Keywords: Diagnosis/Prediction, Segmentation
Motivation: Pancreatic fat accumulation is associated with inflammatory and neoplastic pancreatic diseases. Accurate pancreatic segmentation on proton density fat fraction images remains challenging.
Goal(s): Aim to improve the segmentation accuracy of the pancreas in 3D MR PDFF images.
Approach: A network framework is proposed based on the active contour model. The deep network, while accounting for the analytical solution of the problem, further incorporates deep features to enhance the model's performance.
Results: Our method shows a 9.9% improvement in the Dice coefficient compared to 3D-UNet and a 1.4% improvement compared to nnUNet.
Impact: This method effectively improves the accuracy of pancreas segmentation, enabling further analysis of fatty pancreas diseases. Furthermore, the method extends active contour model from 2D to 3D, addressing the difficulty of the active contour model when dealing with 3D images.
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