects of Lung Transplant Patients

Major strides have been made in lung transplantation during the 1990s and it has become an established treatment option for patients with advanced lung disease. Due to improvements in organ preservation, surgical techniques, postoperative intensive care, and immunosuppression, the risk of perioperative and early mortality (less than 3 months after transplantation) has declined [1]. The transplant recipient now has a greater chance of realizing the benefits of the long and arduous waiting period.

Despite these improvements, suboptimal long-term outcomes continue to be shaped by issues such as opportunistic infections and chronic rejection. Because of the wider use of lung transplantation and the longer life span of recipients, intensivists and ancillary intensive care unit (ICU) staff should be well versed with the care of lung transplant recipients.

In this clinical review, issues related to organ donation will be briefly mentioned. The remaining focus will be on the critical care aspects of lung transplant recipients in the posttransplant period, particularly ICU management of frequently encountered conditions. First, the groups of patients undergoing transplantation and the types of procedures performed will be outlined. Specific issues directly related to the allograft, including early graft dysfunction from ischemia-reperfusion injury, airway anastomotic complications, and infections in the setting of immunosuppression will be emphasized. Finally nonpulmonary aspects of posttransplant care and key pharmacologic points in the ICU will be covered.

Magnetic resonance imaging of pediatric lung parenchyma, airways, vasculature, ventilation, and perfusion: state of the art

Magnetic resonance (MR) imaging is a noninvasive imaging modality, particularly attractive for pediatric patients given its lack of ionizing radiation. Despite many advantages, the physical properties of the lung (inherent low signal-to-noise ratio, magnetic susceptibility differences at lung-air interfaces, and respiratory and cardiac motion) have posed technical challenges that have limited the use of MR imaging in the evaluation of thoracic disease in the past. However, recent advances in MR imaging techniques have overcome many of these challenges. This article discusses these advances in MR imaging techniques and their potential role in the evaluation of thoracic disorders in pediatric patients.

Targets for antibiotic and healthcare resource stewardship in inpatient community-acquired pneumonia: a comparison of management practices with National Guideline Recommendations

PURPOSE

Community-acquired pneumonia (CAP) is the most common infection leading to hospitalization in the USA. The objective of this study was to evaluate management practices for inpatient CAP in relation to Infectious Diseases Society of America/American Thoracic Society (IDSA/ATS) guidelines to identify opportunities for antibiotic and health care resource stewardship.

METHODS

This was a retrospective cohort study of adults hospitalized for CAP at a single institution from 15 April 2008 to 31 May 2009.

RESULTS

Of the 209 patients with CAP who presented to Denver Health Medical Center during the study period and were hospitalized, 166 (79 %) and 43 (21 %) were admitted to a medical ward and the intensive care unit (ICU), respectively. Sixty-one (29 %) patients were candidates for outpatient therapy per IDSA/ATS guidance with a CURB-65 score of 0 or 1 and absence of hypoxemia. Sputum cultures were ordered for 110 specimens; however, an evaluable sample was obtained in only 49 (45 %) cases. Median time from antibiotic initiation to specimen collection was 11 [interquartile range (IQR) 6-19] h, and a potential pathogen was identified in only 18 (16 %) cultures. Blood cultures were routinely obtained for both non-ICU (81 %) and ICU (95 %) cases, but 15 of 36 (42 %) positive cultures were false-positive results. The most common antibiotic regimen was ceftriaxone + azithromycin (182, 87 % cases). Discordant with IDSA/ATS recommendations, oral step-down therapy consisted of a new antibiotic class in 120 (66 %), most commonly levofloxacin (101, 55 %). Treatment durations were typically longer than suggested with a median of 10 (IQR 8-12) days.

CONCLUSIONS

In this cohort of patients hospitalized for CAP, management was frequently inconsistent with IDSA/ATS guideline recommendations, revealing potential targets to reduce unnecessary antibiotic and healthcare resource utilization.

