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

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.