Artificial intelligence in computed tomography for quantifying lung changes in the era of CFTR modulators.

BACKGROUND: Chest computed tomography (CT) remains the imaging standard for demonstrating cystic fibrosis (CF) airway structural disease in vivo. However, visual scoring systems as an outcome measure are time consuming, require training and lack high reproducibility. Our objective was to validate a fully automated artificial intelligence (AI)-driven scoring system of CF lung disease severity. METHODS: Data were retrospectively collected in three CF reference centres, between 2008 and 2020, in 184 patients aged 4-54 years. An algorithm using three 2D convolutional neural networks was trained with 78 patients' CT scans (23 530 CT slices) for the semantic labelling of bronchiectasis, peribronchial thickening, bronchial mucus, bronchiolar mucus and collapse/consolidation. 36 patients' CT scans (11 435 CT slices) were used for testing versus ground-truth labels. The method's clinical validity was assessed in an independent group of 70 patients with or without lumacaftor/ivacaftor treatment (n=10 and n=60, respectively) with repeat examinations. Similarity and reproducibility were assessed using the Dice coefficient, correlations using the Spearman test, and paired comparisons using the Wilcoxon rank test. RESULTS: The overall pixelwise similarity of AI-driven versus ground-truth labels was good (Dice 0.71). All AI-driven volumetric quantifications had moderate to very good correlations to a visual imaging scoring (p<0.001) and fair to good correlations to forced expiratory volume in 1 s % predicted at pulmonary function tests (p<0.001). Significant decreases in peribronchial thickening (p=0.005), bronchial mucus (p=0.005) and bronchiolar mucus (p=0.007) volumes were measured in patients with lumacaftor/ivacaftor. Conversely, bronchiectasis (p=0.002) and peribronchial thickening (p=0.008) volumes increased in patients without lumacaftor/ivacaftor. The reproducibility was almost perfect (Dice >0.99). CONCLUSION: AI allows fully automated volumetric quantification of CF-related modifications over an entire lung. The novel scoring system could provide a robust disease outcome in the era of effective CF transmembrane conductance regulator modulator therapy.

Assessment of pulmonary structure-function relationships in young children and adolescents with cystic fibrosis by multivolume proton-MRI and CT.

BACKGROUND: Lung disease is the most frequent cause of morbidity and mortality in patients with cystic fibrosis (CF), and there is a shortage of sensitive biomarkers able to regionally monitor disease progression and to assess early responses to therapy. PURPOSE: To determine the feasibility of noncontrast-enhanced multivolume MRI, which assesses intensity changes between expiratory and inspiratory breath-hold images, to detect and quantify regional ventilation abnormalities in CF lung disease, with a focus on the structure-function relationship. STUDY TYPE: Retrospective. POPULATION: Twenty-nine subjects, including healthy young children (n = 9, 7-37 months), healthy adolescents (n = 4, 14-22 years), young children with CF lung disease (n = 10, 7-47 months), and adolescents with CF lung disease (n = 6, 8-18 years) were studied. FIELD STRENGTH/SEQUENCE: 3D spoiled gradient-recalled sequence at 1.5T. ASSESSMENT: Subjects were scanned during breath-hold at functional residual capacity (FRC) and total lung capacity (TLC) through noncontrast-enhanced MRI and CT. Expiratory-inspiratory differences in MR signal-intensity (Δ1 H-MRI) and CT-density (ΔHU) were computed to estimate regional ventilation. MR and CT images were also evaluated using a CF-specific scoring system. STATISTICAL TESTS: Quadratic regression, Spearman's correlation, one-way analysis of variance (ANOVA). RESULTS: Δ1 H-MRI maps were sensitive to ventilation heterogeneity related to gravity dependence in healthy lung and to ventilation impairment in CF lung disease. A high correlation was found between MRI and CT ventilation maps (R2 = 0.79, P < 0.001). Globally, Δ1 H-MRI and ΔHU decrease with increasing morphological score (respectively, R2 = 0.56, P < 0.001 and R2 = 0.31, P < 0.001). Locally, Δ1 H-MRI was higher in healthy regions (median 15%) compared to regions with bronchiectasis, air trapping, consolidation, and to segments fed by airways with bronchial wall thickening (P < 0.001). DATA CONCLUSION: Multivolume noncontrast-enhanced MRI, as a nonionizing imaging modality that can be used on nearly any MRI scanner without specialized equipment or gaseous tracers, may be particularly valuable in CF care, providing a new imaging biomarker to detect early alterations in regional lung structure-function. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 3 J. MAGN. RESON. IMAGING 2018;48:531-542.

