Children With Elbow Injuries and Sonographic Elevated Posterior Fat Pad but No Identifiable Posterior Fat Pad on Lateral Radiographs: A Case Series.

Point of Care Ultrasound (POCUS) is used to evaluate the injured pediatric elbow. Standard of care, however, remains radiography. POCUS performed in the setting of normal radiographs have been obtained may demonstrate radiologic occult lipohemarthrosis indicative of occult fracture. We reviewed our pediatric emergency department (PED) POCUS archive for lipohemarthrosis, and then isolated those cases with normal elbow radiography. Radiography was deemed to be normal per the interpretation of the treating PED physician, and was reviewed for this series by an experienced ABR board certified pediatric radiologist. Fracture on POCUS was defined as fracture line or lipohemarthrosis in a posterior sagittal or transverse view of the distal humerus. Fracture was confirmed by signs of cortical healing on follow-up radiography, or clinical course consistent with fracture as documented by an orthopedist. We identified four children with elbow fractures who had no fracture line or elevated posterior fat pad on radiography but demonstrated lipohemarthrosis on POCUS. POCUS may elicit evidence of fracture even after normal radiography, and POCUS findings suggesting occult fracture may allow for more effective guidance on discharge.

Use of Point-of-Care Ultrasound to Identify Occult Fractures of the Tibia in the Pediatric Emergency Department: A Case Series.

BACKGROUND: Although point-of-care ultrasound (POCUS) has been shown to be useful in the identification of both pediatric and adult long-bone fractures in the emergency setting, radiography remains the standard of care. Emergency physicians are often faced with the dilemma of how to evaluate and treat the child with lower leg injury and physical examination concerning for fracture but no readily identifiable fracture line on radiography. CASE REPORTS: We present four cases in which POCUS was used to diagnose a radiographically occult fracture of the proximal tibia in young children. This is the first case series of occult fracture of the tibia diagnosed with POCUS. WHY SHOULD AN EMERGENCY PHYSICIAN BE AWARE OF THIS?: POCUS can demonstrate evidence of fracture even after unremarkable radiography is obtained, and POCUS findings consistent with fracture might allow for more effective guidance on discharge.

Feasibility study of a novel portable digital radiography system modified for fluoroscopy in the neonatal intensive care unit.

BACKGROUND: A portable radiographic system capable of fluoroscopic imaging in the neonatal intensive care unit (NICU) potentially benefits critically ill neonates by eliminating the need to transport them to a fluoroscopy suite. OBJECTIVE: To evaluate whether a portable bedside fluoroscopy system in the NICU can deliver comparable image quality at a similar dose rate to a standard system in a fluoroscopy suite. MATERIALS AND METHODS: In phase A, 20 patients <3 years of age and scheduled to undergo upper gastrointestinal series (upper GI) or voiding cystourethrograms (VCUG) in the radiology fluoroscopy suite were recruited to evaluate a portable fluoroscopic unit. A modified portable radiographic system with a cassette-sized detector and an in-room fluoroscopy system were sequentially used in the same examination. Four radiologists compared the image quality of 20 images from each system using the Radlex score (1-4) for five image quality attributes. The radiation dose rates for the portable and in-suite systems were collected. In phase B, fluoroscopy studies were performed in 5 neonates in the NICU and compared to the 20 previous neonatal studies performed in the department. Clinical workflow, examination time, fluoroscopy time, scattered radiation dose and patient radiation dose were evaluated. RESULTS: In phase A, average dose rates for in-room and portable systems were equivalent, (0.322 mGy/min and 0.320 mGy/min, respectively). Reader-averaged Radlex scores for in-room and portable systems were statistically significantly greater (P<0.05) for all attributes on the portable system except for image contrast. In phase B, scattered radiation from the average fluoroscopy time (26 s) was equivalent to the scattered radiation of 2.6 portable neonatal chest radiographs. Procedure time and diagnostic quality were deemed equivalent. The average dose rate in the NICU with the portable system was 0.21 mGy/min compared to 0.29 mGy/min for the in-room system. CONCLUSION: The portable fluoroscopy unit is capable of providing comparable image quality at equivalent dose levels to an in-room system for neonates with minimal risks to the staff and other patients in the NICU.

Adapting Surgical Clerkship Curricula in Response to the COVID-19 Pandemic.

