Main Logo
Logo

Society for Pediatric Radiology – Poster Archive



Posters - Scientific

SPR Posters - Scientific

Showing Results from 1 to 30 of 37.

Horst Kelly,  Zhongxing Zhou,  Hull Nathan,  Thacker Paul,  Thorne Jamison,  Fletcher Joel,  Mccollough Cynthia

Final Pr. ID: Poster #: SCI-001

We sought to evaluate the quality and interpretability of non-contrast chest CT images in pediatric patients for the diagnosis of airway disease at two low-dose levels with and without denoising using a deep convolutional neural network (CNN), with one of the dose levels approaching that in a standard chest radiograph. Read More

Authors:  Horst Kelly,  Zhongxing Zhou,  Hull Nathan,  Thacker Paul,  Thorne Jamison,  Fletcher Joel,  Mccollough Cynthia

Keywords:  reduced-dose chest CT CNN denoising iterative reconstruction

Moretti Jean-baptiste,  Alchourron Emilie,  Stein Nina,  Farhat Ziad,  Garel Juliette,  Lapierre Chantale,  Dubois Josée,  El-jalbout Ramy

Final Pr. ID: Poster #: SCI-003

Pediatric carotid artery Intima-Media Thickness (IMT) is a non-invasive ultrasound marker of early atherosclerosis. Obesity in children is associated with increased IMT. The objective of this meta-analysis is to report IMT values in children living with overweight/obesity in the literature. Read More

Authors:  Moretti Jean-baptiste,  Alchourron Emilie,  Stein Nina,  Farhat Ziad,  Garel Juliette,  Lapierre Chantale,  Dubois Josée,  El-jalbout Ramy

Keywords:  Carotid Intima-Media Thickness Pediatric Cardiovascular Risk

Michishita Yukiko,  Miyazaki Osamu,  Imai Ayako,  Okamato Reiko,  Tsutsumi Yoshiyuki,  Miyasaka Mikiko,  Sago Haruhiko,  Kanamori Yutaka,  Nosaka Shunsuke

Final Pr. ID: Poster #: SCI-004

Esophageal atresia (EA) is a relatively rare congenital anomaly. Esophageal pouch (EP) is the only direct sign of EA on fetal MRI, but is not always seen. Distended hypopharynx (DHP) has been reported as a useful prenatal sign of EA, but as EP and DHP are both subjective assessments, the prenatal diagnosis of EA is challenging. The aim of this study was to evaluate whether quantitative measurement of distended pharynx is useful in the diagnosis of EA. Read More

Authors:  Michishita Yukiko,  Miyazaki Osamu,  Imai Ayako,  Okamato Reiko,  Tsutsumi Yoshiyuki,  Miyasaka Mikiko,  Sago Haruhiko,  Kanamori Yutaka,  Nosaka Shunsuke

Keywords:  Esophageal Atresia fetal MRI Quantitative

Bedoya M. Alejandra,  Iwasaka-neder Jade,  Bixby Sarah,  Tsai Andy

Final Pr. ID: Poster #: SCI-005

Knowing the gestational status of a neonate (premature or full-term) impacts a pediatric radiologist’s ability to generate a reasonable differential diagnosis of neonatal diseases. Though crucial, this information is often unavailable at the time of the babygram interpretation. Conventional methods based on measuring the clavicular-pubic length (CPL) and the transverse diameter of the chest (TDC) from a babygram have been proposed as reliable estimators of a neonate’s gestational age. In this study, we aimed to compare these two conventional methodologies to that of a deep-learning (DL) model in determining a neonate’s gestational status. Read More

Authors:  Bedoya M. Alejandra,  Iwasaka-neder Jade,  Bixby Sarah,  Tsai Andy

Keywords:  Artificial intelligence Clavicular-pubic length Chest width

Goncalves Luis,  Jamshidi Ramin,  Biyyam Deepa,  Patel Mittun,  Cornejo Patricia

Final Pr. ID: Poster #: SCI-006

The purpose of this case report is to alert the reader to a rare differential diagnosis for infra- as well as intradiaphragmatic lung sequestration. A 38-year-old G2P0010 pregnant patient was referred for fetal magnetic resonance imaging (MRI) due to a 14.2 x 20.2 x 18 mm left paraspinal hyperechogenic mass with no internal vascularity and no convincing systemic arterial feeding vessel concerning for neuroblastoma as seen by ultrasound (US) performed at 34 weeks. Fetal MRI performed the same week showed a homogeneous T2-hyperintense left paraspinal mass in close apposition to and associated with a small area of loss of continuity in the diaphragm. This has been previously reported by postnatal computerized tomography as the "split diaphragm" sign in a case of intradiaphragmatic lung sequestration (Meier AH, Eggli KD, Cillei RE. Intradiaphragmatic extralobar sequestration: a rare pulmonary anomaly. Pediatr Surg 200;44:e27-29). Thus, the differential diagnosis provided at the time was congenital intradiaphragmatic sequestration and neuroblastoma. The fetus delivered via uncomplicated spontaneous vaginal delivery at term. Postnatal US performed at the age of 15 days showed a left hyperechogenic mass extending from the left lower chest to the ipsilateral retroperitoneum through a small defect in the diaphragm, favored to represent an extrapulmonary lung sequestration. The left adrenal gland was normal. A follow-up CT performed at 7 months of age showed a 2.6 cm left paraspinal mass with no systemic arterial blood supply to support the diagnosis of sequestration. The differential diagnosis at the time included neurogenic tumor or a myofibroma arising from the diaphragm. Follow-up CT at 13 months of age showed similar findings. The patient underwent uneventful laparoscopic removal of the mass with a final pathological diagnosis of congenital adrenal rest. Congenital adrenal rest presenting as a diaphragmatic mass is rare and as been reported once in an adult patient with an adenoma in heterotopic adrenal tissue located in the left diaphragm, diganosed because of mass effect in the gastric fundus during an uper gastrointestinal series (Keirns MM. Two unusual tumors of the diaphragm. Radiology 1952; 52:542-547). We hope this report raises awareness of this entity as a potential differential diagnosis for prenatal masses seen in close relationship with the adrenal gland and/or diaphragm. Read More

