# GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT

arXiv: https://arxiv.org/abs/2605.22619 · HTML: https://mlsanity.com/paper/2605.22619/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models](https://mlsanity.com/paper/2404.00578/) (2024)
- [STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training](https://mlsanity.com/paper/2304.06716/) (2023)
- [Large-Vocabulary Segmentation for Medical Images with Text Prompts](https://mlsanity.com/paper/2312.17183/) (2023)
- [A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark](https://mlsanity.com/paper/2203.00131/) (2022)
- [RadGPT: Constructing 3D Image-Text Tumor Datasets](https://mlsanity.com/paper/2501.04678/) (2025)
- [MedSAM3: Delving into Segment Anything with Medical Concepts](https://mlsanity.com/paper/2511.19046/) (2025)
- [Visual Grounding of Whole Radiology Reports for 3D CT Images](https://mlsanity.com/paper/2312.04794/) (2023)
- [Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding](https://mlsanity.com/paper/2404.06798/) (2024)
- [SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation](https://mlsanity.com/paper/2312.14705/) (2023)
- [Learning Segmentation from Radiology Reports](https://mlsanity.com/paper/2507.05582/) (2025)
- [Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding](https://mlsanity.com/paper/2410.23822/) (2024)
- [A multi-modal vision-language model for generalizable annotation-free pathology localization](https://mlsanity.com/paper/2401.02044/) (2024)
- [Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models](https://mlsanity.com/paper/2404.12920/) (2024)
- [EXACT: an explainable anomaly-aware vision foundation model for analysis of 3D chest CT](https://mlsanity.com/paper/2604.24146/) (2026)
- [MMLNB: Multi-Modal Learning for Neuroblastoma Subtyping Classification Assisted with Textual Description Generation](https://mlsanity.com/paper/2503.12927/) (2025)
- [Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models](https://mlsanity.com/paper/2507.12236/) (2025)

## Built on by (most cited first, 1 of 1)

- [Volumetric Radiology AI in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2608.20549/) (2026)

## Abstract (arXiv)

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.