MRI is not routinely used in clinical practice for lung imaging because of the low proton density and respiratory motion artifact. However, the ultrashort echo time (UTE) MRI technique can increase the signal in the lung. Image reconstruction techniques, such as iterative motion compensated (iMoCo) reconstruction, have improved respiratory motion management for free-breathing lung MRI scans. With the advantage of no ionizing radiation, MRI can benefit patients with immunodeficiency who often require repeat imaging, patients with heightened radiation sensitivity, and/or pediatric patients. In this abstract, we aim to evaluate the imaging quality of UTE lung MRI in the pediatric population. Read More

Meeting name: SPR 2023 Annual Meeting & Postgraduate Course , 2023

Authors: Tan Fei, Zapala Matthew, Durand Rachelle, Chan Marilynn, Larson Peder

Keywords: MRI, Image Quality, Lung

According to the current statistics, approximately 1 million children aged 6-14 participated in 11-payer football, more popular as youth football, in the 2021-2022 school year (3). A trend to earlier participation in specialized sports activities in pediatric patients has been observed. Contact sports such as basketball, football, and soccer comprise a considerable proportion of all played sports and are associated with the highest number of injuries, both acute and chronic in nature(9). Lower extremities are the most common site of injury in pediatric football players, followed by upper extremity. Fractures and sprains/strains are the most common injury patterns (1, 9, 10). With the increasing number of young football athletes, there is a greater need to explore football-associated injuries, which can have a considerable physical, emotional, and psychosocial impact on a young individual. This educational exhibit aims to explore the most common American football-related pediatric extremity injuries and their imaging characteristics using various modalities and briefly discuss the treatment options for the pediatric population. Read More

Meeting name: SPR 2024 Annual Meeting & Postgraduate Course , 2024

Authors: Manral Kalpana, Durand Rachelle, Pandya Nirav, Kornblith Aaron, Cort Kayla, Courtier Jesse

Keywords: American football, Pediatric, Extremity injuries

In recent years, the applications of artificial intelligence in radiology have increased exponentially. Randomized controlled trials demonstrating the potential of AI in radiology have been centered around deep learning techniques with artificial neural networks, such as convolutional neural networks (CNNs). Current applications of CNNs include the detection, segmentation and quantification of pathologic conditions. These tasks use deductive AI, which uses discriminative models to identify discrepancies between images. Generative AI is an emerging technique that has a number of exciting novel applications in the field of Pediatric Radiology. This exhibit will provide a practical overview to familiarize pediatric radiologists with this topic and review current and potential future use cases. Generative adversarial networks (GAN) require two opposing networks, a generator that synthesizes new images, and a discriminator that differentiates between real and synthesized images. Through an iterative process, GAN creates highly realistic images that have exciting applications in image creation, translation between imaging modalities, acceleration of image synthesis and identification of pathologic abnormalities. ChatGPT is a popular generative AI model that generates coherent responses to queries, and uses a Generative Pre-trained Transformer (GPT) network to encode and decode language data. ChatGPT is pre-trained on large volume text data to learn how language is used in different contexts. An encoder processes the input sequence and a decoder generates the output sequence. Both encoder and decoder have a multi-head self-attention mechanism allows differential weighing of the sequence to infer meaning and context. Potential applications in pediatric radiology are broad, including patient communication, providing appropriate imaging recommendations, report generation and review of radiologic safety guidelines and regulations. However, generative AI models require careful implementation, training and validation to reduce potential pitfalls in unintentionally synthesizing content that does not exist, or conversely, removing clinically relevant information from an image. The purpose of this exhibit is to: (1) provide an introduction to Generative AI (GAN) and ChatGPT (2) review use cases of GAN and ChatGPT in pediatric radiology (3) provide practical methods for evaluating the performance of artificial intelligence algorithms in pediatric radiology applications. Read More

Meeting name: SPR 2024 Annual Meeting & Postgraduate Course , 2024

Authors: Cheng Jocelyn, Leesmidt Kantheera, Durand Rachelle, Mongan John, Cort Kayla, Courtier Jesse

Keywords: Generative Artificial Intelligence, Artificial Intelligence, ChatGPT

MRI of the abdomen faces several technical challenges owing to respiratory motion, bowel peristalsis, and the need for large volumetric coverage. In adult patients, imaging is typically performed during multiple breath holds to avoid motion artifact; however pediatric patients may be unable to perform consistent breath holds or remain motionless during MRI acquisition. Although techniques such as child life specialists, MRI video goggles, and dedicated MR suite environments have reduced the need for anesthesia in MRI, general anesthesia may be necessary in some patients. Simulating breath holds in anesthetized patients is a technically difficult procedure requiring timed ventilation of the patient's abdomen during MRI acquisition, and results in progressive image degradation due to retained air artifact. Dynamic Scan Optimization (DISCO) combines 3D DCEMRI + 2 pt Dixon + Parallel Imaging + Temporal Acceleration to provide high spatiotemporal resolution while drastically reducing scan time. Because pediatric patients have relatively low respiratory volumes, this technique enables acquisition of diagnostic quality images without breath-holding. The purpose of this exhibit is to: (1) provide a guide for successful application of navigated spontaneous breathing multiphase DISCO sequence (2) review common use cases of the DISCO sequence (3) provide practical suggestions for troubleshooting DISCO Read More

Meeting name: SPR 2023 Annual Meeting & Postgraduate Course , 2023

Authors: Cheng Jocelyn, Durand Rachelle, Zapala Matthew, Cort Kayla, Bhuller Jeanie, Courtier Jesse

Keywords: Dynamic contrast enhanced MRI, DIfferential Sub-sampling with Cartesian Ordering, pediatric abdominal MRI

Cat-Scratch Disease (CSD) is an infectious disease that predominantly affects pediatric patients, usually ages 4-9 years old. The annual incidence is estimated at 4.5 patients per 100,000 population. CSD is primarily caused by B. henselae, an intracellular gram-negative bacillus; it is transmitted via scratch, lick, or bite from a cat. It presents with lymphadenopathy proximal to the site of inoculation; most commonly, this is axillary, epitrochlear, cervical, or inguinal lymphadenopathy. While CSD can be diagnosed clinically and has objective findings on histopathology, the imaging findings are unclear and have been debated in the literature. As such, we sought to clarify the multimodal imaging findings associated with CSD. We performed a review of the literature to highlight the existing radiological consensus. We also contribute several of our own new cases from our institution. Read More

Meeting name: SPR 2023 Annual Meeting & Postgraduate Course , 2023

Authors: Baig Farhan, Zapala Matthew, Kim Jane, Durand Rachelle, Cohen Pierre-alain, Wattier Rachel, Courtier Jesse

Keywords: Cat Scratch Disease, CSD, lymphadenopathy