Authors:  Goncalves Luis,  Jamshidi Ramin,  Biyyam Deepa,  Patel Mittun,  Cornejo Patricia

Keywords:  lung sequestration neuroblastoma adrenal rest

Venkatakrishna Shyam Sunder,  Otero Hansel,  Khrichenko Dmitry,  Serai Suraj

Final Pr. ID: Poster #: SCI-009

MRI can accurately quantify liver iron concentration (LIC) by using T2* sequences. Vendor based, commercially available 3D multi-echo Dixon sequences provide maps of liver T2*/R2* and allow automated, inline post-processing, avoiding conventional manual post-processing. The purpose of our study was to compare R2*/LIC estimates generated by automated 3D multi-echo Dixon sequence to values generated by GRE-based R2* relaxometry as the reference standard. Read More

Authors:  Venkatakrishna Shyam Sunder,  Otero Hansel,  Khrichenko Dmitry,  Serai Suraj

Keywords:  Liver Iron Concentration 3D multi-echo Dixon MRI

Rodriguez Takeuchi Sara,  Doria Andrea,  Sousa-plata Karen,  Man Carina,  Vidarsson Logi,  Rayner Tammy,  Mohanta Arun,  Amirabadi Afsaneh,  Schuh Suzanne

Final Pr. ID: Poster #: SCI-010

Despite being recognized as a secondary sign of appendicitis, no clear definition exists about the amount of intra-abdominal fluid considered physiologic in children. The purpose is (1) to assess the amount of intra-abdominal free fluid by US and MRI in children with suspected appendicitis, (2) to detect the performance characteristics of US for detecting free fluid, and (3) to determine the association between fluid volume and perforated appendicitis. An additional ex-vivo study was done to assess the validity of US measurement abdominal free fluid volume using phantoms. Read More

Authors:  Rodriguez Takeuchi Sara,  Doria Andrea,  Sousa-plata Karen,  Man Carina,  Vidarsson Logi,  Rayner Tammy,  Mohanta Arun,  Amirabadi Afsaneh,  Schuh Suzanne

Keywords:  Appendicitis ascites ultrasonography

Givler Nicole,  Gouge Laura,  Vogel Daniel,  Averill Lauren

Final Pr. ID: Poster #: SCI-012

For patients who had implants placed at our hospital, we found missing documentation when patients presented for imaging procedures. Lack of documentation led to patient safety concerns and time needed to research implants. Using continuous improvement (CI) methods, we aimed to eliminate instances of missing make, model, & manufacturer (3M) information in the EMR for patients recovering in the PACU after an implant procedure. We also aimed to reduce CT/MRI technologist search time for implant information in the EMR to ≤ 5 minutes. Read More

Authors:  Givler Nicole,  Gouge Laura,  Vogel Daniel,  Averill Lauren

Keywords:  implant documentation continuous improvement interdisciplinary

Yen Christopher,  Bhakta Kavita,  Terzo Madison,  Guleria Saurabh,  Hussaini Shaheen,  Huynh Tommy

Final Pr. ID: Poster #: SCI-014

Non-contrast MRI with focused rapid-acquisition sequences can be used in place of CT for effective diagnosis of pediatric acute appendicitis (PAS). However, higher costs and limited resources are major considerations when considering its use. The goal of this study was to evaluate accuracy, utilization, and cost of MR compared to US and CT in the diagnosis of PAS. Read More

Authors:  Yen Christopher,  Bhakta Kavita,  Terzo Madison,  Guleria Saurabh,  Hussaini Shaheen,  Huynh Tommy

Keywords:  magnetic resonance billing quality

Rooks Elizabeth,  Rousslang Lee,  Meldrum Jaren,  Ishikawa Kyle,  Chen John,  Rousslang Nikki,  Nayiga Joyce,  Destigter Kristen

Final Pr. ID: Poster #: SCI-015

Resident trainees in East Africa are challenged in learning pediatric radiology due to limited access to subspecialty knowledge and mentorship. The ubiquitous use of smartphones provides the opportunity to use free instant messaging apps to deliver medical education. To test this approach, we delivered case-based modules via WhatsApp to residents to assess knowledge of pediatric radiology and elicited their feedback for evaluation. Read More

Authors:  Rooks Elizabeth,  Rousslang Lee,  Meldrum Jaren,  Ishikawa Kyle,  Chen John,  Rousslang Nikki,  Nayiga Joyce,  Destigter Kristen

Keywords:  Pediatric Radiology East Africa Education

Handa Atsuhiko,  Bedoya M. Alejandra,  Iwasaka-neder Jade,  Johnston Patrick,  Bixby Sarah

Final Pr. ID: Poster #: SCI-019

To assess the equivalence of MRI without Gd-based contrast and MRI with contrast in the evaluation of synovitis in pediatric patients with juvenile idiopathic arthritis (JIA).

Contrast-enhanced imaging has been the gold-standard for MR evaluation of synovitis in patients with JIA (JAMRIS system). Conventional 2D MRI sequences did not allow reliable differentiation between synovium vs joint fluid. With higher field-strength magnets (1.5T or 3T), and high-resolution 3D sequences, the synovium may be differentiated from joint fluid on noncontrast MRI.
Read More

Authors:  Handa Atsuhiko,  Bedoya M. Alejandra,  Iwasaka-neder Jade,  Johnston Patrick,  Bixby Sarah

Keywords:  arthritis MRI contrast

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

Knight Jessica,  Jaremko Jacob,  Zhou Yuyue,  Keen Christopher,  Rakkundedeth Abhilash,  Ghasseminia Siyavash,  Wichuk Stephanie,  Brilz Alan,  Alves Pereira Fatima,  Kirschner David

