Pediatric Chest Radiographs Research Articles

Visualization and Interpretation of Convolutional Neural Network Predictions in Detecting Pneumonia in Pediatric Chest Radiographs.

Pneumonia affects 7% of the global population, resulting in 2 million pediatric deaths every year. Chest X-ray (CXR) analysis is routinely performed to diagnose the disease. Computer-aided diagnostic (CADx) tools aim to supplement decision-making. These tools process the handcrafted and/or convolutional neural network (CNN) extracted image features for visual recognition. However, CNNs are perceived as black boxes since their performance lack explanations. This is a serious bottleneck in applications involving medical screening/diagnosis since poorly interpreted model behavior could adversely affect the clinical decision. In this study, we evaluate, visualize, and explain the performance of customized CNNs to detect pneumonia and further differentiate between bacterial and viral types in pediatric CXRs. We present a novel visualization strategy to localize the region of interest (ROI) that is considered relevant for model predictions across all the inputs that belong to an expected class. We statistically validate the models’ performance toward the underlying tasks. We observe that the customized VGG16 model achieves 96.2% and 93.6% accuracy in detecting the disease and distinguishing between bacterial and viral pneumonia respectively. The model outperforms the state-of-the-art in all performance metrics and demonstrates reduced bias and improved generalization.

Improving the quality of positioning and reducing the rotation factor during pediatric portable chest radiography using infant immobilizer

Background: The portable chest X-ray in infants hospitalized in neonatal intensive care units is one of the most common diagnostic procedures. Every child during hospitalization period may be incurred over a number of portable chest radiography examinations. Optimization of the infant position for radiography results in the improved diagnostic quality of radiographs.Objective: To evaluate rotation factor during pediatric portable chest radiography; the present study examined the effect of two different methods to stabilize infant position during radiography on the incidence of rotation.Materials and methods: This is an interventional study with nonequivalent groups in which rotation factor was evaluated on 250 portable chest radiography on fields of newborns admitted to NICUs (in two intervention and control groups), by comparing the length of posterior ribs on both sides of the chest. In this study, 176 radiographs were related to infants from three university hospitals so that sandbags or patients accompany had been used to stabilize the position of the patient, and 74 radiographs were for infants referred to an academic center whose positions had been stabilized during X-ray using body immobilizer.Results: The mean difference between the length of right and left posterior ribs in infants stabilized with the usual method (sandbags or patients accompanies) was obtained 6.51±5.05 mm. This statistical index for the second group of infants whose positions had been stabilized through body immobilizer was 2.87±2.15mm. Independent t-test showed a significant difference between the two groups in terms of the difference in the quantity of rotation. In this study, the difference in the length of posterior ribs over 5 mm was found as detectable rotation in the images.Conclusion: The infant position during radiography can be improved considerably by using proper body immobilizer, and repeating the tests can be avoided due to the inappropriate position. By means of such an instrument, there is no need for the help of accompanies or personnel to stabilize infant position, and their exposure will be prevented.

Reliability and validity of the World Health Organization reading standards for paediatric chest radiographs used in the field in an impact study of Pneumococcal Conjugate Vaccine in Kilifi, Kenya.

BackgroundRadiologically-confirmed pneumonia (RCP) is a specific end-point used in trials of Pneumococcal Conjugate Vaccine (PCV) to estimate vaccine efficacy. However, chest radiograph (CXR) interpretation varies within and between readers. We measured the repeatability and reliability of paediatric CXR interpretation using percent agreement and Cohen’s Kappa and the validity of field readings against expert review in a study of the impact of PCV on pneumonia.MethodsCXRs were obtained from 2716 children admitted between 2006 and 2014 to Kilifi County Hospital, Kilifi, Kenya, with clinically-defined severe or very-severe pneumonia. Five clinicians and radiologists attended a three-day training course on CXR interpretation using a WHO standard. All CXRs were read once by two local primary readers. Discordant readings and 13% of concordant readings were arbitrated by a panel of three expert radiologists. To assess repeatability, a 5% median random sample was presented twice. Sensitivity and specificity of the primary readers’ interpretations was estimated against the ‘gold-standard’ of the arbitrators’ results.ResultsOf 2716 CXRs, 2 were uninterpretable and 159 were evaluated twice. The percent agreement and Kappa for RCP were 89% and 0.68 and ranged between 84–97% and 0.19–0.68, respectively, for all pathological findings. Intra-observer repeatability was similar to inter-observer reliability. Sensitivities of the primary readers to detect RCP were 69% and 73%; specificities were 96% and 95%.ConclusionIntra- and inter-observer agreements on interpretations of radiologically-confirmed pneumonia are fair to good. Reasonable sensitivity and high specificity make radiologically-confirmed pneumonia, determined in the field, a suitable measure of relative vaccine effectiveness.