Improved detection of focal pneumonia by chest radiography with bone suppression imaging

OBJECTIVE

To evaluate radiologists' ability to detect focal pneumonia by use of standard chest radiographs alone compared with standard plus bone-suppressed chest radiographs.

METHODS

Standard chest radiographs in 36 patients with 46 focal airspace opacities due to pneumonia (10 patients had bilateral opacities) and 20 patients without focal opacities were included in an observer study. A bone suppression image processing system was applied to the 56 radiographs to create corresponding bone suppression images. In the observer study, eight observers, including six attending radiologists and two radiology residents, indicated their confidence level regarding the presence of a focal opacity compatible with pneumonia for each lung, first by use of standard images, then with the addition of bone suppression images. Receiver operating characteristic (ROC) analysis was used to evaluate the observers' performance.

RESULTS

The mean value of the area under the ROC curve (AUC) for eight observers was significantly improved from 0.844 with use of standard images alone to 0.880 with standard plus bone suppression images (P < 0.001) based on 46 positive lungs and 66 negative lungs.

CONCLUSION

Use of bone suppression images improved radiologists' performance for detection of focal pneumonia on chest radiographs.

KEY POINTS

Bone suppression image processing can be applied to conventional digital radiography systems. Bone suppression imaging (BSI) produces images that appear similar to dual-energy soft tissue images. BSI improves the conspicuity of focal lung disease by minimizing bone opacity. BSI can improve the accuracy of radiologists in detecting focal pneumonia.

Asthma and pneumonia

Chest pain remains a common complaint among children seeking care in the United States. Asthma and lower respiratory tract infections such as pneumonia can be significant causes of chest pain. Children with chest pain caused by either of these pulmonary etiologies generally present with associated respiratory symptoms, including cough, wheezing, tachypnea, respiratory distress, and/or fever. Although analgesic medications can improve chest pain associated with pulmonary pathologies, the mainstay of therapy is to treat the underlying etiology; this includes bronchodilator and/or steroid medications in children with asthma and appropriate antibacterial administration in children with suspicions of bacterial pneumonia. The chest pain generally resolves along with the resolution of other respiratory symptoms.

Imaging of Chest Infections in Children

■ Imaging studies have limited value in the differentiation between viral and bacterial lower respiratory tract infections (moderate evidence).

■ CT provides more information than plain radiographs for complicated pulmonary infections with empyema, pleural effusion, or bronchopleural fistula (moderate evidence).

■ In immunocompromised patients, CT has been shown to characterize the type of infection better than plain radiographs (moderate evidence).

■ Ultrasound has an advantage over CT in the identification and characterization of complicated effusions (moderate evidence).

■ Early detection and therefore intervention for pleural complications of pneumonia are critical and can result in better outcomes (moderate evidence).

■ Early surgery (VATS) is more cost-effective than thoracotomy (without or with image guidance) in the treatment of empyemas in children (strong evidence).

Computed tomography for the diagnosis of infectious diseases of the chest

BACKGROUND

Pulmonary infection is a common reason for imaging of the lung in immunocompetent and immunosuppressed patients. Findings on chest radiography are nonspecific and encompass poor sensitivity. The role of computed tomography (CT) has been evolving in the diagnosis of lung infections.

OBJECTIVE

This paper reviews recent developments in the efficacy and utility of CT in the diagnosis of suspected pulmonary infections in a variety of patient populations.

METHODS

Recent published literature was reviewed to prepare this treatise on the role of CT.

CONCLUSION

Knowledge and skills at pattern recognition are crucial for the CT interpretation in lung infections. Computed tomography scan is increasingly used to increase the sensitivity of the radiologic diagnosis of thoracic infections. The greatest value of CT is when the radiograph is normal, findings are equivocal, and to differentiate infection from non-infectious disorders.

