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.

Hands-On Ultrasound Training for Radiology Residents: The Impact of an Ultrasound Scanning Curriculum.

RATIONALE AND OBJECTIVES: Radiologists are responsible for interpreting ultrasound (US) images accurately, troubleshooting, aiding sonographers, and advancing technology and research. Despite this, most radiology residents do not feel confident performing US independently. The purpose of this study is to evaluate the impact of an abdominal US scanning rotation and digital curriculum on radiology residents' confidence and skills in performing US. MATERIALS AND METHODS: All residents who were rotating in pediatric US at our institution for the first time were included (PGY 3-5). Those who agreed to participate were recruited sequentially from July 2018 to 2021 into (A) control and (B) intervention. B had a 1-week US scanning rotation and US digital course. Both groups completed a pre-and post-confidence self-assessment. Pre-and post-skills were objectively assessed by an expert technologist while participants scanned a volunteer. At completion, B completed an evaluation of the tutorial. Descriptive statistics summarized the demographics and closed questions. Pre-and post-test results were compared using paired-T tests, and effect size (ES) with Cohen's d. Open-ended questions were thematically analyzed. RESULTS: PGY-3 and 4 residents participated, and were enrolled in A (N = 39) and B (N = 30). Scanning confidence significantly improved in both groups, with a greater ES in B (p < 0.01). Scanning skills significantly improved in B (p < 0.01) but not A. Eighty per cent of questionnaire responders used the integrative US tutorial and found it helpful. Free text responses were grouped into themes: 1) Technical issues, 2) Didn't complete course, 3) Didn't understand project, 4) Course was detailed and thorough. CONCLUSIONS: Our scanning curriculum improved residents' confidence and skills in pediatric US and may encourage consistency in training, thus promoting stewardship of high-quality US.

Structured coaching as a means to improve sonographic visualization of the appendix: a quality improvement initiative.

PURPOSE: Ultrasound of the right lower quadrant for appendicitis requires specific training and practice. Improved visualization of the appendix can result in decreased utilization of computed tomography. Increasing the sensitivity of ultrasound for appendicitis thus decreases radiation exposure, reduces cost, and improves the patient healthcare experience in accordance with the three principles of the triple aim designated by the Institute for Healthcare Improvement. The purpose of this study was to examine the effect of a structured training program supplemented by technologist feedback on sonographic visualization of the appendix in a large pediatric health system. METHODS: The baseline ultrasound visualization frequency was computed for 20 ultrasound technologists in a large pediatric health system. Following this, technologists were informed of their individual and relative performance. Those with visualization frequencies less than 75% were provided structured training by a designated sonographer with an appendix visualization frequency above 75% while those with greater than 75% visualization continued to be monitored and informed of their monthly frequency. Following this structured training, appendix visualization frequencies were monitored over the next 5 months. RESULTS: There was no significant effect of sonographer career experience on the baseline appendix visualization frequency. Fourteen of 20 technologists demonstrated improved visualization frequencies post-intervention. The composite visualization frequency among these 20 technologists improved from 66.55 to 69.14%. This resulted in a potential savings of 38 CT scans during the post-intervention period. CONCLUSION: An appendix visualization rate monitoring program coupled with structured training was successful in improving the appendix visualization rate throughout a large pediatric health system. This program demonstrates the positive effect that monitoring and targeted intervention can have on a quality improvement program. The program continues to be carried out as part of a plan-study-do-act cycle.

Single shot lymphoscintigraphy in breast cancer: Effective single tracer sentinel node detection protocol with reduction in procedural pain.