Final Pr. ID: Poster #: SCI-021

Wrist trauma is common in children and generally requires radiography for diagnosis. Many children who receive radiographs do not have fractures and are thus subjected to unnecessary radiation exposure along with increased wait times in the emergency department (ED). Ultrasound (US) is safe, cost-effective, portable and sensitive in visualizing cortical disruption, potentially making it a valuable tool for bedside assessment of fractures. This study aims to determine the feasibility of using US to detect distal radius fractures (DRF) in children and to contrast the accuracy of hand-held device compatible 2D transducers to 3D transducers that can only be used with traditional US machines. In order to address difficulties in US image interpretation by inexperienced users, we investigated the utility of an artificial intelligence (AI) network. Read More

Authors:  Knight Jessica,  Jaremko Jacob,  Zhou Yuyue,  Keen Christopher,  Rakkundedeth Abhilash,  Ghasseminia Siyavash,  Wichuk Stephanie,  Brilz Alan,  Alves Pereira Fatima,  Kirschner David

Keywords:  Artificial Intelligence Ultrasound Musculoskeletal

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

Tokaria Rumana,  Jaramillo Diego

Final Pr. ID: Poster #: SCI-023

It is estimated that the ratio between the femoral and tibial growths is 0.94/0.67 (1.4), but the accuracy of the data used to obtain it is limited. We aim to find a correlation between the rate of new bone growth in between each zebra line in the patients with Osteogenesis Imperfects (OI) who have received cyclic bisphosphonate (BP) therapy with each treatment cycle between the distal tibia and proximal femur. This will allow us to quantify the growth of the distal femur and proximal tibia with accuracy. Read More

Authors:  Tokaria Rumana,  Jaramillo Diego

Keywords:  Osteogenesis Imperfecta zebra lines growth rate

Hutt Airyn,  Shaffer Laura,  Chandra Tushar,  Hayes Laura

Final Pr. ID: Poster #: SCI-024

The growing skeleton has a radiographically different appearance from an adult’s until late adolescence when the physes fuse. If unfamiliar with recognizing these differences on a radiograph, it is common for normal variants to be misinterpreted as fractures and referred to subspecialty orthopedic care. The arising consequences are avoidable; however, to educate caregivers providing interpretations of pediatric orthopedic radiographs we must first understand why and how often these misinterpretations occur. Read More

Authors:  Hutt Airyn,  Shaffer Laura,  Chandra Tushar,  Hayes Laura

Keywords:  Radiography Normal Variants Misinterpretations

Dopp Matthew,  Lund Matthew,  Bartnik-olson Brenda,  Barnes Samuel,  Udochukwu Oyoyo,  Burns-benggon Jennifer,  Paggie Kim

Final Pr. ID: Poster #: SCI-025

Magnetic Resonance Spectroscopy (MRS) is an important imaging adjunct for the diagnosis of hypoxic ischemic injury and brain death. As the concentration of adenosine triphosphate is depleted, the cell switches from oxidative phosphorylation to anaerobic glycolysis. The byproduct of this metabolic pathway is the creation of lactate from pyruvate. This leads to lactic acidosis, which can be detected with MRS. The presence of a lactate peak on MRS is not specific to the degree of hypoxic injury. In hypoxic conditions, other metabolites are detectable by MRS such as Alanine. Alanine is a product of the glucose-alanine cycle, where Pyruvate is converted to Alanine. We hypothesize the presence of high level of Alanine is seen only in severe hypoxia, and therefore may be a more specific marker for severe HIE and brain death. Read More

Authors:  Dopp Matthew,  Lund Matthew,  Bartnik-olson Brenda,  Barnes Samuel,  Udochukwu Oyoyo,  Burns-benggon Jennifer,  Paggie Kim

Keywords:  Brain Death MRS Hypoxia

Schoeman Sean,  Venkatakrishna Shyam Sunder,  Chacko Anith,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-026

To assess the utility and adaptability of some widely used automated segmentation methods when applied to abnormal pediatric magnetic resonance imaging (MRI) brain scans. Segmentation is an essential component of the workflow when building 3D anatomical models of abnormal pediatric brains to demonstrate surface pathology. Read More

Authors:  Schoeman Sean,  Venkatakrishna Shyam Sunder,  Chacko Anith,  Andronikou Savvas

Keywords:  Segmentation 3D Printing MRI Brain

Bao Rina,  Grant Ellen,  Ou Yangming

Final Pr. ID: Poster #: SCI-027

Hypoxic ischemic encephalopathy (HIE) is a brain injury that occurs in 1 ∼ 5/1000 term-born neonates. HIE lesion detection is a crucial step in clinical care of HIE. It could lead to a more accurate estimation of prognosis, a better understanding of neurological symptoms, and a timely prediction of response to therapy in this population. In addition, the rise of Artificial Intelligence (AI) brings hope to objectively and accurately finding HIE lesions. With public MRI data for brain tumors, Alzheimer’s Disease, and other diseases, AI has achieved significant success in MRI-based diagnosis and prognosis of these diseases. To facilitate the early prognosis and diagnosis of HIE, in this work, we focus on HIE lesion detection with MRI data using deep learning methods. Read More

Authors:  Bao Rina,  Grant Ellen,  Ou Yangming

Keywords:  Brain MRIs Brain injury Hypoxic Ischemic Encephalopathy

Freiling John,  Desai Nilesh,  Whitehead William,  Kralik Stephen,  Huisman Thierry

Final Pr. ID: Poster #: SCI-028

The purpose of this study was to determine if concavity of the basiocciput and concavity of the posterior atlanto-occipital membrane are correlated with the need for future hydrocephalus surgical intervention. Read More

Authors:  Freiling John,  Desai Nilesh,  Whitehead William,  Kralik Stephen,  Huisman Thierry

Keywords:  Chiari II Hydrocephalus

Venkatakrishna Shyam Sunder,  Chacko Anith,  Schoeman Sean,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-029


