# Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT

arXiv: https://arxiv.org/abs/2607.12602 · HTML: https://mlsanity.com/paper/2607.12602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [SegVol: Universal and Interactive Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2311.13385/) (2023)
- [Large-Vocabulary Segmentation for Medical Images with Text Prompts](https://mlsanity.com/paper/2312.17183/) (2023)
- [VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation](https://mlsanity.com/paper/2511.11450/) (2025)
- [ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports](https://mlsanity.com/paper/2507.22030/) (2025)

## Abstract (arXiv)

Automatic voxel-level grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability. However, this task remains highly challenging due to the intricate spatial complexity of large 3D volumes and the heterogeneity of free-text findings. Existing end-to-end approaches often struggle to simultaneously learn the localized feature representations required for accurate 3D segmentation and the complex semantic understanding needed for text alignment, leading to suboptimal grounding performance. To overcome this fundamental limitation, we propose a novel decoupled framework that disentangles the problem into two specialized stages: (1) class-agnostic lesion segmentation and (2) text-volume reasoning. This structural separation allows the model to first extract candidate sub-volumes by localizing potential abnormalities. Subsequently, intensive cross-modal reasoning is performed to align these localized sub-volumes with free-text medical findings. To resolve the spatial ambiguities inherent in local regions, the reasoning module is augmented with explicit anatomical guidance, utilizing relative spatial coordinates and lung lobe priors. Evaluated on the ReXGroundingCT benchmark, our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard. These results demonstrate that decoupling detection from reasoning is a highly effective paradigm for handling the complexity of 3D medical visual grounding. Our code is publicly available at https://github.com/khuhm/DAGG.