# Open-Ended CT Volume Segmentation with Weak Supervision from Language

arXiv: https://arxiv.org/abs/2607.25860 · HTML: https://mlsanity.com/paper/2607.25860/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)
- [Weakly-Supervised Semantic Segmentation via Sub-category Exploration](https://mlsanity.com/paper/2008.01183/) (2020)
- [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)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [MedSAM3: Delving into Segment Anything with Medical Concepts](https://mlsanity.com/paper/2511.19046/) (2025)
- [Pillar-0: A New Frontier for Radiology Foundation Models](https://mlsanity.com/paper/2511.17803/) (2025)
- [Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation](https://mlsanity.com/paper/2601.10880/) (2026)
- [Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/1506.04924/) (2015)
- [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)
- [Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks](https://mlsanity.com/paper/2510.14803/) (2025)
- [Weakly Supervised Lesion Co-segmentation on CT Scans](https://mlsanity.com/paper/2001.09174/) (2020)
- [UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity](https://mlsanity.com/paper/2511.13714/) (2025)
- [Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CT](https://mlsanity.com/paper/2603.02026/) (2026)
- [Improving Small Lesion Segmentation in CT Scans using Intensity Distribution Supervision: Application to Small Bowel Carcinoid Tumor](https://mlsanity.com/paper/2207.14700/) (2022)
- [Detection-Guided Deep Learning-Based Model with Spatial Regularization for Lung Nodule Segmentation](https://mlsanity.com/paper/2410.20154/) (2024)

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

- [Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT](https://mlsanity.com/paper/2609.00447/) (2026)

## Abstract (arXiv)

We introduce a method for training a text-conditioned segmentation model for CT scans, which combines voxel-level supervision with coarse but scalable slice-level supervision from reports. We extract, from a large database of scan-report pairs, descriptions of findings with indices of slices where those findings occur. We then finetune a general-purpose 2D image segmentation model, SAM3, with standard segmentation losses from strongly labeled data and with a slice-level classification loss from the extracted weak supervision. Our results on the ReXGroundingCT dataset illustrate that this strategy improves the segmentation dice score: from an 8% relative gain when there are 1000 fully labeled volumes to 22% when there are 250 fully labeled volumes.