Label tree semantic losses for rich multi-class medical image segmentation 事件

Label tree semantic losses for rich multi-class medical image segmentation arXiv:2507.15777v4 Announce Type: replace Abstract: Rich and accurate medical image segmentation is poised to underpin the next generation of AI-defined clinical practice by delineating critical anatomy for pre-operative planning, guiding real-time intra-operative navigation, and supporting precise post-operative assessment. However, commonly used learning methods for medical and surgical imaging segmentation tasks penal