Meeting Banner
Abstract #1871

A Deep Learning Approach for Robust Segmentation of Livers with High Iron Content from MR Images of Pediatric Patients

Zhoubing Xu1, Guillaume Chabin2, Robert Grimm3, Stephan Kannengiesser3, Li Pan4, Vibhas Deshpande5, Gregor Thoermer3, Sasa Grbic1, and Cara Morin6
1Siemens Healthineers, Princeton, NJ, United States, 2Siemens Healthineers, Paris, France, 3Siemens Healthineers, Erlangen, Germany, 4Siemens Healthineers, Baltimore, MD, United States, 5Siemens Healthineers, Austin, TX, United States, 6St. Jude Children's Research Hospital, Memphis, TN, United States

Automated MRI liver segmentation enables the inline evaluation of parametric maps for iron quantification with improved accuracy, efficiency, and repeatability compared to manual efforts. Existing methods optimized for adults and normal livers do not perform well on challenging cases in children and patients with iron overload. We developed a deep learning-based solution trained on 861 T1-weighted MRI that provided significantly improved liver segmentation compared to a commercially available solution and demonstrated its robustness on a challenging cohort of pediatric patients including cases with high iron content.

This abstract and the presentation materials are available to members only; a login is required.

Join Here