mlsanityData to 7 Oct 2026

VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation

arXiv 2511.11450 ↗First posted 14 Nov 2025cs.CV cs.LGcited by 19

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

We introduce VoxTell, a vision-language model for text-prompted volumetric medical image segmentation. It maps free-form descriptions, from single words to full clinical sentences, to 3D masks. Trained on 62K+ CT, MRI, and PET volumes spanning over 1K anatomical and pathological classes, VoxTell uses multi-stage vision-language fusion across decoder layers to align textual and visual features at multiple scales. It achieves state-of-the-art zero-shot performance across modalities on unseen datasets, excelling on familiar concepts while generalizing to related unseen classes. Extensive experiments further demonstrate strong cross-modality transfer, robustness to linguistic variations and clinical language, as well as accurate instance-specific segmentation from real-world text. Code is available at: https://www.github.com/MIC-DKFZ/VoxTell

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. First posted on arXiv 14 Nov 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 18.

19 papers.

Sort:

By area:

  1. 2025Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Datacited by 2
  2. 2026CT-IDP: Segmentation-Derived Quantitative Phenotypes for Interpretable Abdominal CT Disease Classificationcited by 1
  3. 2026TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CTcited by 1
  4. 2026Open-Ended CT Volume Segmentation with Weak Supervision from Languagecited by 1
  5. 2026TubeMLLM: A Foundation Model for Topology Knowledge Exploration in Vessel-like Anatomycited by 0
  6. 2026Hierarchical Text-Guided Brain Tumor Segmentation via Sub-Region-Aware Promptscited by 0
  7. 2026DGRNet: Disagreement-Guided Refinement for Uncertainty-Aware Brain Tumor Segmentationcited by 0
  8. 2026Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Trackingcited by 0
  9. 2026Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CTcited by 0
  10. 2026UniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentationcited by 0
  11. 2026MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentationcited by 0
  12. 2026Text-Guided Refinement of Multi-sequence Glioma Subregion Segmentation with a Vision-Language Foundation Modelcited by 0
7 more
  1. 2026EliSeg: Verified Target Construction for Report-Grounded Abnormality Segmentationcited by 0
  2. 2026NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentationcited by 0
  3. 2026MedPlex: Deep Vision-Language Co-Adaptation for Clinically Grounded Medical Segmentationcited by 0
  4. 2026Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CTcited by 0
  5. 2026MedVA: An End-to-End Neuro-Symbolic Agentic System for Medical Volume Visualizationcited by 0
  6. 2026SAMI3D-DW: Interactive Segmentation of Any 3D Medical Imagescited by 0
  7. 2026Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Datasetcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models
  2. 2026MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation
  3. 2026Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
  4. 2023Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation
  5. 2026Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CT
  6. 2024Read Like a Radiologist: Efficient Vision-Language Model for 3D Medical Imaging Interpretation
  7. 2025Towards Universal Text-driven CT Image Segmentation
  8. 2026T-Gated Adapter: A Lightweight Temporal Adapter for Vision-Language Medical Segmentation