Effective text-based communication, through radiologist reports, of imaging findings in term Hypoxic Ischemic Injury (HII) to family members, non-radiologist colleagues and members of the legal profession can be extremely challenging. Utilization of 3D printed models, where the actual findings of the brain can be communicated via tactile perception and rotating/grasping the models is a potential solution which has not been tested in practice. We aimed to determine the sensitivity and specificity of different groups, comprising trained radiologists, non-radiologist physicians and non-physicians, in the detection of gross disease of the cerebral cortex from 3D printed brain models derived from MRI scans of children.
Read More

Authors:  Venkatakrishna Shyam Sunder,  Chacko Anith,  Schoeman Sean,  Andronikou Savvas

Keywords:  Magnetic Resonance Imaging 3D Printing Hypoxic Ischemic Injury

Bao Rina,  Grant Ellen,  Ou Yangming

Final Pr. ID: Poster #: SCI-030

Hypoxic Ischemic Encephalopathy (HIE) is a brain injury caused by a lack of blood and oxygen supply to the brain. HIE affects 4,000,000 term-born neonates per year worldwide, with an estimated 2 billion/year cost in the US, let alone family burdens. Therefore, reducing mortality and morbidity for HIE patients remains an important public health concern. Therapeutic hypothermia (TH) was established in 2005 as a standard therapy by cooling patients to 33-34°C in the first six postnatal hours for 72 hours. However, 35–50% of the patients still experience adverse outcomes, defined as death or cognitive Bayley Scales of Infant Development by age two years. Ongoing HIE-related trials worldwide are testing whether new therapies can supplement TH and further reduce adverse outcomes. However, therapeutic innovation is slow and inconclusive, for 1) before therapy, patients at high risk of developing adverse outcomes cannot be identified; 2) after therapy, outcomes cannot be measured until age two years. Besides, public MRI data exists for hundreds of patients with brain tumors, Alzheimer’s Disease, and other diseases, fueling AI’s success in MRI-based diagnosis and prognosis of brain tumor, Alzheimer’s Disease, and other disorders. In contrast, annotated MRIs with linked clinical and bio-marker data do not exist publicly for HIE. Our previous work has collected multi-site HIE MRI data. Therefore, to fill the gap in HIE diagnosis with MRI data, target high-risk patients, increase efficiency, evaluate therapeutic effects early, and expedite therapeutic innovations, in this work, we propose to predict 2-year neurocognitive outcomes in neonates using brain MRIs by deep learning methods. Read More

Authors:  Bao Rina,  Grant Ellen,  Ou Yangming

Keywords:  Brain MRIs Brain injury Hypoxic Ischemic Encephalopathy

Tsang Brian,  Gupta Aaryan,  Takahashi Marcelo,  Ola Tolulope,  Baffi Henrique,  Doria Andrea

Final Pr. ID: Poster #: SCI-031

1) To systematically review the uses of AI for magnetic resonance (MR) imaging assessment of primary pediatric cancer and identify common literature topics and knowledge gaps. 2) To assess the adherence of the existing literature to the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines. Read More

Authors:  Tsang Brian,  Gupta Aaryan,  Takahashi Marcelo,  Ola Tolulope,  Baffi Henrique,  Doria Andrea

Keywords:  Artificial intelligence Pediatric cancer Magnetic resonance imaging

Raju Rajiv,  Quijano Carla,  Prada Carlos

Final Pr. ID: Poster #: SCI-032

Hemihyperplasia is most classically associated with Beckwidth Wiedemann, though there are many cases which are associated with other syndromes or are idiopathic in nature. Current screening recommendations for hemihyperplasia do not distinguish between different subtypes of hemihyperplasia. The purpose of this study was to determine whether there is a statistically significant difference in incidence of development of abdominal tumors between hemihyperplasia patients with Beckwidth Wiedemann Syndrome and Non Beckwidth Wiedemann associated hemihyperplasia. Read More

Authors:  Raju Rajiv,  Quijano Carla,  Prada Carlos

Keywords:  Beckwidth Wiedemann Syndrome Hemihyperplasia Genetics

Alzaher Asrar,  Busaeed Fajir,  Alsayegh Hassan

Final Pr. ID: Poster #: SCI-033

In the background of this limited data, this study aims to analyze and compare the size significance of right iliac fossa lymph nodes in pediatric patients in relation to metabolic activity on (18F-FDG PET/CT), scan in tertiary center managing oncological and non-oncological cases. Read More

Authors:  Alzaher Asrar,  Busaeed Fajir,  Alsayegh Hassan

Keywords:  Lymph node size PET/CT CT

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

Calle Toro Juan,  Bester Dewald,  Venkatakrishna Shyam Sunder,  Ali Krim Ahmed,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-036

Suspected airway compression in symptomatic children with Lymphobronchial Tuberculosis (LBTB) can be diagnosed using modern computed tomography (CT) assisted by coronal minimum intensity projection (MinIP) reconstructions. The accuracy of plain radiographs in detecting airway compression in children with TB has not been evaluated against an imaging gold standard in a dedicated manner.

We aimed to compare frontal CXR against thick-slab angled coronal CT MinIP in identifying airway stenosis at ten specific sites and to determine the agreement between the modalities regarding the degree of stenosis.
Read More

Authors:  Calle Toro Juan,  Bester Dewald,  Venkatakrishna Shyam Sunder,  Ali Krim Ahmed,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Keywords:  Lymphobronchial Tuberculosis minimum intensity projection computed tomography

Calle Toro Juan,  Ali Krim Ahmed,  Venkatakrishna Shyam Sunder,  Bester Dewald,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-038

Lymphobronchial TB (LBTB) in children refers to airway narrowing by tuberculous lymphadenopathy. Diagnosis is made invasively using flexible bronchoscopy or noninvasively with CT, which can include minimum intensity projection (MinIP) reconstructions.

