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

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

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

Otjen Jeffrey,  Stanescu A. Luana,  Ansdell David,  Alessio Adam,  Parisi Marguerite

Final Pr. ID: Poster #: SCI-023

Pelvic ultrasound is commonly used to detect ovarian torsion, but the diagnosis remains challenging as there is no single pathognomonic feature. This retrospective case-controlled study aims to identify an algorithm to detect torsion based on common ultrasound imaging features. Read More

Authors:  Otjen Jeffrey , Stanescu A. Luana , Ansdell David , Alessio Adam , Parisi Marguerite

Keywords:  torsion, ultrasound, machine learning

Randhawa Hari,  Park Brandon,  Khanna Praneet,  Jung Daniel,  Das Ayushman,  Ginn Kevin,  Mitchell Grace

Final Pr. ID: Poster #: EDU-003

MRI is crucial to the diagnosis, treatment planning, and monitoring of pediatric posterior fossa tumors; recent advances in machine and deep learning offer the prospect of increased diagnostic accuracy and minimally invasive management strategies. Machine learning and deep learning represent two artificial intelligence (AI) applications of radiomics that show promising results in the identification and classification of pediatric posterior fossa tumors, such as medulloblastoma, diffuse intrinsic pontine glioma, ependymoma, and pilocytic astrocytoma, based on MRI data. Many AI models demonstrate comparable, or in some cases, better, performance than human radiologists. Beyond diagnosis, machine and deep learning algorithms have been developed for tumor histology determination, prognostication, and molecular subtyping, to name just a few examples. In its early stages, however, the technology has several barriers to overcome before mainstream use. Studies of AI algorithms are often conducted with small sample sizes due to the relative rarity of pediatric posterior fossa tumors; many are also conducted at a single institution. Algorithms are susceptible to class imbalance as well, making it more difficult to identify tumors with lower prevalence. Multi-institution studies are important in addressing those limitations, though they have their own cumbersome requirements, such as data harmonization. Deep learning training strategies, such as federated learning, data augmentation, and transfer learning, help to address the problems introduced by working with small data sets. The purpose of this exhibit is to review the methods, results, and limitations identified in studies testing the efficacy of machine and deep learning models for the identification and classification of pediatric posterior fossa tumors and to discuss their potential for use in the clinical setting. Read More

Authors:  Randhawa Hari , Park Brandon , Khanna Praneet , Jung Daniel , Das Ayushman , Ginn Kevin , Mitchell Grace

Keywords:  Artificial Intelligence, Deep Learning, Machine Learning

Satoor Vamsish,  Marine Megan

Final Pr. ID: Poster #: SCI-034

Background/Objective:
Rib fractures are one of the most specific fractures in child abuse and are among the most common identified. Diagnosis of an unsuspected rib fracture in a young child or infant is highly concerning for child abuse. Given rib fractures, particularly acute rib fractures, can be subtle and difficult for even experienced radiologists to identify, a screening diagnostic tool to improve the detection accuracy would provide significant value. The objective of this investigation is to create a machine learning algorithm with the ability to recognize the presence or absence of rib fractures on chest radiographs in pediatric patients less than 3 years old. Read More

Authors:  Satoor Vamsish , Marine Megan

Keywords:  Machine learning, Chest x-ray, Pediatric

Rafful Patricia,  Khalkhali Vahid,  Alkhulaifat Dana,  Welsh Michael,  Wieczkowski Sydney,  Sotardi Susan

Final Pr. ID: Poster #: EDU-002

Pediatric radiologists are self-taught and independently interpret artificial intelligence manuscripts. However, they might not identify the pitfalls and biases related to complex data from pediatric models.
Pediatric imaging differs from adult imaging in several instances such as sample size, growth-related disorders, disease presentation, quality standards, image distortions and motioning, radiation safety adjustment, and other challenges that can impact the development of algorithms and models. The specific metrics to measure the performance of the model must be in accordance with the data and clinical task, as it can vary within the prevalence of the disease and with the balance of the dataset, and therefore can mislead the model performance results.
Challenges related to the model development can arise from data management, data transformation, small datasets, imbalanced datasets, optimization, and type of validation.
All those pieces of information are as important as the medical aspect, however, in artificial intelligence, manuscripts will explore computational engineering and data science more than clinical knowledge. The understanding of the learning architecture, classifiers, parameter, and algorithms will allow the reader to translate engineering details into clinical meaning.
In this work, we will present pitfalls and biases during data curation, hyperparameters, weights, validation, and classification metrics; and discuss the best practices to mitigate those challenges. This work integrates our group experience with a thorough literature review of prior artificial intelligence manuscripts in pediatric radiology for the analysis and application of artificial intelligence to clinical practice.
Our goal is to improve critical thinking when interpreting scientific research in artificial intelligence for pediatric radiologists. Read More

Authors:  Rafful Patricia , Khalkhali Vahid , Alkhulaifat Dana , Welsh Michael , Wieczkowski Sydney , Sotardi Susan

Keywords:  Pitfalls, Machine Learning, Best Practices

Holroyd Alexandria,  Bai Harrison,  Liu Shixin,  Xiao Yanhe,  Liu Yalin,  Wu Jing,  States Lisa

Final Pr. ID: Paper #: 156

Neuroblastoma is a clinically heterogeneous pediatric malignancy, varying in location, histopathologic appearance, and biologic characteristics. Genetics plays an important role in the prognosis. Amplification of the MYC family member, MYCN, is found in 25% of cases and correlates with high-risk disease and poor prognosis. However, genetic information can only be obtained via surgery or biopsy with concurrent morbidity and sampling variability associated with biopsy. The ability to detect MYCN amplification from routine pre-operative imaging can stratify neuroblastoma risk groups and affect clinical decision making. The purpose of this study was to predict the patient's MYCN status based on radiomics analysis of the magnetic resonance imaging (MRI) characteristics in patients with neuroblastoma. Read More

Authors:  Holroyd Alexandria , Bai Harrison , Liu Shixin , Xiao Yanhe , Liu Yalin , Wu Jing , States Lisa

Keywords:  Machine learning, Radiomics, Neuroblastoma