Magnetic resonance imaging of lung infections in children

The advantages and limitations of MRI in lung infections in children have not been well established. This article illustrates the MRI findings in children with pneumonia caused by Mycoplasma pneumoniae, Streptococcus pneumoniae, and other pathogens. Lung parenchymal, pleural, and lymph node abnormalities are well characterized by MRI. Loculation of pleural fluid is detected in children with empyema. Contrast enhancement may be useful in the differentiation of active inflammation from noninflammatory changes. MRI can be particularly useful in the follow-up of children with chronic pulmonary diseases.

Limited value of chest radiography in predicting aetiology of lower respiratory tract infection in general practice

BACKGROUND

In patients with lower respiratory tract infection (LRTI), changes on chest radiography are rare but poorly characterised, especially in general practice.

AIM

To describe the range of findings on chest radiographs and the associations between these findings and the aetiology of LRTI.

DESIGN OF STUDY

A prospective observational study.

SETTING

General practices in the Leiden region, The Netherlands.

METHOD

Adult patients with a defined LRTI were included. Standard medical history and physical examination were performed. Sputum, blood, and throat swabs were collected for diagnostic tests. Chest X-ray findings were assessed in relation to the aetiology.

RESULTS

An abnormality on the chest X-ray was observed in 72 (55%) patients. Forty-five patients (35%) had changes due to infection, and 26 (20%) due to pneumonia. Pathogens were detected in 84 patients (33 single bacterial, 43 single viral, and 8 dual). Twelve (29%) patients with a bacterial infection (including dual infections) compared to four (9%) patients with viral infection had pneumonia on the chest X-ray (odds ratio [OR] = 4.0; 95% confidence interval [CI] = 1.2 to 13.8). Using the presence of pneumonia on chest X-ray as a test to predict a bacterial infection, the positive predictive value and the negative predictive value were 75% (CI = 48 to 93%) and 57% (CI = 45 to 69%), respectively.

CONCLUSION

Pneumonia on the chest X-ray was found more frequently in patients with a bacterial infection than in patients with a viral infection. However, the sensitivity and the specificity are such that pneumonia on the chest X-ray is not a reliable test to discriminate between bacterial and non-bacterial LRTI in the general practice setting.

Imaging of Bacterial Pulmonary Infection in the Immunocompetent Patient

Pulmonary infection is a common reason for imaging of the lung and a common incidental finding in immunocompetent patients. Findings on chest radiography are nonspecific in defining acute infection; however, the radiologist should be aware of classically described patterns of infection, including air space, bronchopneumonia, and interstitial patterns. The radiologist must also be aware of potential limitations of the sensitivity of chest radiography. Imaging findings at computed tomography in acute infection have been poorly studied but may be more specific. Aspiration and septic emboli are additional potential radiographic patterns of infection that may be very characteristic in appearance. In the setting of nonresolving pneumonia, the differential diagnosis includes noninfectious causes as well as a variety of atypical infectious agents, specifically, mycobacterial and fungal agents, which have overlapping but distinctive clinical and radiographic presentations.

Comparison of plain chest radiography and high-resolution CT in human immunodeficiency virus infected patients with community-acquired pneumonia: a sub-Saharan Africa study

