Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation

ArXi:2504.03476v2 Announce Type: replace Accurate lumbar spine segmentation is crucial for diagnosing spinal disorders. Existing methods typically use coarse-grained segmentation strategies that lack the fine detail needed for precise diagnosis. Additionally, their reliance on visual-only models hinders the capture of anatomical semantics, leading to misclassified categories and poor segmentation details.