Our aim was to generate standardized coronal minimum intensity projection CT reconstructions and compare these with flexible bronchoscopy in children with LBTB.
Read More

Authors:  Calle Toro Juan,  Ali Krim Ahmed,  Venkatakrishna Shyam Sunder,  Bester Dewald,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Keywords:  Trachea CT Lymphobronchial TB

Bao Rina,  Grant Ellen,  Ou Yangming

Final Pr. ID: Poster #: SCI-030

Hypoxic Ischemic Encephalopathy (HIE) is a brain injury caused by a lack of blood and oxygen supply to the brain. HIE affects 4,000,000 term-born neonates per year worldwide, with an estimated 2 billion/year cost in the US, let alone family burdens. Therefore, reducing mortality and morbidity for HIE patients remains an important public health concern. Therapeutic hypothermia (TH) was established in 2005 as a standard therapy by cooling patients to 33-34°C in the first six postnatal hours for 72 hours. However, 35–50% of the patients still experience adverse outcomes, defined as death or cognitive Bayley Scales of Infant Development by age two years. Ongoing HIE-related trials worldwide are testing whether new therapies can supplement TH and further reduce adverse outcomes. However, therapeutic innovation is slow and inconclusive, for 1) before therapy, patients at high risk of developing adverse outcomes cannot be identified; 2) after therapy, outcomes cannot be measured until age two years. Besides, public MRI data exists for hundreds of patients with brain tumors, Alzheimer’s Disease, and other diseases, fueling AI’s success in MRI-based diagnosis and prognosis of brain tumor, Alzheimer’s Disease, and other disorders. In contrast, annotated MRIs with linked clinical and bio-marker data do not exist publicly for HIE. Our previous work has collected multi-site HIE MRI data. Therefore, to fill the gap in HIE diagnosis with MRI data, target high-risk patients, increase efficiency, evaluate therapeutic effects early, and expedite therapeutic innovations, in this work, we propose to predict 2-year neurocognitive outcomes in neonates using brain MRIs by deep learning methods. Read More

Authors:  Bao Rina,  Grant Ellen,  Ou Yangming

Keywords:  Brain MRIs Brain injury Hypoxic Ischemic Encephalopathy

Venkatakrishna Shyam Sunder,  Chacko Anith,  Schoeman Sean,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-029


Effective text-based communication, through radiologist reports, of imaging findings in term Hypoxic Ischemic Injury (HII) to family members, non-radiologist colleagues and members of the legal profession can be extremely challenging. Utilization of 3D printed models, where the actual findings of the brain can be communicated via tactile perception and rotating/grasping the models is a potential solution which has not been tested in practice. We aimed to determine the sensitivity and specificity of different groups, comprising trained radiologists, non-radiologist physicians and non-physicians, in the detection of gross disease of the cerebral cortex from 3D printed brain models derived from MRI scans of children.
Read More

Authors:  Venkatakrishna Shyam Sunder,  Chacko Anith,  Schoeman Sean,  Andronikou Savvas

Keywords:  Magnetic Resonance Imaging 3D Printing Hypoxic Ischemic Injury

Alzaher Asrar,  Busaeed Fajir,  Alsayegh Hassan

Final Pr. ID: Poster #: SCI-033

In the background of this limited data, this study aims to analyze and compare the size significance of right iliac fossa lymph nodes in pediatric patients in relation to metabolic activity on (18F-FDG PET/CT), scan in tertiary center managing oncological and non-oncological cases. Read More

Authors:  Alzaher Asrar,  Busaeed Fajir,  Alsayegh Hassan

Keywords:  Lymph node size PET/CT CT

Tsang Brian,  Gupta Aaryan,  Takahashi Marcelo,  Ola Tolulope,  Baffi Henrique,  Doria Andrea

Final Pr. ID: Poster #: SCI-031

1) To systematically review the uses of AI for magnetic resonance (MR) imaging assessment of primary pediatric cancer and identify common literature topics and knowledge gaps. 2) To assess the adherence of the existing literature to the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines. Read More

Authors:  Tsang Brian,  Gupta Aaryan,  Takahashi Marcelo,  Ola Tolulope,  Baffi Henrique,  Doria Andrea

Keywords:  Artificial intelligence Pediatric cancer Magnetic resonance imaging

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

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

Hutt Airyn,  Shaffer Laura,  Chandra Tushar,  Hayes Laura

Final Pr. ID: Poster #: SCI-024

The growing skeleton has a radiographically different appearance from an adult’s until late adolescence when the physes fuse. If unfamiliar with recognizing these differences on a radiograph, it is common for normal variants to be misinterpreted as fractures and referred to subspecialty orthopedic care. The arising consequences are avoidable; however, to educate caregivers providing interpretations of pediatric orthopedic radiographs we must first understand why and how often these misinterpretations occur. Read More

Authors:  Hutt Airyn,  Shaffer Laura,  Chandra Tushar,  Hayes Laura

Keywords:  Radiography Normal Variants Misinterpretations

Tokaria Rumana,  Jaramillo Diego

Final Pr. ID: Poster #: SCI-023

It is estimated that the ratio between the femoral and tibial growths is 0.94/0.67 (1.4), but the accuracy of the data used to obtain it is limited. We aim to find a correlation between the rate of new bone growth in between each zebra line in the patients with Osteogenesis Imperfects (OI) who have received cyclic bisphosphonate (BP) therapy with each treatment cycle between the distal tibia and proximal femur. This will allow us to quantify the growth of the distal femur and proximal tibia with accuracy. Read More

Authors:  Tokaria Rumana,  Jaramillo Diego

Keywords:  Osteogenesis Imperfecta zebra lines growth rate

Venkatakrishna Shyam Sunder,  Otero Hansel,  Khrichenko Dmitry,  Serai Suraj

Final Pr. ID: Poster #: SCI-009

MRI can accurately quantify liver iron concentration (LIC) by using T2* sequences. Vendor based, commercially available 3D multi-echo Dixon sequences provide maps of liver T2*/R2* and allow automated, inline post-processing, avoiding conventional manual post-processing. The purpose of our study was to compare R2*/LIC estimates generated by automated 3D multi-echo Dixon sequence to values generated by GRE-based R2* relaxometry as the reference standard. Read More

Authors:  Venkatakrishna Shyam Sunder,  Otero Hansel,  Khrichenko Dmitry,  Serai Suraj

Keywords:  Liver Iron Concentration 3D multi-echo Dixon MRI

Handa Atsuhiko,  Bedoya M. Alejandra,  Iwasaka-neder Jade,  Johnston Patrick,  Bixby Sarah

Final Pr. ID: Poster #: SCI-019

To assess the equivalence of MRI without Gd-based contrast and MRI with contrast in the evaluation of synovitis in pediatric patients with juvenile idiopathic arthritis (JIA).

