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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.