GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914588453240832 |
|---|---|
| author | Jiang, Shuo Hong, Yuhao Jiang, Chunbo Chen, Weihong Chen, Huangwei Zhu, Shenghao Wu, Beining Liu, Mingxuan Zhu, Zhu Qin, Feiwei Tan, Min Chen, Yifei |
| author_facet | Jiang, Shuo Hong, Yuhao Jiang, Chunbo Chen, Weihong Chen, Huangwei Zhu, Shenghao Wu, Beining Liu, Mingxuan Zhu, Zhu Qin, Feiwei Tan, Min Chen, Yifei |
| contents | Grounding radiology report descriptions to 3D CT volumes is essential for verifiable clinical interpretation, yet remains challenging due to the semantic-spatial gap between free-text narratives and volumetric anatomy. Existing report-assisted and vision-language grounding methods typically rely on phrase-level alignment or dense pixel supervision, resulting in limited lesion-wise correspondence and suboptimal localization accuracy. We propose GLeVE, a graph-guided lesion grounding framework with anatomical prior verification and octree-based autoregressive refinement. GLeVE treats each lesion description as an atomic semantic unit and encodes organ attribution, attributes, and inter-lesion relations through relation-aware graph reasoning to produce discriminative lesion-wise queries. Anatomy-aware proposal generation with region-level verification enforces one-to-one text-lesion alignment, while hierarchical octree refinement progressively improves boundary delineation. Experiments on AbdomenAtlas 3.0 demonstrate consistent gains over classical multimodal foundation models and report-supervised baselines in both segmentation accuracy and lesion-level localization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22619 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT Jiang, Shuo Hong, Yuhao Jiang, Chunbo Chen, Weihong Chen, Huangwei Zhu, Shenghao Wu, Beining Liu, Mingxuan Zhu, Zhu Qin, Feiwei Tan, Min Chen, Yifei Computer Vision and Pattern Recognition Grounding radiology report descriptions to 3D CT volumes is essential for verifiable clinical interpretation, yet remains challenging due to the semantic-spatial gap between free-text narratives and volumetric anatomy. Existing report-assisted and vision-language grounding methods typically rely on phrase-level alignment or dense pixel supervision, resulting in limited lesion-wise correspondence and suboptimal localization accuracy. We propose GLeVE, a graph-guided lesion grounding framework with anatomical prior verification and octree-based autoregressive refinement. GLeVE treats each lesion description as an atomic semantic unit and encodes organ attribution, attributes, and inter-lesion relations through relation-aware graph reasoning to produce discriminative lesion-wise queries. Anatomy-aware proposal generation with region-level verification enforces one-to-one text-lesion alignment, while hierarchical octree refinement progressively improves boundary delineation. Experiments on AbdomenAtlas 3.0 demonstrate consistent gains over classical multimodal foundation models and report-supervised baselines in both segmentation accuracy and lesion-level localization. |
| title | GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.22619 |