BACKGROUND: Coronavirus disease-19 (COVID-19) impacted medical education and led to the significant modification or suspension of clinical clerkships and rotations. OBJECTIVES: To describe a revised surgery clerkship curriculum, in which we divided in-person clinical teaching into smaller groups of students and adopted online-based learning to foster student and patient safety while upholding program standards. METHODS: The third-year surgery core clerkship of a 4-year international English-language program at the Medical School for International Health at Ben Gurion University of the Negev, Beer Sheva, Israel, was adapted by dividing students into smaller capsules for in-person learning and incorporating online learning tools. Specifically, students were divided evenly throughout three surgical departments, each of which followed a different clinical schedule. RESULTS: National Board of Medical Examiners clerkship scores of third-year medical students who were returning to in-person clinical clerkships after transitioning from 8 weeks of online-based learning showed no significant difference from the previous 2 years. CONCLUSIONS: To manage with the restrictions caused by COVID-19 pandemic, we designed an alternative approach to a traditional surgical clerkship that minimized the risk of exposure and used online learning tools to navigate scheduling challenges. This curriculum enabled students to complete their clinical rotation objectives and outcomes while maintaining program standards. Furthermore, this approach provided a number of benefits, which medical schools should consider adopting the model into practice even in a post-pandemic setting.

Radiographic overlap of recurrent Caffey disease and chronic recurrent multifocal osteomyelitis (CRMO) with considerations of molecular origins.

Caffey disease, or infantile cortical hyperostosis, classically describes a self-limited inflammatory disorder that presents in the infant with fussiness, focal swelling and sometimes fever. Imaging is conventionally limited to radiography, which shows mild to profound subperiosteal bone formation and sometimes deformity. This disease was not uncommonly diagnosed in the late 20th century. Interestingly, the disease may not just occur in the infant, and it may be due to a genetic mutation in the alpha-one chain of type 1 collagen (COL1A1). Recurrent or delayed onset in the older child or adolescent also occurs. In more recent years, another type of inflammatory bone disorder, chronic sterile osteomyelitis, has been frequently recognized and, depending on the radiographic stage or the diagnostic modality used, may have characteristics overlapping with Caffey disease. In this review, we discuss the demographics, imaging and known etiologies for Caffey disease and chronic recurrent multifocal osteomyelitis and raise the possibility of similar molecular origins.

Radiation dose monitoring in pediatric fluoroscopy: comparison of fluoroscopy time and dose-area product thresholds for identifying high-exposure cases.

BACKGROUND: Fluoroscopy time has been used as a surrogate for radiation dose monitoring in pediatric fluoroscopy; however it does not account for factors such as magnification or collimation. Dose-area product (DAP) is a more accurate measure of radiation exposure but its dependence on patient weight and body-part thickness is a challenge in children of varying ages. OBJECTIVE: To determine whether fluoroscopy time and DAP produce concurrent results when they are used to identify high-exposure cases, and to establish radiation dose thresholds for our institution. MATERIALS AND METHODS: During a 2-year period we prospectively monitored pediatric fluoroscopy studies performed at the Children's Hospital at Montefiore. We recorded study type, fluoroscopy time, DAP, patient age, weight and height. We then calculated 90th percentile fluoroscopy time and DAP thresholds for weight and age. RESULTS: We evaluated 1,011 cases (453 upper gastrointestinal [UGI] series, 266 voiding cystourethrograms [VCUGs], 120 contrast enemas, 108 speech studies, and 64 esophagrams). Fluoroscopy time demonstrated moderate correlation with DAP (rs=0.45, P<0.001, Spearman rank). DAP strongly correlated with patient weight (rs=0.71, P<0.001) and age (rs=0.70, P<0.001). Concordance of cases exceeding 90th percentile thresholds for fluoroscopy time and DAP were κ=0.27 for UGI series and κ=0.49 for VCUG for weight-based cutoffs, and κ=0.36 for UGI series and κ=0.40 for VCUG for age-based cutoffs. CONCLUSION: The limited correlation of fluoroscopy time with DAP suggests these methods are not equivalent for dose monitoring. However, the strong correlation of DAP with patient weight and age presents a challenge for establishing DAP thresholds in children, who range widely in size. Despite controlling for weight or age, there was limited overlap of cases exceeding the 90th percentile threshold for fluoroscopy time and DAP. This further reinforces the non-overlapping outcome of these two methods and indicates that fluoroscopy time might be inadequate for dose monitoring.