MP20: ImageSim - performance-based medical image interpretation learning system

Introduction: Medical images (e.g. radiographs) are the most commonly ordered tests in emergency medicine. As such, emergency medicine physicians are faced with the task of learning the skill of interpreting these images to an expert performance level by the time they provide opinions that guide patient management decisions. However, discordant interpretations of these images between emergency physicians and expert counterparts (e.g. radiologists) is a common cause of medical error. In pediatrics, this problem is even greater due to the changing physiology with age. Methods: ImageSim (https://imagesim.com/) is an evidence-based on-line learning platform derived and validated over an 11 year period (https://imagesim.com/research-and-efficacy/). This learning system incorporates the concepts of cognitive simulation, gamification, deliberate practice, and performance-based competency in the presentation and interpretation of medical images. Specifically, ImageSim presents images as they are experienced in clinical practice and incorporates a normal to abnormal ratio is representative of that seen in emergency medicine. Further, it forces the participant to commit to the case being normal or abnormal and if abnormal, the participant has to visually locate the specific area of pathology on the image. The participant submits a response and gets text and visual feedback with every case. After each case, the participant gets to play again until they reach a desired competency threshold (80% is bronze resident; 90% silver staff emergency medicine physician; 97% gold radiologist). Importantly, the learning experience also emphasizes deliberate practice such that the learning system provides hundreds of case examples and therefore each participants performance has the opportunity to improve along their individual learning curve. Results: Course selection was made based on known medical image interpretation knowledge gaps for practicing emergency physicians. Currently, ImageSim live courses include pediatric musculoskeletal radiographs (2,100 cases, 7 modules) and pediatric chest radiographs (434 cases). In 2018, we will also release a pediatric point-of-care ultrasound course (400 cases, 4 modules) and the pre-pubertal female genital examination (150 cases). For a demo, go to https://imagesim.com/demo/. Using ImageSim, the deliberate practice of about 120 cases (1 hour time commitment) increases accuracy on average by 15%. Currently integrated into 10 emergency medicine training programs and there are about 300 continuing medical education world-wide participants. Conclusion: While acquiring mastery for these images may take years to acquire via clinical practice alone, this learning system can potentially help achieve this in just a few hours.

Patient related factors influencing the quality of paediatric chest radiographs

No abstract available.

Optimization of Radiological Protection in Pediatric Patients Undergoing Common Conventional Radiological Procedures: Effectiveness of Increasing the Film to Focus Distance (FFD)

Background Increasing the x-ray film to focus distance (FFD), has been recommended as a practical dose optimization tool for patients undergoing conventional radiological procedures. In the previous study, we demonstrated a 32% reduction in absorbed dose is achievable due to increasing the FFD from 100 to 130 cm during pediatric chest radiography. The aim of this study was to examine whether increasing the FFD from 100 to 130 cm is equally effective for other common radiological procedures and performing a literature review of published studies to address the feasibility and probable limitations against implementing this optimization tool in clinical practice. Materials and Methods Radiographic examination of the pelvis (AP view), abdomen (AP view), skull (AP and lateral view), and spine (AP and lateral view), were taken of pediatric patients. The radiation dose and image quality of a radiological procedure is measured in FFD of 100 cm (reference FFD) and 130 cm (increased FFD). The thermo-luminescent dosimeters (TLD) were used for radiation dose measurements and visual grading analysis (VGA) for image quality assessments. Results: Statistically significant reduction in the ESD ranged from 21.91% for the lateral skull projection to 35.24% for the lateral spine projection was obtained, when the FFD was increased from 100 to 130 cm (P 0.05). Conclusion Increasing the FFD from 100 to 130 cm has significantly reduced radiation exposure without affecting on image quality. Our findings are commensurate with the literatures and emphasized that radiographers should learn to use of an updated reference FFD of 130 cm in clinical practice.

Marginal Shape Deep Learning: Applications to Pediatric Lung Field Segmentation.

