Research map / Vision-language and multimodal / Multimodal LLMs
Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation
Sheng Lian, Jianlong Cai, Dengfeng Pan, Guangyong Chen, Hao Xu, Fan Zhang, Guodong Fan, Jialun Pei, Shuo Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add HASF text-visual fusion (ablation) | Swin UNETR baseline · MRSpineSeg | DSC: 64.58 -> 77.13 | Improved |
| add HASF text-visual fusion (ablation) | Swin UNETR baseline · SPIDER | DSC: 66.67 -> 73.00 | Improved |
| add CCAE contrastive enhancement (ablation) | Swin UNETR baseline · MRSpineSeg | DSC: 64.58 -> 73.08 | Improved |
| add CCAE contrastive enhancement (ablation) | Swin UNETR baseline · SPIDER | HD95: 10.29 -> 12.97 | Hurt |
| add CCAE on top of HASF (ablation) | ATM-Net · MRSpineSeg | DSC: 77.13 -> 81.72 | Improved |
| add HASF on top of CCAE (ablation) | ATM-Net · SPIDER | DSC: 69.23 -> 79.39 | Improved |
| inject text at all decoder stages instead of bottleneck only (ablation) | ATM-Net · MRSpineSeg | DSC: 76.25 -> 81.72 | Improved |
| set lambda2 to 0.2 instead of 0.1 (ablation) | ATM-Net · MRSpineSeg | DSC: 76.91 -> 81.72 | Improved |
| set lambda2 to 0.2 instead of 0.3 (ablation) | ATM-Net · MRSpineSeg | DSC: 81.04 -> 81.72 | Improved |
| use Bio-ClinicalBERT instead of RoBERTa (ablation) | ATM-Net · MRSpineSeg | DSC: 77.78 -> 81.72 | Improved |
| use Bio-ClinicalBERT instead of RoBERTa (ablation) | ATM-Net · MRSpineSeg | HD95: 9.52 -> 9.60 | Hurt |
| use Bio-ClinicalBERT instead of PubMedBERT (ablation) | ATM-Net · MRSpineSeg | DSC: 81.42 -> 81.72 | Improved |
Closest papers by meaning
- SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus (ICLR 2026 · similarity 0.86)
- Mine yOur owN Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels (TPAMI 2024 · similarity 0.85)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.83)
- CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation (NeurIPS 2024 · similarity 0.83)
- Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation (CVPR 2024 · similarity 0.83)
- MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