Consensus Report by Pediatric Acute Lung Injury and Sepsis Investigators and Pediatric Blood and Marrow Transplantation Consortium Joint Working Committees: Supportive Care Guidelines for Management of Veno-Occlusive Disease in Children and Adolescents, Part 1: Focus on Investigations, Prophylaxis, and Specific Treatment.

Veno-occlusive disease (VOD) is a common and potentially fatal complication in children undergoing hematopoietic cell transplantation (HCT). It occurs in about one-third of all patients undergoing transplantation and is fatal in 50% of patients with severe disease. Early intervention and specific treatment with defibrotide are associated with improved outcomes. However, there is a lack of supportive care guidelines for management of the multiorgan dysfunction seen in most cases. There is high variability in the management of VOD, which may contribute to the increased morbidity and mortality. Although there is ample research in the specific treatment of VOD, there is paucity of literature regarding the management of ascites, transfusions requirements, fluids and electrolyte dysfunction, delirium, and investigations in children with VOD. The joint working committees of the Pediatric Acute Lung Injury and Sepsis Investigators and the Pediatric Blood and Marrow Transplantation Consortium collaborated to develop a series of evidence-based supportive care guidelines for management of VOD. The quality of evidence was rated and recommendations were made using Grading of Recommendations, Assessment, Development and Evaluation criteria. This manuscript is part 1 of the series and focuses on the need to develop these guidelines; methodology used to establish the guidelines; and investigations needed for diagnosis, prophylaxis, and treatment of VOD in children.

Hepatic Imaging in Neonates and Young Infants: State of the Art.

Neonatal liver disease is an important source of morbidity in the pediatric population. The manifestation of liver disease in young infants may be different than in older patients, and there are a number of diagnoses that are unique to this age group. Familiarity with these entities is important as imaging plays a key role in the diagnostic workup, and prompt diagnosis is necessary to prevent complications. This article reviews the spectrum of liver pathologies that can manifest in the first 6 months of life and is intended to educate the general radiologist who may be faced with interpretation of neonatal liver imaging. Categories of disease that will be reviewed include cholestatic diseases, tumors, vascular anomalies, and acquired diseases. The authors will also review optimization of ultrasonography (US) and magnetic resonance imaging of the liver and present a systematic method for interpretation of neonatal liver US findings in the context of clinical and laboratory findings. © RSNA, 2017.

Identifying intestinal malrotation on magnetic resonance examinations ordered for unrelated indications.

BACKGROUND: Anatomical imaging findings indicating normal bowel rotation can be identified on cross-sectional imaging, including magnetic resonance imaging (MRI) performed for non-related indications. OBJECTIVE: The goal of our study was to assess whether non-targeted MRI can accurately assess intestinal malrotation. MATERIALS AND METHODS: Four anatomical landmarks were assessed on MRIs of the chest, spine or abdomen performed from January 2006 to June 2014, on patients who also had upper gastrointestinal series (UGI) performed within 10 years of the MRI date: 1) retroperitoneal duodenum, 2) left upper quadrant duodenojejunal junction, 3) superior mesenteric artery to the left of the superior mesenteric vein, and 4) right lower quadrant cecum. Two attending radiologists, one pediatric and one abdominal radiologist, independently reviewed the MR images. The pediatric radiologist reviewed images from UGI (considered the gold standard) to determine the intestinal rotation for each case. Validation of the criteria was performed on new patients imaged through January 2016. RESULTS: The original cohort included 109 MRIs (15 chest, 41 spine and 53 abdomen) done on 109 patients (42% males, mean age: 10.2 years). If each of the 4 anatomical questions were answered "yes" (4-YES), specificity was 100% for each radiologist and malrotation was appropriately excluded. Using the 4-YES criteria, the pediatric radiologist excluded malrotation in 71 patients (65%) and the abdominal radiologist excluded it in 65 (60%), with concurrence for 57 patients. Validation of the 4-YES criteria in 23 new patients appropriately proved the 4-YES rule, with neither labeling the one new malrotation case 4-YES. CONCLUSION: If a radiologist can confidently answer "yes" to the four questions evaluated in this study, then intestinal rotation can be safely considered normal. Normal bowel rotation should be commented upon in MRI reports when these four anatomical locations are imaged, thus helping patients avoid unnecessary UGI and radiation exposure.