Representation learning through deep learning (DL) architecture has shown tremendous potential for identification, localization, and texture classification in various medical imaging modalities. However, DL applications to segmentation of objects especially to deformable objects are rather limited and mostly restricted to pixel classification. In this work, we propose marginal shape deep learning (MaShDL), a framework that extends the application of DL to deformable shape segmentation by using deep classifiers to estimate the shape parameters. MaShDL combines the strength of statistical shape models with the automated feature learning architecture of DL. Unlike the iterative shape parameters estimation approach of classical shape models that often leads to a local minima, the proposed framework is robust to local minima optimization and illumination changes. Furthermore, since the direct application of DL framework to a multi-parameter estimation problem results in a very high complexity, our framework provides an excellent run-time performance solution by independently learning shape parameter classifiers in marginal eigenspaces in the decreasing order of variation. We evaluated MaShDL for segmenting the lung field from 314 normal and abnormal pediatric chest radiographs and obtained a mean Dice similarity coefficient of 0.927 using only the four highest modes of variation (compared to 0.888 with classical ASM1 (p-value=0.01) using same configuration). To the best of our knowledge this is the first demonstration of using DL framework for parametrized shape learning for the delineation of deformable objects.

Efficacy of Increasing Focus to Film Distance (FFD) for Patient’s Dose and Image Quality in Pediatric Chest Radiography

Background: Increasing the x-ray focus to film distance (FFD) has been advocated as an effective method to reduce the patients’ radiation dose. The aim of this study was to investigate the efficacy of this technique in patients' dose and image quality in pediatric chest x-ray.Material and methods: Sixty pediatric patients were x-ray imaged at FFDs of 100 and 130 cm. Dose measurements were performed using thermo-luminescent dosimeters (GR200). The quality of images was independently assessed using the anatomical criteria recommended by the European guidelines.Results: Increasing the FFD from 100 to 130 cm has reduced the entrance skin dose (ESD) of patients by 32.2% (p 0.05).Conclusion: Increased FFD to 130 cm reduce the pediatric radiation dose with no significant changes in image quality.

Pediatric Chest Radiographs: Common and Less Common Errors

Radiographic imaging of the pediatric chest presents several unique challenges and nuances, stemming from congenital variants and pathologic processes specific to this population. Errors in interpretation may lead to inappropriate further imaging, incurring additional radiation exposure and cost, as well as psychologic effects on the patients and their families. Here, we aim to highlight some common and less common pitfalls in pediatric chest radiography, as well as some tools for avoiding potential mistakes.

Dose Reduction to the Thyroid Gland in Pediatric Chest Radiography

Background It is remain a main concern that pediatric chest radiographies contribute to the significant radiation exposure to the thyroid gland as a more susceptible organ to radiation induced cancer. The aim of this study was to assessment the entrance surface dose (ESD) of pediatric chest radiography compared to the diagnostic reference levels (DRL) and evaluation the efficacy of the lead (Pb) shield in radiation dose reduction to the thyroid gland. Materials and Methods After assessing each patient against specific inclusion-exclusion criteria, 40 pediatric patients who were undergoing anterior-posterior (AP) projection of the chest x-ray were considered eligible for this study. The ESD of the chest and also ESD of thyroid gland with and without a 1 mm butterfly-shaped lead shield which placed on the thyroid gland were measured using high sensitive thermo luminescent dosimeters (TLD-GR 200). Results The average of ESD for chest radiography was 0.068+ 0.04 mGy (0.021 - 0.232 mGy). The unshielded average thyroid ESD was 0.065+0.053 mGy compared to the shielded average thyroid ESD of 0.001 + 0.034 mGy. The use of Pb-shield produced a statistically significant decrease in the average thyroid dose by about 97% (P< 0.001). Conclusion It seems that the Pb-thyroid shield has potential to reduced radiation dose significantly without compromising image quality. The use of thyroid shield in the AP projection of pediatric chest radiography may be an effective method to reduce patient's radiation risk and its usage should be encouraged. Key Words: chest x-ray, pediatrics, radiation exposure, thyroid gland

SU‐D‐209‐06: Study On the Dose Conversion Coefficients in Pediatric Radiography with the Development of Children Voxel Phantoms

