Keywords: AI/ML Image Reconstruction, Data Processing, Magnetic Resonance Cholangiopancreatography; Deep learning; Image Quality; Pancreaticobiliary System; Gadoteric Acid
Motivation: An automated segmentation model of the pancreaticobiliary system facilitates the acquisition and assessment of diagnostically valuable MRCP images.
Goal(s): To determine impact of contrast enhancement and varying scanning protocols on image quality and develop automated segmentation models of the pancreaticobiliary ducts.
Approach: A multi-center retrospective study trained and validated nn-UNet models, comparing MRCP protocol quality pre- and post-contrast.
Results: The nn-UNet models trained on pre-contrast, post-contrast, and combined MRCP images achieved consistent segmentation accuracy across datasets (DICE>0.80). Post-contrast-RTr-MRCP showed improved contrast and reduced SNR (P<0.001), along with a higher percentage of 3-10 mm duct diameters (P<0.05), while no significant volume changes were observed.
Impact: The automatic segmentation model provides a robust tool for efficient 3D pancreaticobiliary reconstruction, improving MRCP workflow. Future studies may investigate optimizing MRCP quality based on patient factors or clinical scenarios, and assess diagnostic value of quantitative parameters extracted from segmentation.
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.
Keywords