Main Logo

Society for Pediatric Radiology – Poster Archive

Showing 3 Abstracts.

Gould Sharon,  Thacker Mihir

Final Pr. ID: Poster #: CR-022

Knee deformity is the most common and complex lower extremity abnormality associated with Thrombocytopenia Absent Radius (TAR) syndrome. Conventional pre-operative imaging includes radiographs and computed tomography (CT) for assessment of joint alignment. We report utilizing 3-D MRI series and manual segmentation on commeicially available software to create 3-D printed models for pre-operative planning in a TAR syndrome patient with largely unossified epiphyses who had unusually severe femoral anteversion and genu varum. We discuss the methods used for imaging and segmentation as well as the value and limitations of the 3D print in pre-operative planning for this case. Even with the limitations we encountered, better understanding of the spatial relationships and joint alignment was achieved with 3-D model generation and aided in planning for correction of the knee varus deformity and femoral torsion. In addition, the diagnostic MRI information provided the basis to forgo construction of cruciate ligaments at this stage due to an increased risk of failure related to severe joint deformity. Because the prognosis for TAR syndrome is good if the child survives the first 2 years, it is important that orthopedic interventions are well planned to give a good outcome. Utilization of advanced imaging tools such as 3D imaging and printing may aid in definitive surgical planning in complex cases such as this one, and MRI can be used to generate usable anatomical models for pre-operative planning in children with incompletely ossified epiphyses. Read More

Authors:  Gould Sharon , Thacker Mihir

Keywords:  3D printing, MRI, segmentation

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

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