Purpose:Conversion coefficients of organ dose normalized to entrance skin dose (ESD) are widely used to evaluate the organ doses directly using ESD without time‐consuming dose measurement, this work aims to investigate the dose conversion coefficients in pediatric chest and abdomen radiography with the development of 5 years and 10 years old children voxel phantoms.Methods:After segmentation of organs and tissues from CT slice images of ATOM tissue‐equivalent phantoms, a 5‐year‐old and a 10‐year‐old children computational voxel phantoms were developed for Monte Carlo simulation. The organ doses and the entrance skin dose for pediatric chest postero‐anterior projection and abdominal antero‐posterior projection were simulated at the same time, and then the organ dose conversion coefficients were calculated.To verify the simulated results, dose measurement was carried out with ATOM tissue‐equivalent phantoms for 5 year chest radiography.Results:Simulated results and experimental results matched very well with each other, the result differences of all the organs covered in radiation field were below 16% for 5‐year‐old child in chest projection. I showed that the conversion coefficients of organs covered in the radiation field were much larger than organs out of the field for all the study cases, for example, the conversion coefficients of stomach, liver intestines, and pancreas are larger for abdomen radiography while conversion coefficients of lungs are larger for chest radiography.Conclusion:The voxel children phantoms were helpful to evaluate the radiation doses more accurately and efficiently. Radiation field was the essential factor that affects the organ dose, use reasonably small field should be encouraged for radiation protection.This work was supported by the National Natural Science Foundation of China(11475047)

Digital platform for improving non-radiologists' and radiologists' interpretation of chest radiographs for suspected tuberculosis - a method for supporting task-shifting in developing countries.

Shifting X-ray interpretation to non-radiologists can help to address radiologist shortages in developing countries. To determine the change in accuracy of non-radiologists and radiologists for the radiographic diagnosis of paediatric tuberculosis after a short skill-development course. Participants interpreted 15 paediatric chest radiographs before and after a 30-minute course using three possible responses: (1) diagnostic for tuberculosis, (2) abnormal but inconclusive for diagnosis of tuberculosis and (3) normal. We compared proportions of correct diagnoses, sensitivity, and specificity, before and after the course. We included 256 participants comprising 229 non-radiologists (134 radiographers, 32 paediatricians, 39 Médecins Sans Frontières clinicians and 24 physicians including paediatricians) and 27 radiologists. Mean change proportions of correct diagnosis ranged from -27% to 53% for individuals and 9% to 20% for groups. All groups showed a statistically significant improvement. Mean change in diagnostic sensitivity ranged from -38% to 100% for individuals and from 16% to 41% for groups. All groups showed a statistically significant improvement. Mean change in specificity ranged from -57% to 57% for individuals and from -15% to -4% for groups. The decrease was statistically significant for physicians, paediatricians and radiographers. The course resulted in increased correct diagnoses and improved sensitivity at the expense of specificity.

Approach to Pediatric Chest Radiograph.

Chest radiograph remains the first line imaging modality even today, especially in ICU settings. Hence proper interpretation of chest radiographs is crucial, which can be achieved by adopting a systematic approach and proper description and identification of abnormalities. In this review, the authors describe a short and comprehensive way of interpreting the pediatric chest radiograph.

Compliance of Radiation Dose and Image Quality in a Nigerian Teaching Hospital with the European Guidelines for Pediatric Screen-Film Chest Radiography

Introduction Blue light is a part of the spectrum with the highest energy content, which can reach the retina. The damage that it can cause to the retina is called photochemical or blue-light retinal injury. For the retinal injury assessment of the photochemical and aphakic retinal hazards in the wavelength range of 300-700 nm, use of effective spectral radiance limits (W.m-2.sr-1) seems to be slightly perplexing for ophthalmologists. However, in this study, the temperature (OC) that can emit the same effective spectral radiance limit was detected using a computer code; this method could help prevent blue-light retinal injury. Materials and Methods The limits proposed by International Commission on Non-Ionizing Radiation Protection for blue-light induced photochemical and aphakic eye hazards were expressed in terms of temperature by a computer code for 13 Planckian sources that produce the same radiance. The calculated temperature by the computer code, here known as threshold temperature, is the maximum source temperature that for a specified viewing distance and source diameter does not cause the exposure at the receptor position to exceed the exposure limit. Results In terms of threshold temperature, the exposure limits for aphakia or infant retinal injury are much lower than retinal photochemical damage. For light sources with more effective radiances, these differences reach 800 K. Conclusion This method allows evaluation of photochemical and aphakic retinal hazard only by comparing the calculated threshold temperature by a computer code with the temperature of the radiant source, which may be beneficial for hygienist and ophthalmic clinicians.

Using Standardized Interpretation of Chest Radiographs to Identify Adults with Bacterial Pneumonia--Guatemala, 2007-2012.