Contrast-enhanced imaging has been the gold-standard for MR evaluation of synovitis in patients with JIA (JAMRIS system). Conventional 2D MRI sequences did not allow reliable differentiation between synovium vs joint fluid. With higher field-strength magnets (1.5T or 3T), and high-resolution 3D sequences, the synovium may be differentiated from joint fluid on noncontrast MRI.
Read More

Authors:  Handa Atsuhiko,  Bedoya M. Alejandra,  Iwasaka-neder Jade,  Johnston Patrick,  Bixby Sarah

Keywords:  arthritis MRI contrast

Moretti Jean-baptiste,  Alchourron Emilie,  Stein Nina,  Farhat Ziad,  Garel Juliette,  Lapierre Chantale,  Dubois Josée,  El-jalbout Ramy

Final Pr. ID: Poster #: SCI-003

Pediatric carotid artery Intima-Media Thickness (IMT) is a non-invasive ultrasound marker of early atherosclerosis. Obesity in children is associated with increased IMT. The objective of this meta-analysis is to report IMT values in children living with overweight/obesity in the literature. Read More

Authors:  Moretti Jean-baptiste,  Alchourron Emilie,  Stein Nina,  Farhat Ziad,  Garel Juliette,  Lapierre Chantale,  Dubois Josée,  El-jalbout Ramy

Keywords:  Carotid Intima-Media Thickness Pediatric Cardiovascular Risk

Schoeman Sean,  Venkatakrishna Shyam Sunder,  Chacko Anith,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-026

To assess the utility and adaptability of some widely used automated segmentation methods when applied to abnormal pediatric magnetic resonance imaging (MRI) brain scans. Segmentation is an essential component of the workflow when building 3D anatomical models of abnormal pediatric brains to demonstrate surface pathology. Read More

Authors:  Schoeman Sean,  Venkatakrishna Shyam Sunder,  Chacko Anith,  Andronikou Savvas

Keywords:  Segmentation 3D Printing MRI Brain

Rodriguez Takeuchi Sara,  Doria Andrea,  Sousa-plata Karen,  Man Carina,  Vidarsson Logi,  Rayner Tammy,  Mohanta Arun,  Amirabadi Afsaneh,  Schuh Suzanne

Final Pr. ID: Poster #: SCI-010

Despite being recognized as a secondary sign of appendicitis, no clear definition exists about the amount of intra-abdominal fluid considered physiologic in children. The purpose is (1) to assess the amount of intra-abdominal free fluid by US and MRI in children with suspected appendicitis, (2) to detect the performance characteristics of US for detecting free fluid, and (3) to determine the association between fluid volume and perforated appendicitis. An additional ex-vivo study was done to assess the validity of US measurement abdominal free fluid volume using phantoms. Read More

Authors:  Rodriguez Takeuchi Sara,  Doria Andrea,  Sousa-plata Karen,  Man Carina,  Vidarsson Logi,  Rayner Tammy,  Mohanta Arun,  Amirabadi Afsaneh,  Schuh Suzanne

Keywords:  Appendicitis ascites ultrasonography

Calle Toro Juan,  Bester Dewald,  Venkatakrishna Shyam Sunder,  Ali Krim Ahmed,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-036

Suspected airway compression in symptomatic children with Lymphobronchial Tuberculosis (LBTB) can be diagnosed using modern computed tomography (CT) assisted by coronal minimum intensity projection (MinIP) reconstructions. The accuracy of plain radiographs in detecting airway compression in children with TB has not been evaluated against an imaging gold standard in a dedicated manner.

We aimed to compare frontal CXR against thick-slab angled coronal CT MinIP in identifying airway stenosis at ten specific sites and to determine the agreement between the modalities regarding the degree of stenosis.
Read More

Authors:  Calle Toro Juan,  Bester Dewald,  Venkatakrishna Shyam Sunder,  Ali Krim Ahmed,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Keywords:  Lymphobronchial Tuberculosis minimum intensity projection computed tomography

Calle Toro Juan,  Ali Krim Ahmed,  Venkatakrishna Shyam Sunder,  Bester Dewald,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Final Pr. ID: Poster #: SCI-038

Lymphobronchial TB (LBTB) in children refers to airway narrowing by tuberculous lymphadenopathy. Diagnosis is made invasively using flexible bronchoscopy or noninvasively with CT, which can include minimum intensity projection (MinIP) reconstructions.

Our aim was to generate standardized coronal minimum intensity projection CT reconstructions and compare these with flexible bronchoscopy in children with LBTB.
Read More

Authors:  Calle Toro Juan,  Ali Krim Ahmed,  Venkatakrishna Shyam Sunder,  Bester Dewald,  Lucas Susan,  Goussard Pierre,  Andronikou Savvas