Non-central peripherally inserted central catheters in neonatal intensive care: complication rates and longevity of catheters relative to tip position.

BACKGROUND: Peripherally inserted central catheters (PICCs) represent a mainstay of intravascular access in the neonatal intensive care setting when long-term vascular access is needed. Ideally, PICCs should be inserted and maintained in a central position with the tip ending in the superior or inferior vena cava. This is not always achievable, and sometimes the tip remains in a peripheral location. Higher complication rates have been reported with non-central PICCs; however these findings have not been confirmed in a solely neonatal series and PICCs with tips in peripheral veins have not been studied. OBJECTIVE: To compare complication rates and length of catheter duration related to PICC position in neonates. MATERIALS AND METHODS: We conducted a retrospective analysis of all PICCs inserted in term and preterm infants in a tertiary neonatal intensive care unit between May 2007 and December 2009. A single pediatric radiologist reinterpreted the catheter tip site on initial anteroposterior (AP) chest radiographs and categorized sites as central (superior vena cava, inferior vena cava, brachiocephalic vein), intermediate (subclavian, axillary, common or external iliac veins), or peripheral (veins peripheral to axillary or external iliac veins). We analyzed complication rates and length of catheter duration among the three categories. RESULTS: We collected data on a total of 176 PICCs. Infants with PICCs in a central location had a significantly lower complication rate (18/97, 19%) than those with the PICC tip in an intermediate (24/64, 38%) or peripheral (9/15, 60%) locations (P=0.0003). Length of catheter duration was noted to be longest with central, intermediate with intermediate, and shortest with peripheral PICC tip locations (17.7±14.8 days for central vs. 11.4±10.7 days for intermediate vs. 5.4±2.5 days for peripheral, P=0.0003). CONCLUSION: A central location is ideal for the tip of a PICC. When this is not achievable, an intermediate location is preferable to a more peripheral position.

MRI usage in a pediatric emergency department: an analysis of usage and usage trends over 5 years.

BACKGROUND: Magnetic resonance imaging (MRI) usage has anecdotally increased due to the principles of ALARA and the desire to Image Gently. Aside from a single abstract in the emergency medicine literature, pediatric emergency department MRI usage has not been described. OBJECIVE: Our objective was to determine whether MRI use is indeed increasing at a high-volume urban pediatric emergency department with 24/7 MRI availability. Also, we sought to determine which exams, time periods and demographics influenced the trend. MATERIALS AND METHODS: Institutional Review Board exemption was obtained. Emergency department patient visit and exam data were obtained from the hospital database for the 2011-2015 time period. MRI usage data were normalized using emergency department patient visit data to determine usage rates. The z-test was used to compare MRI use by gender. The chi-square test was used to test for trends in MRI usage during the study period and in patient age. MRI usage for each hour and each weekday were tabulated to determine peak and trough usage times. RESULTS: MRI usage rate per emergency department patient visit was 0.36%. Headache, pain and rule-out appendicitis were the most common indications for neuroradiology, musculoskeletal and trunk exams, respectively. Usage in female patients was significantly greater than in males (0.42% vs. 0.29%, respectively, P<0.001). Usage significantly increased during the 5-year period (P<0.001). Use significantly increased from age 3 to 17 (0.011% to 1.1%, respectively, P<0.001). Sixty percent of exams were performed after-hours, the highest volume during the 10 p.m. hour and lowest between 4 a.m. and 9 a.m. MRI use was highest on Thursdays and lowest on Sundays (MRI on 0.45% and 0.22% of patients, respectively). CONCLUSION: MRI use in children increased during the study period, most notably in females, on weekdays and after-hours.

Three-dimensional ultrasound of the neonatal brain: technical approach and spectrum of disease.

Brain pathology is an important cause of morbidity and mortality in neonates, especially in the premature population. While conventional two-dimensional neurosonography is traditionally used for screening, diagnosis and monitoring of brain disorders such as germinal matrix hemorrhage, periventricular leukomalacia and hydrocephalus, three-dimensional ultrasonography has gained popularity in a variety of clinical applications in recent years. Three-dimensional ultrasonography is not yet widely utilized in pediatric imaging but is a potentially powerful tool for evaluating the neonatal brain. Three-dimensional neurosonography allows imaging of the entire brain in a single volumetric sweep and offers the capability of reconstructing images in the axial plane and performing volumetric analyses that are unavailable in conventional two-dimensional neurosonography. The purpose of this article is two-fold: (1) to present the technical aspects of three-dimensional neurosonography and (2) to illustrate the potential applications of three-dimensional neurosonography in the context of commonly encountered neonatal neuropathology.

