Skip to main content

๐Ÿงฌ BiomedParse v2

The v2 release extends BiomedParse to end-to-end 3D segmentation and adds built-in object-existence detection. It is distinct from the original 2D BiomedParse v1.

Official codePaperWeights

โ† Model atlas

At a glanceโ€‹

FieldDetails
Model typeText-guided biomedical parsing model
Research team / organizationMicrosoft Research
Input / modality3D CT, MRI, ultrasound, PET and 3D microscopy according to the v2 README; dedicated pretrained v2 weights are for 3D.
Prompt / interactionText-concept prompts; slice-wise model inference with neighboring volume context encoded into RGB input.
Code licenseCode: Apache-2.0. The Hugging Face model card lists CC BY-NC-SA 4.0 for model artifacts and requires acceptance of the gated-model conditions. Do not conflate v1 and v2 model terms.

๐Ÿ“š Paper and publicationโ€‹

A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities โ€” Nature Methods 22, 166โ€“176 (2025), DOI: 10.1038/s41592-024-02499-w. The v2 3D checkpoint also builds on the CVPR 2025 Text-guided 3D Segmentation Challenge release.

Version pin: this card follows the upstream v2 branch.

๐Ÿ“ฆ Checkpoints and accessโ€‹

biomedparse_v2.ckpt (~4.46 GB) is hosted in the gated Hugging Face repository microsoft/BiomedParse; access may require accepting model conditions and authentication. The upstream v2 README also provides a challenge-trained Docker image.

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€‹

git clone --branch v2 https://github.com/microsoft/BiomedParse.git
cd BiomedParse
conda create -n biomedparse_v2 python=3.10.14
conda activate biomedparse_v2
python -m pip install -r assets/requirements/inference.txt
# Download biomedparse_v2.ckpt after completing HF access requirements:
python inference.py --input_dir examples/imgs --output_dir outputs/3d \
--checkpoint /path/to/biomedparse_v2.ckpt --slice_batch_size 4

The script expects challenge-format preprocessed NPZ volumes. Raw DICOM/NIfTI still needs modality-appropriate intensity preprocessing; reduce --slice_batch_size if GPU memory is limited.

โš ๏ธ Version and practical notesโ€‹

Use the v2 branch and biomedparse_v2.ckpt for the 3D workflow. The v1 branch and weights are a separate 2D workflow; raw scanner images require modality-appropriate preprocessing.

๐Ÿ“œ Licenseโ€‹

Code: Apache-2.0. The Hugging Face model card lists CC BY-NC-SA 4.0 for model artifacts and requires acceptance of the gated-model conditions. Do not conflate v1 and v2 model 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.