BackgroundBacterial pneumonia is a leading cause of illness and death worldwide, but quantifying its burden is difficult due to insensitive diagnostics. Although World Health Organization (WHO) protocol standardizes pediatric chest radiograph (CXR) interpretation for epidemiologic studies of bacterial pneumonia, its validity in adults is unknown.MethodsPatients (age ≥15 years) admitted with respiratory infections to two Guatemalan hospitals between November 2007 and March 2012 had urine and nasopharyngeal/oropharyngeal (NP/OP) swabs collected; blood cultures and CXR were also performed at physician clinical discretion. ‘Any bacterial infection’ was defined as a positive urine pneumococcal antigen test, isolation of a bacterial pneumonia pathogen from blood culture, or detection of an atypical bacterial pathogen by polymerase chain reaction (PCR) of nasopharyngeal/oropharyngeal (NP/OP) specimens. ‘Viral infection’ was defined as detection of viral pathogens by PCR of NP/OP specimens. CXRs were interpreted according to the WHO protocol as having ‘endpoint consolidation’, ‘other infiltrate’, or ‘normal’ findings. We examined associations between bacterial and viral infections and endpoint consolidation.FindingsUrine antigen and/or blood culture results were available for 721 patients with CXR interpretations; of these, 385 (53%) had endpoint consolidation and 253 (35%) had other infiltrate. Any bacterial infection was detected in 119 (17%) patients, including 106 (89%) pneumococcal infections. Any bacterial infection (Diagnostic Odds Ratio [DOR] = 2.9; 95% confidence Interval (CI): 1.3–7.9) and pneumococcal infection (DOR = 3.4; 95% CI: 1.5–10.0) were associated with ‘endpoint consolidation’, but not ‘other infiltrate’ (DOR = 1.7; 95% CI: 0.7–4.9, and 1.7; 95% CI: 0.7–4.9 respectively). Viral infection was not significantly associated with ‘endpoint consolidation’, ‘other infiltrate,’ or ‘normal’ findings.Interpretation‘Endpoint consolidation’ was associated with ‘any bacterial infection,’ specifically pneumococcal infection. Therefore, endpoint consolidation may be a useful surrogate for studies measuring the impact of interventions, such as conjugate vaccines, against bacterial pneumonia.

Optimisation of paediatric chest radiography.

The purpose of this work is to present the algorithm for the optimisation of paediatric chest radiography aimed to reduce patient doses at keeping adequate image quality. Optimal tube voltage, tube current and exposure time, use of automatic or manual exposure control and use of antiscatter grid were recommended for different age groups and depending on the patient size. The optimised protocols and radiography technique resulted in decrease in Entrance surface air kerma and effective dose values in a factor of between 1.5 and over 5 for different age groups. Image quality was assessed to be of sufficient diagnostic quality.

Automated detection of endotracheal tubes in paediatric chest radiographs

The aim of this study was to develop an automated method for the detection of endotracheal tube and location of its tip in paediatric chest radiographs. In this method, a seed point was first determined from the line crossing the cervical region and a line path was traced from the seed point. Two features, Lmax and C, were determined from the path and were combined to detect the existence of the endotracheal tube. Multiple thresholds applied to the line path were used to determine the candidate locations for the tip, and the most suitable location was selected from these candidates by analysing the image features. To evaluate the performance of detection of endotracheal tube existence, support vector machine was used to classify the images with and without endotracheal tubes on the basis of Lmax and C. The discriminant performance of the method was evaluated using receiver operating characteristic (ROC) analysis. To evaluate the precision of the detected tip locations, the tip locations in paediatric chest images were annotated by a radiologist. The distance (error) between the detected and annotated locations was used to evaluate detection precision for the tip location. The proposed method was evaluated using 528 images with endotracheal tubes and 816 images without endotracheal tubes. The discriminant performance in this study, evaluated as Az (area under the ROC curve), for detecting the existence of endotracheal tubes on the basis of the two features was 0.943±0.009, and the detection error of the tip location was 1.89±2.01mm. The proposed method obtained high performance results and could be useful for detecting the malposition of endotracheal tubes in paediatric chest radiographs.

