Meeting Banner
Abstract #3062

Deep Learning-based Automatic Perfusion Phase Identification for Dynamic T1-weighted Liver MRI

Robert Grimm1, Malte Müller2, Cornelius Jacob1, Sabine Mollus1, Christian Tietjen3, Moon Hyung Choi4, Kazuki Oyama5, Thomas Weikert6, Andrew D Hardie7, Jeong Hee Yoon8, Heinrich von Busch3, Gregor Thoermer1, and Volker Daum2
1MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany, 2Chimaera GmbH, Erlangen, Germany, 3Digital and Automation, Siemens Healthcare GmbH, Erlangen, Germany, 4Eunpyeong St. Mary’s Hospital, Catholic University of Korea, Seoul, Korea, Republic of, 5Department of Radiology, Shinshu University Hospital, Nagano, Japan, 6Department of Radiology, Universitätsspital Basel, Basel, Switzerland, 7Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, United States, 8Seoul National University Hospital and College of Medicine, Seoul, Korea, Republic of

Synopsis

Keywords: Data Analysis, Machine Learning/Artificial IntelligenceA deep learning-based approach for automatic identification of the perfusion phases in dynamic T1-weighted liver MRI is presented. First, an encoder model combined with two dense layers was trained to classify each image into pre-contrast, arterial, portal-venous, late, or hepatobiliary phase. In a second pass, classification errors are detected and adjusted, based on the expected occurrence order and relative timing to the arterial phase. The AI model reached sensitivities of 67% to 99%. Most common mis-classifications were confusions of the portal-venous or late phase with the adjacent phases. By the rule-based adjustments, the classification performance was raised to >95% accuracy.

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.

Keywords