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

Benitez Steven,  Levin Terry

Final Pr. ID: Poster #: EDU-063

With the expansion of the internet and the development of new media tools, learning methods among medical students and residents in all specialties particularly Radiology have changed. While didactic lectures and personal interaction with mentors each play an important part in education, self learning via a variety of internet sources has gained a significant role and has come to replace the use of standard textbooks. Existing online modules are minimally interactive and present radiographic images concurrently with text. In most, users use the cursor to hover over the image in order to display the abnormality. Read More

Authors:  Benitez Steven , Levin Terry

Keywords:  learning module, hips, pediatric

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

Wu Yujie,  Namdar Khashayar,  Chen Chaojun,  Hosseinpour Shahob,  Shroff Manohar,  Doria Andrea,  Khalvati Farzad

Final Pr. ID: Poster #: SCI-020

X-Ray based manual Cobb angle measurement is inherently time-consuming and associated with high inter- and intra-observer variability. The existing automated scoliosis measurement methods suffer from insufficient accuracy. We propose a two-step segmentation-based deep architecture to automate Cobb angle measurement for scoliosis assessment. Read More

Authors:  Wu Yujie , Namdar Khashayar , Chen Chaojun , Hosseinpour Shahob , Shroff Manohar , Doria Andrea , Khalvati Farzad

Keywords:  Scoliosis, Deep Learning, Cobb Angle

Castiglione James,  Gilligan Leah,  Somasundaram Elanchezhian,  Trout Andrew,  Brady Samuel

Final Pr. ID: Paper #: 059

In this study, we trained two convolutional neural networks to automatically identify the third vertebral level and segment the abdominal muscle in contrast enhanced abdominal CT images. In the future, these models will be used to determine reference ranges for skeletal muscle mass in children by age for the purpose of identifying patient characteristics associated with differences in skeletal muscle mass. Read More

Authors:  Castiglione James , Gilligan Leah , Somasundaram Elanchezhian , Trout Andrew , Brady Samuel

Keywords:  Neural Network, Segmentation, Deep Learning

Mahalingam Neeraja,  Bates Alister,  Higano Nara,  Gunatilaka Chamindu,  Woods Jason,  Somasundaram Elanchezhian

Final Pr. ID: Poster #: SCI-010

To develop an optimized AI model to automatically segment lung volumes from pulmonary magnetic resonance images (MRI) and generate tidal volume calculations for neonatal patients with chronic lung disease of prematurity (bronchopulmonary dysplasia, BPD). Read More

Authors:  Mahalingam Neeraja , Bates Alister , Higano Nara , Gunatilaka Chamindu , Woods Jason , Somasundaram Elanchezhian

Keywords:  Bronchopulmonary Dysplasia, MRI, Deep Learning

Chen Chaojun,  Namdar Khashayar,  Wu Yujie,  Hosseinpour Shahob,  Shroff Manohar,  Doria Andrea,  Khalvati Farzad

Final Pr. ID: Poster #: SCI-022

Scoliosis is a deformity of the spine that affects 2-3% of the population. Currently, the reference standard for assessing scoliosis is the manual assignment of Cobb angles at the site of the curvature center using X-ray images. This process is time consuming and unreliable as it is affected by inter- and intra-observer variability. To overcome these inaccuracies, machine learning (ML) methods can be used to automate the Cobb angle measurement process. Read More

Authors:  Chen Chaojun , Namdar Khashayar , Wu Yujie , Hosseinpour Shahob , Shroff Manohar , Doria Andrea , Khalvati Farzad

Keywords:  Scoliosis, Cobb Angle, Deep Learning

Cole Elizabeth,  Pauly John,  Vasanawala Shreyas,  Cheng Joseph

Final Pr. ID: Poster #: SCI-059

Convolutional neural networks (CNNs) have proven to be valuable in the fields of image processing and computer vision. Our work applies complex-valued CNNs to magnetic resonance imaging (MRI) to reduce scan times. The reduction of scan times has widespread pediatric benefits. A typical scan requires that patients remain still for up to an hour to produce a clear image, which is difficult for children without inducing anesthesia, which carries risks. A need exists for greatly improved MRI scan times without the loss of diagnostic accuracy. This scan time can be reduced by subsampling in k-space. We use CNNs to reconstruct images from these undersampled acquisitions. Our work investigates complex-valued CNNs for image reconstruction in lieu of two-channel real-valued CNNs. Read More

Authors:  Cole Elizabeth , Pauly John , Vasanawala Shreyas , Cheng Joseph

Keywords:  Magnetic Resonance Imaging, deep learning, Neural network

Reid Janet,  Gandhi Trupti,  Kazmi Parvez,  Anupindi Sudha,  Francavilla Michael,  States Lisa

Final Pr. ID: Poster #: EDU-137

Learning at point of care has become the norm. There is endless unfiltered radiology educational material available on the internet. Radiology trainees and educators need a filtered high quality engine available at point of care to enable efficient and effective learning and teaching.
Read More