Keywords:  Trachea CT Lymphobronchial TB

Goncalves Luis,  Jamshidi Ramin,  Biyyam Deepa,  Patel Mittun,  Cornejo Patricia

Final Pr. ID: Poster #: SCI-006

The purpose of this case report is to alert the reader to a rare differential diagnosis for infra- as well as intradiaphragmatic lung sequestration. A 38-year-old G2P0010 pregnant patient was referred for fetal magnetic resonance imaging (MRI) due to a 14.2 x 20.2 x 18 mm left paraspinal hyperechogenic mass with no internal vascularity and no convincing systemic arterial feeding vessel concerning for neuroblastoma as seen by ultrasound (US) performed at 34 weeks. Fetal MRI performed the same week showed a homogeneous T2-hyperintense left paraspinal mass in close apposition to and associated with a small area of loss of continuity in the diaphragm. This has been previously reported by postnatal computerized tomography as the "split diaphragm" sign in a case of intradiaphragmatic lung sequestration (Meier AH, Eggli KD, Cillei RE. Intradiaphragmatic extralobar sequestration: a rare pulmonary anomaly. Pediatr Surg 200;44:e27-29). Thus, the differential diagnosis provided at the time was congenital intradiaphragmatic sequestration and neuroblastoma. The fetus delivered via uncomplicated spontaneous vaginal delivery at term. Postnatal US performed at the age of 15 days showed a left hyperechogenic mass extending from the left lower chest to the ipsilateral retroperitoneum through a small defect in the diaphragm, favored to represent an extrapulmonary lung sequestration. The left adrenal gland was normal. A follow-up CT performed at 7 months of age showed a 2.6 cm left paraspinal mass with no systemic arterial blood supply to support the diagnosis of sequestration. The differential diagnosis at the time included neurogenic tumor or a myofibroma arising from the diaphragm. Follow-up CT at 13 months of age showed similar findings. The patient underwent uneventful laparoscopic removal of the mass with a final pathological diagnosis of congenital adrenal rest. Congenital adrenal rest presenting as a diaphragmatic mass is rare and as been reported once in an adult patient with an adenoma in heterotopic adrenal tissue located in the left diaphragm, diganosed because of mass effect in the gastric fundus during an uper gastrointestinal series (Keirns MM. Two unusual tumors of the diaphragm. Radiology 1952; 52:542-547). We hope this report raises awareness of this entity as a potential differential diagnosis for prenatal masses seen in close relationship with the adrenal gland and/or diaphragm. Read More

Authors:  Goncalves Luis,  Jamshidi Ramin,  Biyyam Deepa,  Patel Mittun,  Cornejo Patricia

Keywords:  lung sequestration neuroblastoma adrenal rest

Bedoya M. Alejandra,  Iwasaka-neder Jade,  Bixby Sarah,  Tsai Andy

Final Pr. ID: Poster #: SCI-005

Knowing the gestational status of a neonate (premature or full-term) impacts a pediatric radiologist’s ability to generate a reasonable differential diagnosis of neonatal diseases. Though crucial, this information is often unavailable at the time of the babygram interpretation. Conventional methods based on measuring the clavicular-pubic length (CPL) and the transverse diameter of the chest (TDC) from a babygram have been proposed as reliable estimators of a neonate’s gestational age. In this study, we aimed to compare these two conventional methodologies to that of a deep-learning (DL) model in determining a neonate’s gestational status. Read More

Authors:  Bedoya M. Alejandra,  Iwasaka-neder Jade,  Bixby Sarah,  Tsai Andy

Keywords:  Artificial intelligence Clavicular-pubic length Chest width

Knight Jessica,  Jaremko Jacob,  Zhou Yuyue,  Keen Christopher,  Rakkundedeth Abhilash,  Ghasseminia Siyavash,  Wichuk Stephanie,  Brilz Alan,  Alves Pereira Fatima,  Kirschner David

Final Pr. ID: Poster #: SCI-021

Wrist trauma is common in children and generally requires radiography for diagnosis. Many children who receive radiographs do not have fractures and are thus subjected to unnecessary radiation exposure along with increased wait times in the emergency department (ED). Ultrasound (US) is safe, cost-effective, portable and sensitive in visualizing cortical disruption, potentially making it a valuable tool for bedside assessment of fractures. This study aims to determine the feasibility of using US to detect distal radius fractures (DRF) in children and to contrast the accuracy of hand-held device compatible 2D transducers to 3D transducers that can only be used with traditional US machines. In order to address difficulties in US image interpretation by inexperienced users, we investigated the utility of an artificial intelligence (AI) network. Read More

Authors:  Knight Jessica,  Jaremko Jacob,  Zhou Yuyue,  Keen Christopher,  Rakkundedeth Abhilash,  Ghasseminia Siyavash,  Wichuk Stephanie,  Brilz Alan,  Alves Pereira Fatima,  Kirschner David

Keywords:  Artificial Intelligence Ultrasound Musculoskeletal

Rooks Elizabeth,  Rousslang Lee,  Meldrum Jaren,  Ishikawa Kyle,  Chen John,  Rousslang Nikki,  Nayiga Joyce,  Destigter Kristen

Final Pr. ID: Poster #: SCI-015

Resident trainees in East Africa are challenged in learning pediatric radiology due to limited access to subspecialty knowledge and mentorship. The ubiquitous use of smartphones provides the opportunity to use free instant messaging apps to deliver medical education. To test this approach, we delivered case-based modules via WhatsApp to residents to assess knowledge of pediatric radiology and elicited their feedback for evaluation. Read More

Authors:  Rooks Elizabeth,  Rousslang Lee,  Meldrum Jaren,  Ishikawa Kyle,  Chen John,  Rousslang Nikki,  Nayiga Joyce,  Destigter Kristen

Keywords:  Pediatric Radiology East Africa Education

Michishita Yukiko,  Miyazaki Osamu,  Imai Ayako,  Okamato Reiko,  Tsutsumi Yoshiyuki,  Miyasaka Mikiko,  Sago Haruhiko,  Kanamori Yutaka,  Nosaka Shunsuke

Final Pr. ID: Poster #: SCI-004

Esophageal atresia (EA) is a relatively rare congenital anomaly. Esophageal pouch (EP) is the only direct sign of EA on fetal MRI, but is not always seen. Distended hypopharynx (DHP) has been reported as a useful prenatal sign of EA, but as EP and DHP are both subjective assessments, the prenatal diagnosis of EA is challenging. The aim of this study was to evaluate whether quantitative measurement of distended pharynx is useful in the diagnosis of EA. Read More