Value of Focused Appendicitis Ultrasound and Alvarado Score in Predicting Appendicitis in Children: Can We Reduce the Use of CT?

OBJECTIVE: The purpose of this study was to evaluate the effectiveness of focused appendicitis ultrasound combined with Alvarado score to accurately identify appendicitis in children in whom it is suspected, thereby reducing unnecessary CT examinations and associated radiation exposure. MATERIALS AND METHODS: We retrospectively evaluated the focused appendicitis ultrasound, CT, clinical, and laboratory findings of 522 consecutively registered children (231 boys, 291 girls; mean age, 13.04 [SD, 5.02] years; range, 0.74 months-21 years) who underwent focused appendicitis ultrasound for abdominal pain in a pediatric emergency department from January 2008 through October 2009. All children underwent surgery or clinical follow-up to exclude missed appendicitis. Sonographic findings were characterized as positive, negative, or inconclusive (appendix not visualized). Alternative diagnoses were noted. Alvarado score (0-10 points based on multiple clinical criteria) was determined. Focused appendicitis ultrasound and Alvarado score results were compared with surgical and pathologic reports. RESULTS: Both focused appendicitis ultrasound results and Alvarado score were associated with likelihood of surgery for appendicitis (p = 0.0001). Focused appendicitis ultrasound had conclusive results: 105 positive and 27 negative in 132 of 522 (25.2%) children. In the 390 of 522 (74.7%) children with inconclusive focused appendicitis ultrasound findings, 43 of 390 (11.0%) eventually had a diagnosis of appendicitis with CT (n = 26) or Alvarado score (n = 17). Among children with inconclusive focused appendicitis ultrasound findings and an Alvarado score less than 5 (241/522, 46.1%), only one patient had appendicitis. The negative predictive value (NPV) of inconclusive ultrasound findings and low Alvarado score combined was 99.6%. Among children with inconclusive focused appendicitis ultrasound findings and an Alvarado score of 5-8, the NPV decreased to 89.7%. CONCLUSION: Children with inconclusive focused appendicitis ultrasound findings and a low Alvarado score are extremely unlikely to have appendicitis (NPV, 99.6%). Avoiding unnecessary CT of these patients is a safe approach to diagnosis.

MRI findings in pediatric patients with scurvy.

In modern times scurvy is a rarely encountered disease caused by ascorbic acid (vitamin C) deficiency. However, sporadic cases of scurvy persist, particularly within the pediatric population. Recent individual case reports highlight an increased incidence of scurvy among patients with autism or developmental delay, with isolated case reports detailing the magnetic resonance imaging (MRI) findings of scurvy in these pediatric populations. We present the MRI findings of scurvy in four patients with autism or developmental delay, and review the literature on MRI findings in pediatric patients with scurvy. Despite its rarity, the radiologist must consider scurvy in a pediatric patient with a restricted diet presenting with arthralgia or myalgia.

Appropriateness of imaging studies ordered by emergency medicine residents: results of an online survey.

OBJECTIVE: The purpose of this study is to determine the proficiency of emergency medicine residents in selecting appropriate radiologic examinations for specific clinical scenarios and to ascertain whether their training improves competency in this area over the course of their residency. MATERIALS AND METHODS: An online multiple-choice questionnaire was created. It included 10 clinical scenarios excerpted from the American College of Radiology Appropriateness Criteria guidelines and instructed residents to select the most appropriate initial imaging study. A link and invitation to the survey were e-mailed to the residency program directors and coordinators of all American Council for Graduate Medical Education-accredited emergency medicine residency training programs with the request that they be forwarded to their current residents. Responses were graded, with correct answers derived from the American College of Radiology guidelines. Results were stratified by year of emergency medicine training, and an analysis of variance was performed. RESULTS: A total of 583 residents from at least 77 different emergency medicine residency training programs completed the survey. Overall, the average number of questions answered correctly was 7.1 of 10 (SD, 1.2). First-through fourth-year residents averaged 6.9 (SD, 1.3), 7.1 (SD, 1.2), 7.1 (SD, 1.1), and 7.5 (SD, 1.1) correct answers, respectively. Analysis of variance found no significant difference between the scores of the four classes (p = 0.09). CONCLUSION: Emergency medicine residents do not show significant improvement over the course of their residency in their ability to choose appropriate imaging studies. This finding suggests that there is a role for more-rigorous focused instruction to better familiarize residents with appropriateness guidelines for diagnostic imaging selection.

