AIC-UNet: Anatomy-informed Cascaded UNet for Robust Multi-Organ Segmentation

arXiv:2403.18878v1 Announce Type: cross
Abstract: Imposing key anatomical features, such as the number of organs, their shapes, sizes, and relative positions, is crucial for building a robust multi-organ segmentation model. Current attempts to incorporate anatomical features include broadening effective receptive fields (ERF) size with resource- and data-intensive modules such as self-attention or introducing organ-specific topology regularizers, which may not scale to multi-organ segmentation problems where inter-organ relation also plays a huge role. We introduce a new approach to impose anatomical …

aic arxiv cs.cv cs.lg eess.iv robust segmentation type unet