Authors:  Michishita Yukiko,  Miyazaki Osamu,  Imai Ayako,  Okamato Reiko,  Tsutsumi Yoshiyuki,  Miyasaka Mikiko,  Sago Haruhiko,  Kanamori Yutaka,  Nosaka Shunsuke

Keywords:  Esophageal Atresia fetal MRI Quantitative

Horst Kelly,  Zhongxing Zhou,  Hull Nathan,  Thacker Paul,  Thorne Jamison,  Fletcher Joel,  Mccollough Cynthia

Final Pr. ID: Poster #: SCI-001

We sought to evaluate the quality and interpretability of non-contrast chest CT images in pediatric patients for the diagnosis of airway disease at two low-dose levels with and without denoising using a deep convolutional neural network (CNN), with one of the dose levels approaching that in a standard chest radiograph. Read More

Authors:  Horst Kelly,  Zhongxing Zhou,  Hull Nathan,  Thacker Paul,  Thorne Jamison,  Fletcher Joel,  Mccollough Cynthia

Keywords:  reduced-dose chest CT CNN denoising iterative reconstruction

Yen Christopher,  Bhakta Kavita,  Terzo Madison,  Guleria Saurabh,  Hussaini Shaheen,  Huynh Tommy

Final Pr. ID: Poster #: SCI-014

Non-contrast MRI with focused rapid-acquisition sequences can be used in place of CT for effective diagnosis of pediatric acute appendicitis (PAS). However, higher costs and limited resources are major considerations when considering its use. The goal of this study was to evaluate accuracy, utilization, and cost of MR compared to US and CT in the diagnosis of PAS. Read More

Authors:  Yen Christopher,  Bhakta Kavita,  Terzo Madison,  Guleria Saurabh,  Hussaini Shaheen,  Huynh Tommy

Keywords:  magnetic resonance billing quality

Givler Nicole,  Gouge Laura,  Vogel Daniel,  Averill Lauren

Final Pr. ID: Poster #: SCI-012

For patients who had implants placed at our hospital, we found missing documentation when patients presented for imaging procedures. Lack of documentation led to patient safety concerns and time needed to research implants. Using continuous improvement (CI) methods, we aimed to eliminate instances of missing make, model, & manufacturer (3M) information in the EMR for patients recovering in the PACU after an implant procedure. We also aimed to reduce CT/MRI technologist search time for implant information in the EMR to ≤ 5 minutes. Read More

Authors:  Givler Nicole,  Gouge Laura,  Vogel Daniel,  Averill Lauren

Keywords:  implant documentation continuous improvement interdisciplinary

Raju Rajiv,  Quijano Carla,  Prada Carlos

Final Pr. ID: Poster #: SCI-032

Hemihyperplasia is most classically associated with Beckwidth Wiedemann, though there are many cases which are associated with other syndromes or are idiopathic in nature. Current screening recommendations for hemihyperplasia do not distinguish between different subtypes of hemihyperplasia. The purpose of this study was to determine whether there is a statistically significant difference in incidence of development of abdominal tumors between hemihyperplasia patients with Beckwidth Wiedemann Syndrome and Non Beckwidth Wiedemann associated hemihyperplasia. Read More

Authors:  Raju Rajiv,  Quijano Carla,  Prada Carlos

Keywords:  Beckwidth Wiedemann Syndrome Hemihyperplasia Genetics

Bao Rina,  Grant Ellen,  Ou Yangming

Final Pr. ID: Poster #: SCI-027

Hypoxic ischemic encephalopathy (HIE) is a brain injury that occurs in 1 ∼ 5/1000 term-born neonates. HIE lesion detection is a crucial step in clinical care of HIE. It could lead to a more accurate estimation of prognosis, a better understanding of neurological symptoms, and a timely prediction of response to therapy in this population. In addition, the rise of Artificial Intelligence (AI) brings hope to objectively and accurately finding HIE lesions. With public MRI data for brain tumors, Alzheimer’s Disease, and other diseases, AI has achieved significant success in MRI-based diagnosis and prognosis of these diseases. To facilitate the early prognosis and diagnosis of HIE, in this work, we focus on HIE lesion detection with MRI data using deep learning methods. Read More

Authors:  Bao Rina,  Grant Ellen,  Ou Yangming

Keywords:  Brain MRIs Brain injury Hypoxic Ischemic Encephalopathy

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

Dopp Matthew,  Lund Matthew,  Bartnik-olson Brenda,  Barnes Samuel,  Udochukwu Oyoyo,  Burns-benggon Jennifer,  Paggie Kim

Final Pr. ID: Poster #: SCI-025

Magnetic Resonance Spectroscopy (MRS) is an important imaging adjunct for the diagnosis of hypoxic ischemic injury and brain death. As the concentration of adenosine triphosphate is depleted, the cell switches from oxidative phosphorylation to anaerobic glycolysis. The byproduct of this metabolic pathway is the creation of lactate from pyruvate. This leads to lactic acidosis, which can be detected with MRS. The presence of a lactate peak on MRS is not specific to the degree of hypoxic injury. In hypoxic conditions, other metabolites are detectable by MRS such as Alanine. Alanine is a product of the glucose-alanine cycle, where Pyruvate is converted to Alanine. We hypothesize the presence of high level of Alanine is seen only in severe hypoxia, and therefore may be a more specific marker for severe HIE and brain death. Read More

Authors:  Dopp Matthew,  Lund Matthew,  Bartnik-olson Brenda,  Barnes Samuel,  Udochukwu Oyoyo,  Burns-benggon Jennifer,  Paggie Kim

Keywords:  Brain Death MRS Hypoxia

Freiling John,  Desai Nilesh,  Whitehead William,  Kralik Stephen,  Huisman Thierry

Final Pr. ID: Poster #: SCI-028

The purpose of this study was to determine if concavity of the basiocciput and concavity of the posterior atlanto-occipital membrane are correlated with the need for future hydrocephalus surgical intervention. Read More

Authors:  Freiling John,  Desai Nilesh,  Whitehead William,  Kralik Stephen,  Huisman Thierry

Keywords:  Chiari II Hydrocephalus