Does bedside sonographic measurement of the inferior vena cava diameter correlate with central venous pressure in the assessment of intravascular volume in children?

OBJECTIVES: Previous studies demonstrated that the collapsibility index (percent decrease in inferior vena cava [IVC] diameter with inspiration) of 50% or greater and an IVC/aorta ratio of 0.8 or less correlated with a low intravascular volume. Our study sought to determine if bedside ultrasound (BUS) measurements of the IVC diameter correlate with central venous pressure (CVP) measurements as an indicator of intravascular volume status in acutely ill children. METHODS: A convenience sample of children younger than 21 years who were admitted to the pediatric critical care unit and required CVP monitoring had BUS measurements of both IVC and aortic diameters with simultaneous CVP measurement. The collapsibility index (sagittal view) and IVC/aorta ratio (transverse view) were calculated from these measurements. A CVP of 8 mm Hg or less was considered as a marker for decreased intravascular volume. RESULTS: Of the 51 participants, 21 (43%) had a CVP of 8 mm Hg or less. Eight (16%) of 51 children had a collapsibility index 50% or greater, and 8 (18%) of 43 had an IVC/aorta ratio of 0.8 or less. The sensitivity of a collapsibility index 0.5 or greater to predict a CVP of 8 mm Hg or less was 14%, the specificity was 83%, the positive predictive value was 38%, and the negative predictive value was 57%. Neither collapsibility index (r = -0.23, P = 0.11) nor IVC/aorta (r = -0.19, P = 0.22) correlated with CVP in assessing intravascular volume in our study population. CONCLUSIONS: Based on these data, the IVC and aortic measurements by BUS are not reliable indicators of intravascular volume (as determined by CVP) in acutely ill children.

COVID-Necessitated Online Radiology Elective Improves Student Imaging Appropriateness in Clinical Case Vignettes.

RATIONALE AND OBJECTIVES: The use of imaging in medicine has increased considerably over the previous decades, contributing to significant inefficiency of use. Radiology education varies amongst institutions without standardized learning objectives. Consequently, many physicians and student doctors are unprepared to make appropriate choices regarding imaging. In response to COVID-19-engendered restrictions, we created a fully online, image-intensive radiology curriculum to introduce students to clinical radiology and appropriate imaging usage. MATERIALS AND METHODS: A 2-week radiology elective curriculum was created that adopted accessible, free, online-based learning to foster student education and patient safety while upholding academic standards. Each unit included an emphasis on imaging appropriateness. Students assembled an elective portfolio including self-assessments and prepared a clinical radiology conference to present as a radiologist in training. Two final assessments were required. One consisted of clinical vignettes based on American College of Radiology (ACR) Appropriateness Criteria (AC). The second was an MRI safety quiz. RESULTS: Third and fourth year students at five institutions (N = 97) completed the elective. Examination scores on an assessment adapted from the ACR AC were significantly improved compared to previously published scores of medical students who took ACR AC-based assessments without taking a radiology course. The course was published and shared with medical schools worldwide. CONCLUSION: The elective successfully educated students in radiology through a virtual platform and introduced them to the concept of appropriateness in medical imaging. These goals were accomplished using a free, online, easily accessible curriculum. Incorporation of additional topics within the discipline of radiology should be included in the curriculum in the future.

Use of Artificial Intelligence in Radiology: Impact on Pediatric Patients, a White Paper From the ACR Pediatric AI Workgroup.

In this white paper, the ACR Pediatric AI Workgroup of the Commission on Informatics educates the radiology community about the health equity issue of the lack of pediatric artificial intelligence (AI), improves the understanding of relevant pediatric AI issues, and offers solutions to address the inadequacies in pediatric AI development. In short, the design, training, validation, and safe implementation of AI in children require careful and specific approaches that can be distinct from those used for adults. On the eve of widespread use of AI in imaging practice, the group invites the radiology community to align and join Image IntelliGently (www.imageintelligently.org) to ensure that the use of AI is safe, reliable, and effective for children.