Clinical potential for imaging in patients with asthma and other lung disorders.

The ability of lung imaging to phenotype patients, determine prognosis, and predict response to treatment is expanding in clinical and translational research. The purpose of this perspective is to describe current imaging modalities that might be useful clinical tools in patients with asthma and other lung disorders and to explore some of the new developments in imaging modalities of the lung. These imaging modalities include chest radiography, computed tomography, lung magnetic resonance imaging, electrical impedance tomography, bronchoscopy, and others.

Quantitative CT characterization of pediatric lung development using routine clinical imaging.

BACKGROUND: The use of quantitative CT analysis in children is limited by lack of normal values of lung parenchymal attenuation. These characteristics are important because normal lung development yields significant parenchymal attenuation changes as children age. OBJECTIVE: To perform quantitative characterization of normal pediatric lung parenchymal X-ray CT attenuation under routine clinical conditions in order to establish a baseline comparison to that seen in pathological lung conditions. MATERIALS AND METHODS: We conducted a retrospective query of normal CT chest examinations in children ages 0-7 years from 2004 to 2014 using standard clinical protocol. During these examinations semi-automated lung parenchymal segmentation was performed to measure lung volume and mean lung attenuation. RESULTS: We analyzed 42 CT examinations in 39 children, ages 3 days to 83 months (mean ± standard deviation [SD] = 42 ± 27 months). Lung volume ranged 0.10-1.72 liters (L). Mean lung attenuation was much higher in children younger than 12 months, with values as high as -380 Hounsfield units (HU) in neonates (lung volume 0.10 L). Lung volume decreased to approximately -650 HU by age 2 years (lung volume 0.47 L), with subsequently slower exponential decrease toward a relatively constant value of -860 HU as age and lung volume increased. CONCLUSION: Normal lung parenchymal X-ray CT attenuation decreases with increasing lung volume and age; lung attenuation decreases rapidly in the first 2 years of age and more slowly thereafter. This change in normal lung attenuation should be taken into account as quantitative CT methods are translated to pediatric pulmonary imaging.

Menarche? A Case of Abdominal Pain and Vaginal Bleeding in a Preadolescent Girl.

Abdominal pain is one of the most common complaints in the pediatric ED. Because of the broad range of potential diagnoses, it can pose challenges in diagnosis and therapy in the preadolescent girl. An 11-year-old previously healthy girl presented to our pediatric ED with fever, decreased appetite, vaginal bleeding, and abdominal pain. Initial evaluation yielded elevated creatinine levels, leukocytosis with bandemia, elevated inflammatory markers, and urine concerning for a urinary tract infection. She began receiving antibiotics for presumed pyelonephritis and was admitted to the hospital. After worsening respiratory status and continued abdominal pain, a computed tomography scan was obtained and a pelvic foreign body and abscess were identified. Adolescent gynecology was consulted for examination under anesthesia for abscess drainage and foreign body removal. A foreign body in the vagina or uterus can present as vaginal discharge, vaginal bleeding, abdominal pain, dysuria, or hematuria. Because symptoms can be diverse, an intravaginal or uterine foreign body should be considered in the preteen female patient presenting to the ED with abdominal pain.

The incidental pulmonary nodule in a child. Part 1: recommendations from the SPR Thoracic Imaging Committee regarding characterization, significance and follow-up.

No guidelines are in place for the follow-up and management of pulmonary nodules that are incidentally detected on CT in the pediatric population. The Fleischner guidelines, which were developed for the older adult population, do not apply to children. This review summarizes the evidence collected by the Society for Pediatric Radiology (SPR) Thoracic Imaging Committee in its attempt to develop pediatric-specific guidelines.Small pulmonary opacities can be characterized as linear or as ground-glass or solid nodules. Linear opacities and ground-glass nodules are extremely unlikely to represent an early primary or metastatic malignancy in a child. In our review, we found a virtual absence of reported cases of a primary pulmonary malignancy presenting as an incidentally detected small lung nodule on CT in a healthy immune-competent child.Because of the lack of definitive information on the clinical significance of small lung nodules that are incidentally detected on CT in children, the management of those that do not have the typical characteristics of an intrapulmonary lymph node should be dictated by the clinical history as to possible exposure to infectious agents, the presence of an occult immunodeficiency, the much higher likelihood that the nodule represents a metastasis than a primary lung tumor, and ultimately the individual preference of the child's caregiver. Nodules appearing in children with a history of immune deficiency, malignancy or congenital pulmonary airway malformation should not be considered incidental, and their workup should be dictated by the natural history of these underlying conditions.