PURPOSE: Variation in protocols for axillary sentinel lymph node (SLN) mapping exists. We strive to evaluate the effectiveness of reduction in number of injections on reducing procedural pain, while maintaining nodal detection. METHODS: Over 7 years, the number of periareolar injections performed was reduced stepwise from 4 to 1. This was analyzed for SLN detection and patients' subjective perceived pain. RESULTS: 828 patients with invasive breast cancer who underwent SLN mapping were included. Laterality of breast injection site included 326 (39.4%) in the right breast, 354 (42.8%) in the left breast and 148 (17.9%) in bilateral breasts. In patients who had 4 injection sites in a unilateral breast (n = 143), the reported pain score was 4.3 ± 2.4. Patients with 3 injections (n = 163), 2 injections (n = 163) and 1 injection (n = 211) in a breast reported pain scores of 3.4 ± 2.4, 3.2 ± 2.2, and 2.9 ± 2.6, respectively. In patients who had bilateral sentinel node procedures, those with 4 injections in each breast for a total of 8 injections (n = 37) reported a pain score of 5.7 ± 2.4. Patients with 3 (n = 51), 2 (n = 31) and 1 (n = 39) injection(s) in each breast reported perceived pain of 4.8 ± 2.8, 3.7 ± 2.7 and 3.5 ± 1.9, respectively. Incremental decreased pain scores were achieved with decreasing number of injections (p < 0.001). Nodal detection was maintained. CONCLUSION: A single periareolar subdermal injection site reduces periprocedural pain while maintaining nodal detection.

Elevating Radiology Education Research Through a Dedicated Research Fellowship: Adding Professional Identity as Essential for Success.

RATIONALE AND OBJECTIVES: Education research has been undervalued in radiology, with few radiology journals having dedicated space for such research and barriers to production including dedicated time, resources, grant funding, and mentorship. As radiologists, we have an opportunity to study education in our unique learning environments and create more effective ways to teach that are grounded in established education theory, solid assessment methodologies, and a focus on merit as well as worth. MATERIALS AND METHODS: The growth of education research in our field requires a two-pronged approach; We must cultivate leaders in education research from within our specialty, and continue to submit high quality work to radiology journals to increase exposure of the reviewers and readership to education methodologies. RESULTS: We have created the first radiology education research fellowship to this end. This manuscript details the fellowship creation process, the first education research fellow experience, and in-depth analysis of the inaugural year via a qualitative program review. CONCLUSION: We were successful in supporting an inaugural fellow in attaining the knowledge and skills to become a productive education researcher. Beyond this, the fellowship experience was a catalyst in developing her unique professional identity as an education master which will further raise the status of education research in pediatric radiology.

Contrast-enhanced ultrasound of the pediatric bowel.

Contrast-enhanced ultrasound (CEUS) has emerged as a valuable modality for bowel imaging in adults and children. CEUS enables visualization of the perfusion of the bowel wall and of the associated mesentery in healthy and disease states. In addition, CEUS images can be used to make quantitative measurements of contrast kinetics, allowing for objective assessment of bowel wall enhancement. Bowel CEUS is commonly applied to evaluate inflammatory bowel disease and to monitor treatment response. It has also been applied to evaluate necrotizing enterocolitis, intussusception, appendicitis and epiploic appendagitis, although experience with these applications is more limited. In this review article, we present the current experience using CEUS to evaluate the pediatric bowel with emphasis on inflammatory bowel disease, extrapolating the established experience from adult studies. We also discuss emerging applications of CEUS as an adjunct or problem-solving tool for evaluating bowel perfusion.

RADIAL: leveraging a learning management system to support radiology education.

Increasing volume and complexity of cases in academic radiology and the drive toward pediatric sub-specialization have threatened knowledge assimilation for radiologists. There is a clear need for a system that retrieves vetted information from the excess available on the internet. Partnered with an interdisciplinary team from the Graduate School of Education, the authors created the first comprehensive learning management system (LMS) for radiology, implemented in the reading room to augment image interpretation and point-of-care education. The LMS supports quantitative analysis using a robust analytics platform to evaluate user statistics, facilitating improved quality of patient care by revolutionizing the way radiologists assimilate knowledge. This integration promises to enhance workflow and point-of-care teaching and to support the highest quality of care.

Pediatric magnetic resonance imaging training versus job-readiness: using education research tools to re-align.

