Meeting Banner
Abstract #3835

MRCP-Specific Adaptive Volume Clipping: A Deep Learning Method for Automated Removal of Unnecessary Areas in MRCP images

Yuta Sugimoto1, Naoto Fujita1, Satoshi Funayama2, Shintaro Ichikawa2, Satoshi Goshima2, and Yasuhiko Terada1
1University of Tsukuba, Tsukuba, Japan, 2Hamamatsu University School of Medicine, Hamamatsu, Japan

Synopsis

Keywords: Analysis/Processing, Biliary, Pancreas

Motivation: In Magnetic Resonance Cholangiopancreatography (MRCP), maximum-intensity projection images are created to enhance duct structures, but areas in the image that interfere with a diagnosis must be manually removed. Automating this process would greatly reduce manual workload.

Goal(s): To develop a deep learning model that automatically removes unnecessary areas in MRCP images, reducing manual processing and speeding up diagnosis.

Approach: We evaluated four approaches using two schemes (segmentation and MRCP-Specific Adaptive Volume Clipping (MAVC)) and two deep neural networks (U-Net and Transformer).

Results: The MAVC/Transformer model achieved the best performance, effectively removing unnecessary areas in MRCP images and enhancing diagnostic efficiency.

Impact: The MRCP-Specific Adaptive Volume Clipping method enhances MRCP examination efficiency by automatically removing unnecessary regions in maximum-intensity projection images of MRCP. This approach reduces manual workload, offering flexibility without precise segmentation, and improves workflow and diagnostic 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