Is chest CT useful in newborn screened infants with cystic fibrosis at 1 year of age?

RATIONALE: Sensitive outcome measures applicable in different centres to quantify and track early pulmonary abnormalities in infants with cystic fibrosis (CF) are needed both for clinical care and interventional trials. Chest CT has been advocated as such a measure yet there is no validated scoring system in infants. OBJECTIVES: The objectives of this study were to standardise CT data collection across multiple sites; ascertain the incidence of bronchial dilatation and air trapping in newborn screened (NBS) infants with CF at 1 year; and assess the reproducibility of Brody-II, the most widely used scoring system in children with CF, during infancy. METHODS: A multicentre observational study of early pulmonary lung disease in NBS infants with CF at age 1 year using volume-controlled chest CT performed under general anaesthetic. MAIN RESULTS: 65 infants with NBS-diagnosed CF had chest CT in three centres. Small insignificant variations in lung recruitment manoeuvres but significant centre differences in radiation exposures were found. Despite experienced scorers and prior training, with the exception of air trapping, inter- and intraobserver agreement on Brody-II score was poor to fair (eg, interobserver total score mean (95% CI) κ coefficient: 0.34 (0.20 to 0.49)). Only 7 (11%) infants had a total CT score ≥ 12 (ie, ≥ 5% maximum possible) by either scorer. CONCLUSIONS: In NBS infants with CF, CT changes were very mild at 1 year, and assessment of air trapping was the only reproducible outcome. CT is thus of questionable value in infants of this age, unless an improved scoring system for use in mild CF disease can be developed.

An official American Thoracic Society clinical practice guideline: classification, evaluation, and management of childhood interstitial lung disease in infancy.

BACKGROUND: There is growing recognition and understanding of the entities that cause interstitial lung disease (ILD) in infants. These entities are distinct from those that cause ILD in older children and adults. METHODS: A multidisciplinary panel was convened to develop evidence-based guidelines on the classification, diagnosis, and management of ILD in children, focusing on neonates and infants under 2 years of age. Recommendations were formulated using a systematic approach. Outcomes considered important included the accuracy of the diagnostic evaluation, complications of delayed or incorrect diagnosis, psychosocial complications affecting the patient's or family's quality of life, and death. RESULTS: No controlled clinical trials were identified. Therefore, observational evidence and clinical experience informed judgments. These guidelines: (1) describe the clinical characteristics of neonates and infants (<2 yr of age) with diffuse lung disease (DLD); (2) list the common causes of DLD that should be eliminated during the evaluation of neonates and infants with DLD; (3) recommend methods for further clinical investigation of the remaining infants, who are regarded as having "childhood ILD syndrome"; (4) describe a new pathologic classification scheme of DLD in infants; (5) outline supportive and continuing care; and (6) suggest areas for future research. CONCLUSIONS: After common causes of DLD are excluded, neonates and infants with childhood ILD syndrome should be evaluated by a knowledgeable subspecialist. The evaluation may include echocardiography, controlled ventilation high-resolution computed tomography, infant pulmonary function testing, bronchoscopy with bronchoalveolar lavage, genetic testing, and/or lung biopsy. Preventive care, family education, and support are essential.

Scoring of chest CT in children with cystic fibrosis: state of the art.

Chest CT has been proposed as a surrogate outcome measure in the evaluation of cystic fibrosis lung disease. Quantitative evaluation of chest CT findings requires application of a scoring system to derive numerical values. Several scoring systems are in use. These mostly rely on a subjective judgement of the severity and extent of various features of cystic fibrosis lung disease, including bronchiectasis, bronchial wall thickening, mucous plugging and air-trapping. Scores can subsequently be added to produce a total score. The precision or reproducibility of scoring systems has been assessed but with heterogeneous statistical approaches. Total scores appear to have high levels of reproducibility, but this might mask poorer levels of agreement for individual observations and component scores. It can also be questioned whether total scores are biologically meaningful, as compared to assessments of individual features. Various studies suggest that CT scores give an accurate indicator of the severity of disease, and CT scores might be the best predictors of long-term outcome, but data in this area are limited. CT scores are more sensitive than traditional lung-function indices such as FEV; however the lung clearance index, by multiple breath washout, appears to offer comparable sensitivity to CT. It is not clear whether CT scores are adequately responsive to changes in disease severity in the short to medium term; this is a challenge to the use of CT as a surrogate outcome measure for clinical trials of therapies specific to cystic fibrosis. Cystic fibrosis scoring would benefit from greater levels of standardisation in terms of CT techniques, scoring system, training of observers and measures of reproducibility. Automated approaches to quantifying CT parameters might also offer improved precision. The benefits of chest CT must be weighed against the principal drawback of radiation exposure. The case for more widespread use of chest CT would be strengthened if precision of CT scoring were improved.

