Germaine Colton, Richards Allyson, Tocchio Shannon, Welch Kathryn, Ku Elliot, Martinez Sam
Final Pr. ID: Poster #: EDU-057
The incidence of cervical spine injuries is much less common in pediatric patients compared to their adult counterparts; however, these injuries result in more severe morbidity and mortality in the pediatric population, with increased rates of permanent neurological damage and death not uncommon. Understanding the physiology and anatomy as well as the clinical presentation of different pathologies is an essential skill when evaluating cervical spine injuries. Imaging the pediatric population presents challenges with variant anatomy and unique injury presentations on imaging. Here, we establish a search pattern for cervical spine imaging and review common pitfalls radiologists will encounter when reviewing cervical spine imaging in the setting of trauma.
CONTENT ORGANIZATION:
1) Epidemiology of pediatric cervical spine injuries.
2) Overview of the pediatric cervical spine with focus on developmental anatomy, common variants and physiologic considerations.
3) Review of search pattern considerations for cervical spine imaging.
4) Imaging examples of traumatic cervical spine injuries with illustration of critical findings and avoidable pitfalls.
5) Brief review of the role of the radiologist when reviewing cervical spine injuries.
SUMMARY:
This exhibit will provide education on important anatomy, imaging findings and pitfalls to avoid when reviewing cervical spine trauma imaging in pediatric patients. Teaching points will include:
1) Normal versus variant anatomy of the cervical spine.
2) Vital anatomical locations to review in the setting of cervical spine injury.
3) Detection of imaging features significant for cervical spine injuries using a wide variety of unique cases.
4) Effectively identifying and reporting the type and extent of the injury.
Read More
Authors: Germaine Colton , Richards Allyson , Tocchio Shannon , Welch Kathryn , Ku Elliot , Martinez Sam
Keywords: Cervical Spine Injury, Anatomy, Pitfalls
Meister Moshe, Kim Jane, Son Jennifer
Final Pr. ID: Poster #: EDU-019
Ultrasonography (US) is an essential tool in pediatric imaging, particularly in the emergency setting. Although US is often the favored initial modality for abdominal imaging in children, it is a highly operator-dependent modality prone to misinterpretation which can lead to false positive or negative exams, or even a different, incorrect diagnosis. Conditions discussed in this series include ileocolic intussusception, hypertrophic pyloric stenosis, appendicitis, and foreign bodies. We will review diagnostic criteria, highlight crucial findings, as well as illustrate commonly-encountered difficulties and mimics. Read More
Authors: Meister Moshe , Kim Jane , Son Jennifer
Keywords: ultrasound, mimic, pitfall
Wu Markus, Sharma Priya, Rajderkar Dhanashree
Final Pr. ID: Poster #: EDU-036
In this education exhibit we will review a variety of presentations of posttransplant lymphoproliferative disorder (PTLD) and review the approach to imaging these patients. We will include cases that are atypical and discuss the pitfalls in imaging this population. We will provide imaging guidelines after a review of the current literature. Read More
Authors: Wu Markus , Sharma Priya , Rajderkar Dhanashree
Keywords: PTLD, Transplantation, Pitfalls
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