yzluka/PulmonaryEmbolismSegmentation

Pulmonary Embolism Segmentation

This repository contains a portable Hugging Face-compatible version of the Pulmonary Embolism Segmentation model from Mazurowski Lab.

The model is a 3D Residual Encoder U-Net trained with nnU-Net v2. The runtime model code is implemented directly in PyTorch, so inference does not require nnunetv2 or dynamic-network-architectures.

• GitHub: https://github.com/mazurowski-lab/PulmonaryEmbolismSegmentation
• Hugging Face model: https://huggingface.co/yzluka/PulmonaryEmbolismSegmentation
• Paper: https://link.springer.com/article/10.1007/s10278-026-01958-4
• Contact: Yixin Zhang, yz696@duke.edu

The model weights are released under a CC-BY 4.0-NC license. Researchers interested in other licensing options should contact MinnHealth.

Model

• Architecture: 3D ResidualEncoderUNet
• Input: single-channel CT volume
• Output: 2 logits, background and pulmonary embolism
• Training patch size: [224, 320, 320]
• Plan spacing: [1.0, 0.7373045682907104, 0.7373045682907104]
• Published checkpoint: fold_all

Usage

from pulmonary_embolism_segmentation import PulmonaryEmbolismSegmentationModel

model = PulmonaryEmbolismSegmentationModel.from_pretrained(
    "yzluka/PulmonaryEmbolismSegmentation",
    trust_remote_code=True,
)

For full DICOM inference, use the included helper code from the project repository:

python scripts/run_inference.py `
  --model-dir yzluka/PulmonaryEmbolismSegmentation `
  --input sample_data/02GE/dicom `
  --output outputs/02GE_segmentation_nnunet_preprocess.npz `
  --tile-size 128,256,256

The inference helper follows the nnU-Net v2 preprocessing order:

1. read image and spacing
2. crop nonzero region
3. CT clip and normalize
4. resample image to plan spacing
5. sliding-window prediction
6. resample logits back to cropped source grid
7. argmax
8. insert crop back into the original image shape

Dependencies

Core model loading:

• torch
• transformers
• numpy
• scipy
• scikit-image

DICOM/NIfTI helpers:

• SimpleITK
• nibabel

Evaluation

Evaluation details are described in the associated paper. This model card does not report standalone evaluation metrics because performance should be interpreted in the context of the dataset, preprocessing, and intended research use.

Intended Use

This model is intended for research use in pulmonary embolism segmentation from CT pulmonary angiography. It is not a medical device and should not be used for clinical decision-making without appropriate validation.

Citation

If you use this model, please cite the associated paper:

@article{pulmonary_embolism_segmentation_2026,
  title = {Pulmonary Embolism Segmentation},
  author = {Zhang, Yixin},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2026},
  doi = {10.1007/s10278-026-01958-4},
  url = {https://link.springer.com/article/10.1007/s10278-026-01958-4}
}