Accurate multi-organ segmentation of abdominal CT is essential for many clinical applications, yet it often relies on large, fully annotated datasets. However, most available datasets are partially labeled, collected from different medical centers. To address this, we propose BAPLDE-MOSNet, a boundary-aware multi-organ segmentation network that leverages task-guided attention and dynamic feature enhancement modules to handle partially labeled data. BAPLDE-MOSNet integrates an edge prediction auxiliary regression network into the basic segmentation architecture in a multi-task learning manner. In addition, It introduces a boundary correction module by embedding boundary-related edge features into the segmentation task-related feature representation to effectively utilize boundary information to guide more accurate localization and segmentation of abdominal multi-organs. Moreover, a dynamic feature enhancement module is introduced to improve the network's attention to the target area. Our proposed method is rigorously validated on five public datasets (LiTS, KiTS, MSD Pancreas, MSD Spleen and the external BTCV benchmark), achieving state-of-the-art performance with an average DSC of 93.42% and HD95 of 3.635mm. Notably, it exhibits superior generalization on the external BTCV dataset (average DSC of 77.87% and average HD95 of 26.626 mm), outperforming both specialized single-organ networks and existing multi-organ approaches in comprehensive evaluations.
Hu et al. (Wed,) studied this question.