Congenital lung lesions: prenatal MRI and postnatal findings.

BACKGROUND: Congenital lung lesions refer to a spectrum of malformations and developmental abnormalities of the foregut, pulmonary airways and vasculature. These lesions range from small, asymptomatic to large space-occupying masses that can increase risk of fetal death and respiratory compromise after birth. Prenatal sonography has been used for routine screening in pregnancy. The advent of prenatal magnetic resonance imaging leads to complementary use in the diagnosis of fetal anomalies, including in fetuses with congenital lung lesions. OBJECTIVE: To determine whether fetal MRI can differentiate congenital lung lesions by comparing prenatal diagnosis with postnatal imaging and pathology. MATERIALS AND METHODS: In a 4-year period, 76 fetuses with suspected lung lesions were referred for fetal MRI. We retrospectively reviewed the MR exams and assigned a specific diagnosis based on predetermined criteria. We then compared the prenatal diagnosis to postnatal imaging and pathology. RESULTS: Of 76 cases, 7 were excluded because of an alternative diagnosis. Of the 69 remaining patients, 3 died and 13 were lost to follow-up. Among the 53 patients, there were 56 lung lesions. Four of these lesions were difficult to diagnose because of size and location. Based on imaging records we gave the remaining 52 lesions a specific prenatal diagnosis: 28 congenital pulmonary airway malformations (CPAM), 4 bronchopulmonary sequestrations (BPS), 9 cases of overinflation, 9 hybrid lesions and 2 bronchogenic cysts. The prenatal diagnosis was concordant with postnatal evaluation in 51 of the 52 lung lesions. One fetus given the diagnosis of CPAM prenatally was diagnosed with a hybrid lesion postnatally. CONCLUSION: Prenatal MRI is highly accurate in defining congenital lung anomalies. When fetal MRI findings suggest a specific diagnosis, postnatal findings confirmed the prenatal MRI diagnosis in 98% of cases.

Chest computed tomography scores of severity are associated with future lung disease progression in children with cystic fibrosis.

RATIONALE: Most children with cystic fibrosis (CF) experience a slow decline in spirometry, although some children continue to be at risk for more significant lung disease progression. Chest computed tomography (CT) scans have been shown to be more sensitive to changes in lung disease than spirometry and may provide a means for predicting future lung disease progression. OBJECTIVES: We hypothesized that Brody chest CT scan scores obtained in 2000 in a prospectively monitored cohort of children with CF would be associated with the most recent measures of lung disease severity. METHODS: Brody chest CT scan scores were calculated for 81 children enrolled in the Wisconsin CF Neonatal Screening Project. Multivariable linear regression was used to determine associations between Brody scores and the most recent (age 21 yr or June 30, 2010, whichever was later) measures of CF lung disease. MEASUREMENTS AND MAIN RESULTS: The mean observation time after the chest CT scan was 7.5 years. Brody chest CT scan scores were significantly associated with the most recent measures of spirometry (P < 0.001) and Wisconsin and Brasfield chest radiograph scores (P < 0.001). The strength of this association was much stronger than spirometry obtained near the time of the chest CT scan (P < 0.01) but not chest radiograph scores. CONCLUSIONS: Chest CT scan scores are associated with future lung disease severity, and quantitative chest imaging(chest CT scan and chest radiograph scores) is more strongly associated with future lung disease severity than measures of spirometry. These findings may help clinicians identify patients at risk of future lung disease progression.

Structural lung disease in preschool children with cystic fibrosis: An 18 month natural history study.