BACKGROUND: Fellows begin MRI training with variable experience and expertise. To better serve patients, pediatric radiology fellows should gain competence in MRI that enables seamless transition to independent practice. OBJECTIVE: We implemented a needs assessment survey and conducted a focus group discussion to identify knowledge gaps and inform creation of a curriculum for pediatric body MRI. MATERIALS AND METHODS: We electronically distributed a comprehensive anonymous needs assessment survey in October 2016 to current fellows and recent (<5 years) graduates from Accreditation Council for Graduate Medical Education (ACGME)-accredited pediatric radiology fellowships, with follow-up in January 2017. We conducted a focus group discussion among current fellows at our institution in October 2017 to inform a better understanding of the results. RESULTS: Eighty-one pediatric radiologists (8 fellows/73 attendings) completed the survey (24%); 5 current fellows participated in the focus group. The technical issues most commonly identified with limited or no instruction during training included setting up an MR service, accessory equipment (coil) selection and MRI field inhomogeneity correction. Areas needing increased attention and inclusion within the curriculum included coil choice/patient positioning (n=42, 52%), contrast agents (n=40, 49%), field strength (n=33, 41%) and strategies for motion correction (n=33, 41%). Most fellows were uncomfortable with setting up an MR service (n=57, 70%), correcting field inhomogeneity (n=56, 69%) and improving image quality (n=50, 62%). The focus group showed consensus that there was insufficient MR training in residency to prepare them for fellowship. The group also preferred shorter lectures and streaming via video education/tutorials. CONCLUSION: While traditional instruction emphasizes image interpretation, trainees in pediatric radiology need a curriculum that also emphasizes technical and non-interpretive aspects of MRI.

Job-Readiness After Pediatric Neuroradiology Training: Defining Trainee Needs.

RATIONALE AND OBJECTIVES: To describe and analyze the pediatric neuroradiology implicit curriculum for general-pediatric and neuro-pediatric radiology fellowship training in order to define specific trainee needs and inform an explicit pediatric neuroradiology curriculum. MATERIALS AND METHODS: A focus group of pediatric radiologists, pediatric neuroradiologists and fellows was conducted to create a needs assessment questionnaire that focused on training experience, current job, and a list of essential competency items. The questionnaire was distributed to 175 members of the Society for Pediatric Radiology. Data were derived from categorical and continuous survey variables. Using an inductive approach, we analyzed and systematically inspected the data to derive themes regarding trainee needs and how they might inform an explicit curriculum. RESULTS: Fifty-seven pediatric radiologists (response rate of 33%) responded to the survey. Sixty-three percent of respondents were fellowship trained in general pediatric radiology, 21% in pediatric neuroradiology, and 16% in both. In their current jobs, 75% of respondents were responsible for interpreting some pediatric neuroradiology. 50% or greater reported limited or no fellowship instruction in five areas of imaging interpretation: fetal neuroimaging; ear and/or nose and/or throat imaging; head and neck imaging; neuroembryology; neuro-spectroscopy and four areas of technical skills and/or image quality: reducing imaging time; choice of contrast agents; sedation; understanding clinical management pathways. CONCLUSION: Trainees endorse inadequate training in certain aspects of imaging interpretation and technical skills which are known to remain a significant and vital aspect of pediatric neuroradiology practice, revealing an opportunity to emphasize these aspects in an explicit curriculum and dedicate educational resources towards this cause.

Brief communication: A radiology resident's experience with COVID-19 in New York City.

The COVID-19 pandemic impacted New York City severely. As a radiology resident, I was unsure how my role would change as the pandemic unfolded. Like many hospital systems in New York City, my department was asked to assist in the clinical care of patients during the dramatic surge of admissions related to COVID-19. I placed invasive central lines for critically ill patients in the intensive care unit to help reduce the workload on already overwhelmed critical care teams. I also performed direct patient care within dedicated COVID-19 inpatient floors.

Contrast-enhanced US in Pediatric Patients: Overview of Bowel Applications.

