Zhu Xiaowei,  Silvestro Elizabeth,  Andronikou Savvas

Final Pr. ID: Paper #: 019

Dynamic 4D CT (D4DCT) can replace bronchography in the assessment of tracheobronchomalacia (TBM) but setting up a new D4DCT service for infants with TBM poses unique challenges due to their venerability. Simulation prior to implementation is essential as D4DCT involves continuous volumetric CT scanning through the breathing cycle, potentially delivering high radiation doses. Radiation dose, gantry rotation and scan dynamics can be customized.
Our purpose is to describe the development and implementation of CT dynamic airway protocol using a 3D printed Infant Dynamic Airway Phantom (phantom) for simulation of D4DCT in tachnypnoea and collapsible airways, thereby validating image quality and estimating radiation dose prior to clinical implementation. Read More

Authors:  Zhu Xiaowei,  Silvestro Elizabeth,  Andronikou Savvas

Keywords:  dynamic airway ,  infant ,  D4DCT

Kim Kevin,  Nowrangi Rajeev,  Mcgehee Arianna,  Joshi Neil,  Acharya Patricia

Final Pr. ID: Paper #: 020

To assess whether a convolutional neural network (CNN) can be trained via transfer learning to accurately diagnose germinal matrix hemorrhage-intraventricular hemorrhage (GMH-IVH) on cranial ultrasound (CUS) by comparing its performance to that of a board-certified radiologist. Secondary endpoints will include the ability of CNN to grade GMH-IVH severity, identify GMH-IVH on MRI, and assess low-grade GMH-IVH on CUS that cannot reliably be seen by a radiologist. Read More

Authors:  Kim Kevin,  Nowrangi Rajeev,  Mcgehee Arianna,  Joshi Neil,  Acharya Patricia

Keywords:  AI ,  Cranial ultrasound ,  germinal matrix hemorrhage

Xue Christine,  Nowrangi Rajeev,  Smith John,  Acharya Patricia

Final Pr. ID: Paper #: 021

To assess whether a convolutional neural network (CNN) can be trained via transfer learning to accurately diagnose metaphyseal corner fractures on long bone radiographs by comparing its performance to that of a board-certified pediatric radiologist. Secondary endpoints will include the ability of the CNN to detect the type of long bone presented on the radiograph as well as identify the chronicity of the fracture. Read More

Authors:  Xue Christine,  Nowrangi Rajeev,  Smith John,  Acharya Patricia

Keywords:  AI ,  Nonaccidental Trauma ,  metaphyseal corner fractures

Zapala Matthew,  Li Yi,  Belisario Jennifer,  Phelps Andrew,  Courtier Jesse,  Vlasses Christopher

Final Pr. ID: Paper #: 022

Virtual reality (VR) has been used successfully as a psychological preparation tool in the pediatric patient population for elective surgery, oncological procedures and pain management. MRI exams require patients to remain motionless in a small, confined space for extended periods of time creating nervousness and an inability to hold still. VR offers a new way to prepare pediatric patients for MRI through simulations to reduce nervousness and decrease motion, resulting in more successful imaging outcomes. This study is designed to assess if VR simulations of an MRI exam can increase anticipatory knowledge and reduce nervousness in a pediatric cohort. Read More

Authors:  Zapala Matthew,  Li Yi,  Belisario Jennifer,  Phelps Andrew,  Courtier Jesse,  Vlasses Christopher

Keywords:  Virtual Reality ,  MRI ,  Child Life

Asmar Julia,  Singhal Hannah,  Lypka Michael,  Chan Sherwin

Final Pr. ID: Paper #: 023

Many studies have shown that patient education with interactive, multimedia design can enhance information retention. Merge Cube is a commercially available interactive object that allows one to use a phone or iPad to display and manipulate 3D images via an app. The purpose of this study is to determine if reviewing personalized 3D computerized tomography (CT) images via Merge Cube improves patients’ education and understanding versus reviewing the images on a monitor. Read More

Authors:  Asmar Julia,  Singhal Hannah,  Lypka Michael,  Chan Sherwin

Keywords:  3D Visualization ,  Maxillofacial ,  Patient Outcomes

Meda Karthik,  Milla Sarah,  Rostad Bradley

Final Pr. ID: Paper #: 024

Machine learning that can identify and localize objects in an image using a labeled bounding box is called object detection. The purpose of this study is to demonstrate object detection in identifying rickets on pediatric wrist radiographs. Read More

Authors:  Meda Karthik,  Milla Sarah,  Rostad Bradley

Keywords:  Machine learning ,  Artificial intelligence ,  rickets

Rostad Bradley,  Richer Edward,  Riedesel Erica,  Alazraki Adina

Final Pr. ID: Paper #: 025

Timely diagnosis of foreign body ingestion in children is important, particularly in the case of an ingested button battery. A button battery which lodges in the esophagus can quickly cause severe esophageal and mediastinal injury. It is also important to distinguish an ingested button battery from a coin; a button battery may be misdiagnosed a coin because of its similar radiographic appearance. The purpose of this study is to develop a machine learning model to identify button batteries and coins on pediatric foreign body series radiographs. Read More

Authors:  Rostad Bradley,  Richer Edward,  Riedesel Erica,  Alazraki Adina

Keywords:  Machine learning ,  Artificial intelligence ,  Button battery

Rostad Bradley,  Richer Edward,  Riedesel Erica,  Alazraki Adina

Final Pr. ID: Paper #: 026

Foreign body ingestion is common in children. Timely diagnosis of the nature and location of the foreign body is important. A button battery which lodges in the esophagus can quickly cause severe esophageal and mediastinal injury. Machine learning that can detect anatomical regions of interest is an important step in computerized foreign body localization and may result in prioritization of radiographs with mediastinal foreign bodies. The purpose of this study is to develop a machine learning model to identify anatomical regions of interest on pediatric foreign body series radiographs. Read More

Authors:  Rostad Bradley,  Richer Edward,  Riedesel Erica,  Alazraki Adina

Keywords:  Machine learning ,  Artificial intelligence ,  Foreign body

Tung Eric,  Ayyala Rama,  Sams Cassandra,  Swenson David

Final Pr. ID: Paper #: 027

In an effort to improve communication of important radiology findings, we designed and deployed a unique comprehensive radiology report categorization (RADCAT) system that organizes results by acuity and need for radiology follow-up. The goal of our study is to outline and compare the distribution of RADCAT pediatric imaging reports from three different clinical settings. Read More

Authors:  Tung Eric,  Ayyala Rama,  Sams Cassandra,  Swenson David

Keywords:  Quality ,  Reporting ,  Grading

Annapragada Akshaya,  Donaruma-kwoh Marcella,  Annapragada Ananth,  Starosolski Zbigniew

Final Pr. ID: Paper #: 028

Child abuse is the principal cause of traumatic injury and death in children 0-36 months old. Radiologic findings are a critically important piece of evidence necessary for assessment by a Child Protection Team to assess possible abuse. Current algorithmic strategies for the detection of abuse are sensitive, but compromise specificity. The purpose of this study was to determine the performance of deep learning to diagnose child abuse using Natural Language Processing of the unstructured free-text from Electronic Health Records (EHR), including essential information from Radiology Reports. Read More

Authors:  Annapragada Akshaya,  Donaruma-kwoh Marcella,  Annapragada Ananth,  Starosolski Zbigniew

Keywords:  Child Abuse ,  decision support ,  Convolutional Neural Network