SCPMan: Shape context and prior constrained multi-scale attention network for pancreatic segmentation
Abstract: Highlights•Introduce MFE and MAI modules for clearer pancreas segmentation boundaries.•Propose SCM module for combined pancreas location and shape modeling.•Develop ASM module to guide pancreas shape with prior constraints.•Use weighted BCE and IoU loss functions to tackle background-pancreas area imbalance.
External IDs:doi:10.1016/j.eswa.2024.124070
Loading