BACKGROUND: This study was performed to describe the natural history of CF lung disease in young children over an 18 month period to assess the use of CT scanning as an outcome measure for intervention trials. METHODS: Chest CT scans were obtained at baseline and after 18 months in 42 two- to six-year-old children with CF. CT scans were scored by 2 experienced radiologists for the presence and severity of bronchiectasis, mucous plugging, and air trapping. RESULTS: Mean age at baseline 3.5 (1.3) (mean, sd) years. One or more findings of CF lung disease was seen on the first CT in 27 (64%) and at 18 months in 30 (75%). From baseline to 18 months bronchiectasis, mucous plugging, and air trapping increased from 50% to 53%, 14% to 28%, and 48% to 58% respectively. There was marked variability in the rate of progression, with subjects commonly showing improvement in lung disease. Bronchiectasis worsened in 14 (33%) and improved in 13 (31%). Single subjects with F508del/class III and F508del/class V demonstrated greater worsening and improvement respectively than F508del homozygous and class I genotypes. CONCLUSIONS: The natural history of CF lung disease over 18 months varies widely between subjects. Factors including genotype may affect natural history as well as the effectiveness of mediators and could be an important confounder if not recognized. These findings suggest that the use of CT scanning as an outcome surrogate for CF lung disease in young children may be more challenging than has been previously recognized.

Sirolimus for angiomyolipoma in tuberous sclerosis complex or lymphangioleiomyomatosis.

BACKGROUND: Angiomyolipomas in patients with the tuberous sclerosis complex or sporadic lymphangioleiomyomatosis are associated with mutations in tuberous sclerosis genes resulting in constitutive activation of the mammalian target of rapamycin (mTOR). The drug sirolimus suppresses mTOR signaling. METHODS: We conducted a 24-month, nonrandomized, open-label trial to determine whether sirolimus reduces the angiomyolipoma volume in patients with the tuberous sclerosis complex or sporadic lymphangioleiomyomatosis. Sirolimus was administered for the first 12 months only. Serial magnetic resonance imaging of angiomyolipomas and brain lesions, computed tomography of lung cysts, and pulmonary-function tests were performed. RESULTS: Of the 25 patients enrolled, 20 completed the 12-month evaluation, and 18 completed the 24-month evaluation. The mean (+/-SD) angiomyolipoma volume at 12 months was 53.2+/-26.6% of the baseline value (P<0.001) and at 24 months was 85.9+/-28.5% of the baseline value (P=0.005). At 24 months, five patients had a persistent reduction in the angiomyolipoma volume of 30% or more. During the period of sirolimus therapy, among patients with lymphangioleiomyomatosis, the mean forced expiratory volume in 1 second (FEV1) increased by 118+/-330 ml (P=0.06), the forced vital capacity (FVC) increased by 390+/-570 ml (P<0.001), and the residual volume decreased by 439+/-493 ml (P=0.02), as compared with baseline values. One year after sirolimus was discontinued, the FEV1 was 62+/-411 ml above the baseline value, the FVC was 346+/-712 ml above the baseline value, and the residual volume was 333+/-570 ml below the baseline value; cerebral lesions were unchanged. Five patients had six serious adverse events while receiving sirolimus, including diarrhea, pyelonephritis, stomatitis, and respiratory infections. CONCLUSIONS: Angiomyolipomas regressed somewhat during sirolimus therapy but tended to increase in volume after the therapy was stopped. Some patients with lymphangioleiomyomatosis had improvement in spirometric measurements and gas trapping that persisted after treatment. Suppression of mTOR signaling might constitute an ameliorative treatment in patients with the tuberous sclerosis complex or sporadic lymphangioleiomyomatosis. (ClinicalTrials.gov number, NCT00457808.)

Patient-derived granulocyte/macrophage colony-stimulating factor autoantibodies reproduce pulmonary alveolar proteinosis in nonhuman primates.

RATIONALE: Granulocyte/macrophage colony-stimulating factor (GM-CSF) autoantibodies (GMAb) are strongly associated with idiopathic pulmonary alveolar proteinosis (PAP) and are believed to be important in its pathogenesis. However, levels of GMAb do not correlate with disease severity and GMAb are also present at low levels in healthy individuals. OBJECTIVES: Our primary objective was to determine whether human GMAb would reproduce PAP in healthy primates. A secondary objective was to determine the concentration of GMAb resulting in loss of GM-CSF signaling in vivo (i.e., critical threshold). METHODS: Nonhuman primates (Macaca fascicularis) were injected with highly purified, PAP patient-derived GMAb in dose-ranging (2.2-50 mg) single and multiple administration studies, and after blocking antihuman immunoglobulin immune responses, in chronic administration studies maintaining serum levels greater than 40 microg/ml for up to 11 months. MEASUREMENTS AND MAIN RESULTS: GMAb blocked GM-CSF signaling causing (1) a milky-appearing bronchoalveolar lavage fluid containing increased surfactant lipids and proteins; (2) enlarged, foamy, surfactant-filled alveolar macrophages with reduced PU.1 and PPARgamma mRNA, and reduced tumor necrosis factor-alpha secretion; (3) pulmonary leukocytosis; (4) increased serum surfactant protein-D; and (5) impaired neutrophil functions. GM-CSF signaling varied inversely with GMAb concentration below a critical threshold of 5 microg/ml, which was similar in lungs and blood and to the value observed in patients with PAP. CONCLUSIONS: GMAb reproduced the molecular, cellular, and histopathologic features of PAP in healthy primates, demonstrating that GMAb directly cause PAP. These results have implications for therapy of PAP and help define the therapeutic window for potential use of GMAb to treat other disorders.