The objective of the study was to determine the proportion of patients with missed lesions on plain chest radiographs compared with high-resolution computed tomography (HRCT) in 49 human immunodeficiency virus (HIV) infected patients with community-acquired pneumonia (CAP). Patients underwent plain chest radiography and HRCT scans of the chest at admission. Microbiological investigations for CAP were performed. An experienced radiologist, without knowledge of clinical or pathological data, reported the chest radiographs and HRCT scans. The study group included 26 females and 23 males, aged 18-53 years (mean age 36 years). Organisms were isolated from 26 patients (53%). In 40 patients (82%), the HRCT scans demonstrated lesions not visualized on the plain chest radiographs. There was 100% correlation between plain radiographic and HRCT scan findings in nine cases (18%). Lesions that were not visualized on the plain radiographs but elucidated on HRCT included: pleural effusion (n = 14), ground-glass opacification (n = 20), pericardial effusion (n = 8), cavitation (n = 4), cysts (n = 4), bullae (n = 4), abscess (n = 1) and pneumothorax (n = 1). In 20 of 23 cases, hilar lymphadenopathy, identified on HRCT, was not recognized on plain chest radiographs. In patients in whom an organism was isolated, a correct HRCT diagnosis of pulmonary tuberculosis, bacterial pneumonia and Pneumocystis carinii pneumonia (PCP) was made in 80%, 84% and 100% of cases, respectively. The proportion of patients with missed lesions on plain chest radiographs in HIV infected patients with CAP was high. This has important implications for management and prognosis. HRCT scans correlate well with the microbiological diagnosis when reported by an experienced radiologist.

Reliability of radiographic findings and the relation to etiologic agents in community-acquired pneumonia

In a clinical setting the chest radiograph is the reference standard in establishing the diagnosis of community-acquired pneumonia (CAP). This study aimed to assess interobserver reliability (IR) of radiographic findings and the relationship to different causative pathogens in CAP. Chest radiographs of 192 patients with pneumonia, obtained from a database, were reviewed by 2 radiologists and 1 respiratory physician without specific clinical information. Main pattern of infiltrate, extent of pneumonia, presence of pleural fluid, thickened bronchial walls, lymphadenopathy and air bronchogram were scored. Also, the involved lobes were identified. Sputum cultures, blood cultures and serological tests were performed to identify the causative pathogen. IR was poor (kappa <0.4) for determining the main pattern of infiltrate and presence of air bronchogram, lymphadenopathy and thickening of bronchial walls. IR was fair to good (kappa 0.4-0.7) or even excellent (kappa>0.7) for determining the presence of pleural effusion, the extent of pneumonia and for identifying the lobes involved. Mycoplasma pneumoniae was associated more often with patchy alveolar opacities than Streptococcus pneumoniae (P=0.05). Chlamydia spp. were associated with unilobar involvement (86%), especially when compared to M. Pneumoniae (P=0.03) and S. pneumoniae (P=0.004). In conclusion, simple features such as presence of pleural fluid, the extent of pneumonia and identifying the involved lobes show fair to excellent IR. Other features such as main pattern of infiltrate are difficult to assess and show poor IR. Hardly any relation between different pathogens and radiological features was found. Therefore, chest radiographs are of limited value in predicting the causative pathogen, but are of good use to determine the extent of pneumonia and to detect complications such as parapneumonic effusion.

Radiology of community-acquired pneumonia

This article reviews the radiographic appearance of common community-acquired pneumonia. Included are the common bacterial pneumonias, tuberculosis, fungal pneumonia, pneumocystis pneumonia, and viral pneumonias. The various radiographic appearances and the clues for differentiating the pneumonias are discussed. Images enhance the discussion.

Agreement between emergency physician diagnosis and radiologist reports in patients discharged from an emergency department with community-acquired pneumonia

To evaluate the level of concurrence between radiologist reports and the diagnosis of community-acquired pneumonia (CAP) in patients discharged from an emergency department (ED), a retrospective chart audit of patients discharged with a diagnosis of 'pneumonia' or 'possible pneumonia' from the ED during a 2-year period was conducted. Emergency physician (EP) and radiology report (RR) diagnoses were categorized as 'pneumonia', 'possible pneumonia', 'non-pneumonia' and 'normal', and categories from each were compared. 815 charts were analyzed. Of 671 EP diagnoses of 'pneumonia', 304 (45.3%) RR's reported 'pneumonia' and 82 (12.2%), 'possible pneumonia'. Of 815 EP diagnoses of 'pneumonia' or 'possible pneumonia', 426 (52.3%) RRs were in agreement, while 216(26.5%) were of diagnoses other than pneumonia and 173 (21.1%) were read as normal. EPs and radiologists frequently disagree on whether a patient has pneumonia or not. Perhaps it is time to revisit the gold standard status of plain chest X-ray.