Authors:  Reid Janet , Gandhi Trupti , Kazmi Parvez , Anupindi Sudha , Francavilla Michael , States Lisa

Keywords:  education, CMS, LMS, learning, point-of-care

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

Zucker Evan,  Sandino Christopher,  Kino Aya,  Lai Peng,  Vasanawala Shreyas

Final Pr. ID: Paper #: 014

To assess the image quality and clinical performance of a novel accelerated, free-breathing 2D cine cardiac MR sequence with DCNN reconstruction in comparison to conventional breath-held 2D cine balanced steady-state free precession (bSSFP). Read More

Authors:  Zucker Evan , Sandino Christopher , Kino Aya , Lai Peng , Vasanawala Shreyas

Keywords:  Cardiac, MRI, Deep 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

Sammer Marla,  Kan J.,  Donnelly Lane

Final Pr. ID: Paper #: 088

To evaluate the peer collaborative improvement (PCI) process used in our pediatric radiology department since January 2016, differences in sequential surveys and temporal change in types of submissions were assessed. Read More

Authors:  Sammer Marla , Kan J. , Donnelly Lane

Keywords:  Peer Learning, Survey

Mutasa Simukayi,  Liu Michael,  Duong Phuong,  Jambawalikar Sachin,  Mostoufi-moab Sogol,  Jaramillo Diego

Final Pr. ID: Paper #: 112

There is growing research in diffusion tensor imaging (DTI) for providing metrics and images of physeal structure and function, particularly in evaluating children with possible growth disorders. There is a need for a faster automated process to segment the diffusion data, however. We utilized a deep learning algorithm to automatically generate a region of interest (ROI) for use in fully automatic diffusion tensor tractography of cartilage columns in the distal femoral physis. Read More

Authors:  Mutasa Simukayi , Liu Michael , Duong Phuong , Jambawalikar Sachin , Mostoufi-moab Sogol , Jaramillo Diego

Keywords:  Deep learning, growth disorders, MRi

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

Alkhulaifat Dana,  Rafful Patricia,  Lopez Rippe Julian,  Khalkhali Vahid,  Welsh Michael,  Wieczkowski Sydney,  Reid Janet,  Sotardi Susan

Final Pr. ID: Poster #: EDU-043

In recent years, artificial intelligence (AI) applications for radiology have undergone exponential growth. AI has the potential to assist pediatric radiologists in several respects, including identification of various pathologies and prioritization of studies with urgent imaging findings. Although image analysis is an important application of AI, there are many additional use cases where AI can assist radiologists, including radiology operations and quality analysis. Therefore, it is critical that radiologists familiarize themselves with the wide range of AI methodologies and applications.
Although efforts have been made to create formal education for radiologists, currently available resources typically rely upon didactic lectures, without real-life context for the technology. However, case-based education is a principal component of radiology education. Furthermore, prior research has demonstrated that trainees and radiologists are interested in case-based approaches for learning AI [1].

Thus, the purpose of this educational exhibit is to provide an informative resource specifically for pediatric radiologists which utilizes a case-based learning approach. This resource uses 5 cases intended to demonstrate the variety of uses of AI in pediatric radiology, while illustrating the underlying process of AI model selection and development. Specifically, these cases will be selected to encompass AI topics including: image classification, lesion segmentation, natural language processing for imaging reports, recommender systems to enhance radiologist practice and predictive modeling for radiology operations research. This approach allows us to explore decision-points in AI model building, while examining potential pitfalls that may arise. This educational exhibit was developed based on a thorough literature review of prior AI research combined with our professional experience, and aims to provide educational resource intended to teach AI model selection and development to pediatric radiologists.

References
1. Velez-Florez MC, Ghosh A, Patton D, et al (2022) Artificial intelligence curriculum needs assessment for a pediatric radiology fellowship program: what, how, and why? Acad Radiol. https://doi.org/10.1016/j.acra.2022.04.026 Read More

Authors:  Alkhulaifat Dana , Rafful Patricia , Lopez Rippe Julian , Khalkhali Vahid , Welsh Michael , Wieczkowski Sydney , Reid Janet , Sotardi Susan

Keywords:  Artificial Intelligence, Case-Based Learning, Education

Somasundaram Elanchezhian,  Brady Samuel,  Crotty Eric,  Trout Andrew,  Anton Christopher,  Towbin Alexander,  Coley Brian,  Dillman Jonathan

Final Pr. ID: Paper #: 032

At our institution, airway radiographs are routinely checked by the radiologist to ensure diagnostic image quality prior to the technologist completing the examination. These checks interrupt the workflow for both the technologist and radiologist. In this study, we develop and validate a deep learning algorithm to detect non-diagnostic lateral airway radiographs. Read More

Authors:  Somasundaram Elanchezhian , Brady Samuel , Crotty Eric , Trout Andrew , Anton Christopher , Towbin Alexander , Coley Brian , Dillman Jonathan

Keywords:  Deep learning, Airway, Xray