Short-term impact of pictorial posters and a crash course on radiographic errors for improving the quality of paediatric chest radiographs in an unsupervised unit — a pilot study for quality-assurance outreach

Chest radiography is the most commonly performed diagnostic X-ray examination. The radiation dose to the patient for this examination is relatively low but because of its frequent use, the contribution to the collective dose is considerable. Optimized image quality not only allows for more accurate diagnosis but also supports radiation protection, which is particularly important in children. To determine whether the introduction of a poster of technical errors in paediatric radiography accompanied by a short lecture (crash course) for radiographers on common errors can sustainably decrease the number and rate of these errors in an unsupervised radiology department (without a paediatric-trained radiologist or paediatric-trained radiography personnel). We conducted a pilot study for quality-assurance outreach, with retrospective and prospective components, in the paediatric radiology department of a teaching hospital. The technical errors in frontal chest radiographs performed in the unit were assessed by quality-assurance analysis using a customized tick-sheet. The review was performed before and after an intervention that involved a half-hour crash course and poster displays in the department. We compared the rate of technical errors made before and after the intervention. There was statistically significant improvement in quality of radiographs (P < 0.0083) performed immediately after the intervention. There was a statistically significant decline in the quality of radiographs performed >2 months after the intervention. A simple intervention of a crash course and poster placement resulted in improved quality of paediatric chest radiographs. A decline in quality after 2 months suggests the need to repeat this or another type of intervention regularly.

Evaluation of entrance surface air kerma in pediatric chest radiography

Abstract The objective of this study was to evaluate the entrance surface air kerma in pediatric chest radiography. An evaluation of 301 radiographical examinations in anterior–posterior (AP) and posterior–anterior (PA) (166 examinations) and lateral (LAT) (135 examinations) projections was performed. The analyses were performed on patients grouped by age; the groups included ages 0–1 y, 1–5 y, 5–10 y, and 10–15 y. The entrance surface air kerma was determined with DoseCal software (Radiological Protection Center of Saint George׳s Hospital, London) and thermoluminescent dosimeters. Two different exposure techniques were compared. The doses received by patients who had undergone LAT examinations were 40% higher, on average, those in AP/PA examinations because of the difference in tube voltage. A large high-dose “tail” was observed for children up to 5 y old. An increase in tube potential and corresponding decrease in current lead to a significant dose reduction. The difference between the average dose values for different age ranges was not practically observed, implying that the exposure techniques are still not optimal. Exposure doses received using the higher tube voltage and lower current-time product correspond to the international diagnostic reference levels.

Evolution of a Round Pneumonia

A previously healthy 14-year-old male presented to the emergency department (ED) complaining of 2 days of subacute onset, right-anterior pleuritic chest pain. He reported an associated dry cough, but denied fever, sputum, hemoptysis, shortness of breath, orthopnea, leg swelling, weight loss or night sweats. The patient had no known sick contacts, and had no identifiable cardiac or thromboembolic risk factors. We obtained a 2-view chest radiograph, which revealed an indeterminate 1.3 cm focal density in the right upper lobe (Figure 1). The patient was discharged on oral analgesics with a plan for follow-up imaging. Figure 1. Anterior-Posterior chest radiograph on index visit showing a 1.3 cm right upper lobe density (arrows). Six days after symptom onset the patient returned to the ED with worsening pain despite oral analgesics, a low-grade fever and a worsening dry cough. On physical examination the patient was well appearing and in no apparent distress. His temperature was 99.8 °F; his blood pressure was 105/72; his heart rate was 95 beats/minute; and his oxygen saturation on room air was 99%. A previously planted PPD was read as negative. We obtained a repeat chest radiograph, which revealed a wedge-shaped consolidation in the inferior segment of the right upper lobe (Figure 2). The patient was treated with an oral cephalosporin as an outpatient with complete resolution of his symptoms. Figure 2. Anterior-Posterior chest radiograph on day 6 showing consolidation of the inferior segment of the right upper lobe (arrows). Round pneumonia is primarily seen in children and adolescents. In one study, 75% of patients were under 8 years of age, and 90% under 12.1 It is postulated that round pneumonias occurs more often in children as they have poorly developed pathways of collateral ventilation, more closely apposed lung connective tissue septa and smaller alveoli, when compared to adults. These factors combine to form more compact areas of infiltrate, which can appear as round lesions on chest radiography.2 Round pneumonias are most often caused by Streptococcus pneumoniae, and resolution after treatment, rather than progression to lobar pneumonia, is the rule.1,3 In addition to infection, the differential diagnosis of a round lesion on a pediatric chest radiograph includes primary lung neoplasm, congenital bronchogenic consolidation, and Wilms tumor.2 The majority of round lesions in children, however, are nonneoplastic, and advanced imaging with computed tomography or magnetic resonance imaging is not typically indicated unless symptoms suggest an alternative diagnosis.4