[Guidelines for the management of community pneumonia in adult who needs hospitalization]

Community acquired pneumonia is still an important health problem. In Spain the year incidence is 162 cases per 100,000 inhabitants with 53,000 hospital admission costing 115 millions of euros per year. In the last years there have been significant advances in the knowledge of: aetiology, diagnostic tools, treatment alternatives and antibiotic resistance. The Spanish Societies of Intensive and Critical Care (SEMICYUC), Infectious Diseases and Clinical Microbiology (SEIMC) and Pulmonology and Thoracic Surgery (SEPAR) have produced these evidence-based Guidelines for the management of community acquired pneumonia in Adults. The main objective is to help physicians to make decisions about this disease. The different points that have been developed are: aetiology, diagnosis, treatment and prevention.

Radiology of bacterial pneumonia

Bacterial pneumonia is commonly encountered in clinical practice. Radiology plays a prominent role in the evaluation of pneumonia. Chest radiography is the most commonly used imaging tool in pneumonias due to its availability and excellent cost benefit ratio. CT should be used in unresolved cases or when complications of pneumonia are suspected. The main applications of radiology in pneumonia are oriented to detection, characterisation and follow-up, especially regarding complications. The classical classification of pneumonias into lobar and bronchial pneumonia has been abandoned for a more clinical classification. Thus, bacterial pneumonias are typified into three main groups: Community acquired pneumonia (CAD), Aspiration pneumonia and Nosocomial pneumonia (NP).The usual pattern of CAD is that of the previously called lobar pneumonia; an air-space consolidation limited to one lobe or segment. Nevertheless, the radiographic patterns of CAD may be variable and are often related to the causative agent. Aspiration pneumonia generally involves the lower lobes with bilateral multicentric opacities. Nosocomial Pneumonia (NP) occurs in hospitalised patients. The importance of NP is related to its high mortality and, thus, the need to obtain a prompt diagnosis. The role of imaging in NP is limited but decisive. The most valuable information is when the chest radiographs are negative and rule out pneumonia. The radiographic patterns of NP are very variable, most commonly showing diffuse multifocal involvement and pleural effusion. Imaging plays also an important role in the detection and evaluation of complications of bacterial pneumonias. In many of these cases, especially in hospitalised patients, chest CT must be obtained in order to better depict these associate findings.

Imagerie moderne des pneumonies infectieuses aiguës

Les pneumonies infectieuses aiguës constituent un problème de santé publique important, car elles sont une cause majeure de morbidité et de mortalité chez l’adulte. Si les données cliniques et radiographiques permettent le plus souvent de faire le diagnostic de pneumonie infectieuse, le diagnostic étiologique est plus difficile. En effet, de nombreux agents pathogènes peuvent être responsables de pneumonie et la réaction du parenchyme pulmonaire est peu variée, d’où la faible spécificité des lésions radiologiques observées en dehors de quelques cas particuliers. C’est pourquoi la compréhension des mécanismes physiopathologiques permet d’expliquer certains aspects radiologiques. De même, la connaissance des bases anatomocliniques et radiologiques autorise la reconnaissance de trois aspects radiographiques principaux. Quant à l’appréciation des contextes épidémiologique et immunitaire, ils peuvent permettre également d’approcher le germe en cause.

