Skip to main content

๐Ÿ—ฃ๏ธ VoxTell v1.1

A free-text promptable 3D vision-language segmentation model that maps natural-language descriptions, from short labels to clinical phrases, to volumetric masks.

Official codePaperWeights

โ† Model atlas

At a glanceโ€‹

FieldDetails
Model typeFree-text 3D segmentation model
Research team / organizationGerman Cancer Research Center (DKFZ) / Helmholtz Imaging
Input / modality3D CT, MRI and PET volumes; current v1.1 weights are distributed by the authors.
Prompt / interactionFree-text prompt only; no point/box interaction is required by the standard predictor.
Code licenseCode: Apache-2.0. Check the Hugging Face repository for model-weight terms.

๐Ÿ“š Paper and publicationโ€‹

VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation โ€” IEEE/CVF CVPR 2026, pp. 37538โ€“37557; arXiv:2511.11450.

๐Ÿ“ฆ Checkpoints and accessโ€‹

Official Hugging Face repository: mrokuss/VoxTell; v1.1 is downloaded automatically on first use and cached. The model includes the frozen Qwen3-Embedding-4B text encoder.

The code, model checkpoint and any required foundation-model checkpoint can have different terms. Review each linked source before use or redistribution.

โš™๏ธ Official setup and inferenceโ€‹

conda create -n voxtell python=3.12
conda activate voxtell
# Install PyTorch matching the available CUDA driver, then:
pip install voxtell
voxtell-predict -i case.nii.gz -o output -p "liver" "spleen"

Use NIfTI input and preserve orientation metadata. VoxTell expects RAS orientation, does not automatically resample unusual voxel spacing and recommends checking orientation/spacing when results look anatomically misplaced.

โš ๏ธ Version and practical notesโ€‹

This is a text-only volumetric model. Preserve the exact English prompt, image orientation, voxel spacing and model tag; prompt wording and preprocessing can affect predictions.

๐Ÿ“œ Licenseโ€‹

Code: Apache-2.0. Check the Hugging Face repository for model-weight terms.

Citation: Cite the paper above and the upstream project as directed by its authors. This repository links to the original paper; it does not redistribute the code or weights.

Source pages checked: 27 October 2026. Upstream environments, weights and access policies may change; use the linked project as the source of truth.