Contrast material-enhanced US is a technique that is approved by the U.S. Food and Drug Administration for the characterization of liver lesions and intravesicular applications in children; however, contrast-enhanced US has several other pediatric applications in clinical practice. The most common application is for patients with inflammatory bowel disease (IBD). Contrast-enhanced US can be used to diagnose IBD, distinguish regions of active or chronic inflammation of the bowel wall, and evaluate associated complications such as abscesses, fistulas, and strictures. Dynamic contrast material evaluation provides qualitative and quantitative information about mural and mesenteric blood flow, which is essential in the determination of disease activity in these patients. It also has the potential to provide a means of monitoring the response to therapy beyond endoscopy or MR enterography. In addition to its use for IBD, contrast-enhanced US can be used to assess for bowel perfusion when problem solving in patients with necrotizing enterocolitis, neonatal bowel infarction, or intussusception. It is a useful imaging technique to fortify diagnoses that may otherwise be indeterminate, such as appendicitis, epiploic appendagitis, intraluminal bowel masses, and complex cysts. Finally, innovative applications such as shear-wave elastography have the potential to provide information about the stiffness of the bowel wall. Online supplemental material is available for this article. ©RSNA, 2020 See discussion on this article by Watson and Humphries.

Improved Diagnostic Sensitivity of Bowel Disease of Prematurity on Contrast-Enhanced Ultrasound.

Bowel diseases of prematurity, including necrotizing enterocolitis, are dreaded ailments of neonates. Early diagnosis is difficult, with clinical and radiographic findings often inconclusive. We present a novel use of contrast-enhanced ultrasound in detection of pediatric bowel disease. Early identification of compromised blood flow or an at-risk bowel can be quantitatively detected and monitored. This ability has implications for guidance of emerging therapies, allowing targeting of inflammation. These findings represent an advancement in detection of bowel disease in neonates.

Does obtaining an initial magnetic resonance imaging decrease the reamputation rates in the diabetic foot?

OBJECTIVE: Diabetes mellitus (DM) through its over glycosylation of neurovascular structures and resultant peripheral neuropathy continues to be the major risk factor for pedal amputation. Repetitive trauma to the insensate foot results in diabetic foot ulcers, which are at high risk to develop osteomyelitis. Many patients who present with diabetic foot complications will undergo one or more pedal amputations during the course of their disease. The purpose of this study was to determine if obtaining an initial magnetic resonance imaging (MRI), prior to the first amputation, is associated with a decreased rate of reamputation in the diabetic foot. Our hypothesis was that the rate of reamputation may be associated with underutilization of obtaining an initial MRI, useful in presurgical planning. This study was designed to determine whether there was an association between the reamputation rate in diabetic patients and utilization of MRI in the presurgical planning and prior to initial forefoot amputations. METHODS: Following approval by our institutional review board, our study design consisted of a retrospective cohort analysis of 413 patients at Staten Island University Hospital, a 700-bed tertiary referral center between 2008 and 2013 who underwent an initial great toe (hallux) amputation. Of the 413 patients with a hallux amputation, there were 368 eligible patients who had a history of DM with documented hemoglobin A1c (HbA1c) within 3 months of the initial first ray (hallux and first metatarsal) amputation and available radiographic data. Statistical analysis compared the incidence rates of reamputation between patients who underwent initial MRI and those who did not obtain an initial MRI prior to their first amputation. The reamputation rate was compared after adjustment for age, gender, ethnicity, HbA1c, cardiovascular disease, hypoalbuminemia, smoking, body mass index, and prior antibiotic treatment. RESULTS: The results of our statistical analysis failed to reveal a significant association between obtaining an initial MRI and the reamputation rate. We did, however, find a statistical association between obtaining an early MRI and decreased mortality rates. DISCUSSION: Obtaining an early MRI was not associated with the reamputation rate incidence in the treatment of the diabetic foot. It did, however, have a statistically significant association with the mortality rate as demonstrated by the increased survival rate in patients undergoing MRI prior to initial amputation.