Cystic and cavitary lung diseases: focal and diffuse

Cysts and cavities are commonly encountered abnormalities on chest radiography and chest computed tomography. Occasionally, the underlying nature of the lesions can be readily apparent as in bullae associated with emphysema. Other times, cystic and cavitary lung lesions can be a diagnostic challenge. In such circumstances, distinguishing cysts (wall thickness < or = 4 mm) from cavities (wall thickness > 4 mm or a surrounding infiltrate or mass) and focal or multifocal disease from diffuse involvement facilitates the diagnostic process. Other radiological characteristics, including size, inner wall contour, nature of contents, and location, when correlated with the clinical context and tempo of the disease process provide the most helpful diagnostic clues. Focal or multifocal cystic lesions include blebs, bullae, pneumatoceles, congenital cystic lesions, traumatic lesions, and several infectious processes, including coccidioidomycosis, Pneumocystis carinii pneumonia, and hydatid disease. Malignant lesions including metastatic lesions may rarely present as cystic lesions. Focal or multifocal cavitary lesions include neoplasms such as bronchogenic carcinomas and lymphomas, many types of infections or abscesses, immunologic disorders such as Wegener granulomatosis and rheumatoid nodule, pulmonary infarct, septic embolism, progressive massive fibrosis with pneumoconiosis, lymphocytic interstitial pneumonia, localized bronchiectasis, and some congenital lesions. Diffuse involvement with cystic or cavitary lesions may be seen in pulmonary lymphangioleiomyomatosis, pulmonary Langerhans cell histiocytosis, honeycomb lung associated with advanced fibrosis, diffuse bronchiectasis, and, rarely, metastatic disease. High-resolution computed tomography of the chest frequently helps define morphologic features that may serve as important clues regarding the nature of cystic and cavitary lesions in the lung.

Cytomegalovirus pneumonia mimicking lung cancer in an immunocompetent host

Cytomegalovirus (CMV) pneumonia can be a life-threatening disease in immunocompromised patients such as transplant recipients and patients given immunosuppressive therapy. Although CMV infections are highly prevalent in the general population, symptomatic pneumonia in an immunocompetent adult has been documented rarely. We describe a 47-year-old male smoker who presented with a 3.5-cm cavitary mass in the upper lobe of the left lung, highly suggestive of lung cancer. Wedge resection of the mass on thoracotomy revealed CMV pneumonia with no evidence of malignancy or other infections. No antiviral therapy was given to this immunocompetent patient, and no additional manifestations of CMV disease occurred.

What diagnostic tests are needed for community-acquired pneumonia?

Diagnostic tests play an important part in the evaluation and management of patients with CAP. Tests have key roles in diagnosing the presence of CAP and in assessing severity. An ideal test for microbiologic diagnosis in CAP is not yet available, and initial antimicrobial therapy usually is empiric. Nonetheless, when appropriately applied and correctly performed, tests for the identification of pathogens in CAP are useful and cost-effective.

Pneumonias in the compromised host

The choice of diagnostic modality depends on the patient's status, the expertise of the operator and pathologic resources of the hospital, and is a decision that should be guided by the infectious disease consultant and the clinicians involved in the care of the patient. Although the diagnosis must be tissue based, every attempt must be made to arrive at a tissue diagnosis as soon as possible in order to start specific therapy as soon as possible. It is as important to determine that the cause of the patient's pulmonary infiltrate is noninfectious versus infectious. Pulmonary embolic disease, CHF, ARDS, pulmonary hemorrhage, and pulmonary drug reactions may be reversible and require nonantimicrobially based therapies to treat the patient. Often clinicians are overwhelmed by differential diagnostic possibilities of exotic infectious disease pathogens and overlook easily treatable noninfectious disease mimics of pneumonia. Although differential diagnostic possibilities are great in the compromised host, clinicians should not be overwhelmed by diagnostic possibilities. Instead, clinicians should try to approach the patient syndromically, taking into account the degree and type of immunosuppression, the appearance and behavior of the infiltrates on the chest radiograph and the nature of the host defense defects and time relationships that will limit the differential diagnosis to relatively few diagnostic possibilities. The clinician can then treat empirically patients with presumed bacterial pneumonias and devise a diagnostic plan designed to arrive at a specific tissue diagnosis as soon as possible in patients who are likely to have nonbacterial infection of the lungs.