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

Three-dimensional (3D) imaging has emerged as a valuable tool in diagnosing pediatric Müllerian duct anomalies (MDAs), offering superior anatomical visualization and assessment compared to traditional imaging techniques with two-dimensional ultrasound. MDAs are frequently associated with other congenital anomalies of the cervix, vagina, or urinary tract, and are a common cause of infertility and pregnancy loss after adolescence. In pediatric patients, MDAs are often discovered incidentally during imaging for other conditions. Magnetic resonance imaging (MRI) is the preferred modality for evaluating MDAs in children, providing multiplanar capabilities and detailed soft tissue characterization while avoiding ionizing radiation. MRI protocols for MDAs typically include T2-weighted sequences for visualizing uterine morphology and T1-weighted sequences to detect blood products in cases of associated endometriosis or hematometra . The use of 3D MRI techniques allows for enhanced depiction of uterine and vaginal anatomy, and is particularly advantageous in differentiating complex anomalies such as septate and bicornuate uteri. Additionally, 3D reconstructions can provide a virtual hysterosalpingogram (MR-HSG), offering a comprehensive assessment of the reproductive tract without the need for invasive procedures. 3D imaging's accuracy extends to the detection of associated renal anomalies, given the concurrent development of the urinary and reproductive systems. Identifying these anomalies early is crucial for planning surgical interventions that may involve both gynecologic and urologic components . Overall, 3D imaging significantly enhances the diagnostic accuracy and management of pediatric Müllerian duct anomalies. By providing detailed anatomical insights and allowing for non-invasive classification, it plays a critical role in guiding treatment strategies, reducing the need for repeat surgeries, and improving long-term reproductive outcomes for affected patients. The purpose of this educational exhibit is to: 1. Review the embryology, classification, and imaging features of Müllerian duct anomalies using 3-dimensional imaging 2. Review the indications and techniques for surgical management of Müllerian duct anomalies in pediatric patients 3. Provide sample cases and clinical courses of patients with specific Müllerian duct anomalies with tips for implementation of 3-D imaging 4. Allow learners to test their knowledge with a quiz. Read More

Meeting name: SPR 2025 Annual Meeting , 2025

Authors: Cheng Jocelyn, Leesmidt Kantheera, Liu Amanda, Young Victoria, Davda Sunit, Berger-chen Sloane, Courtier Jesse

Keywords: MRI, Mullerian Duct Anomalies, 3D Imaging