Ten rules for ordering chest CTs.

These "rules" are suggestions for clinicians who order chest computed tomography (CTs). The first three address CT scanning technique and the ordering details that we find cause the most confusion. The next three are on patient preparation, and specifically the use of sedation and anesthesia. Radiation risk is next, and we end with three, more philosophical, rules on how we can best work together as clinicians and imagers. This is not a complete or systematic review. You won't find detailed references (or any references for that matter), descriptions of the latest techniques, or lists of sample protocols. We hope that the reader will consult his or her imaging colleagues when more specific guidance is needed. The goal of this article is to provide simple answers to frequently asked questions and to address some of the concerns that arise when deciding how to perform a chest CT scan in a child. These are the opinions of the authors, two pediatric radiologists with special interest in chest imaging and 50 years combined experience in working with clinical colleagues to provide the best imaging care for their patients. We hope that sharing these thoughts will help to decrease confusion and increase understanding to the benefit of the children we serve.

Neuroendocrine cell hyperplasia of infancy: diagnosis with high-resolution CT.

OBJECTIVE: Neuroendocrine cell hyperplasia of infancy is a form of childhood interstitial lung disease originally reported as persistent tachypnea of infancy. Reports of small series of cases and anecdotal experience have suggested that this disorder may have a consistent CT pattern. The purpose of this study was to review the CT findings in children with neuroendocrine cell hyperplasia of infancy to determine the findings at high-resolution CT, the diagnostic accuracy of CT compared with biopsy, and interrater reliability. MATERIALS AND METHODS: Images from 23 CT examinations of children with biopsy-proven neuroendocrine cell hyperplasia of infancy and six CT examinations of children with other childhood interstitial lung diseases were reviewed by two pediatric radiologists with special expertise in thoracic imaging. Identifying digital data were removed, and images were reviewed without clinical data. A CT assessment form was completed for each patient. RESULTS: Ground-glass opacification was the most common finding in patients with neuroendocrine cell hyperplasia of infancy. The right middle lobe and lingula were most commonly involved. Air trapping with a mosaic pattern was the second most common finding. Interrater reliability was very good with a kappa value of 0.93. The sensitivity and specificity of CT in the diagnosis of neuroendocrine cell hyperplasia of infancy were at least 78% and 100%. CONCLUSION: Neuroendocrine cell hyperplasia of infancy can have a characteristic appearance on high-resolution CT scans, the imaging findings being useful in differentiating neuroendocrine cell hyperplasia of infancy from other types of childhood interstitial lung disease. The appearance aids radiologists in suggesting a specific diagnosis but does not exclude this diagnosis; in 17-22% of cases, the readers in this study did not suggest the diagnosis of neuroendocrine cell hyperplasia of infancy when it was present.

Quality initiatives: department scorecard: a tool to help drive imaging care delivery performance.

The radiology department at a midwestern U.S. children's hospital has created a scorecard that is presented quarterly to the institutional leadership and is available to all radiology employees on the institutional intranet. The scorecard currently has 33 measures in six areas: clinical services (safety, quality, timeliness); education; research; professionalism, communication, and user satisfaction; finances and administration; and staffing. For each measure, the goal, current value of the measure, interval at which the measure is updated, date of last update, and previous value of the measure are listed. Each measure was reviewed over time to determine those measures for which target goals were met. Results indicate that a visible and transparent department scorecard is one of the more powerful tools available to the radiology leadership to call attention to and improve performance in specific areas. The use of such a scorecard can help develop a departmental culture of quality improvement, focus healthcare providers on specific quality improvement projects, and drive departmental performance.