FOCUS-3D Pretrained Models

This repository provides the pretrained model weights for FOCUS-3D, a deep learning framework for robust and generalizable 3D cell segmentation in fluorescence microscopy.

For source code, installation instructions, and usage examples, please visit the official GitHub repository:

GitHub: https://github.com/yu-lab-vt/FOCUS-3D

Model Weights

Checkpoint	Application
model_final.pth	General 3D cell segmentation — recommended as the default model for general fluorescence microscopy data
model_final_membrane.pth	3D cell membrane segmentation — optimized for images with fluorescently labeled cell membranes
model_final_nuclei.pth	3D cell nuclei segmentation — optimized for images with fluorescently labeled cell nuclei

License

The model weights in this repository are released under the Apache License 2.0.

Citation

If you use FOCUS-3D or these pretrained model weights in your research, please cite our work.

@article{zhang2026focus,
  title={FOCUS-3D: Robust, generalizable volumetric cell segmentation for three-dimensional fluorescence microscopy},
  author={Zhang, Qinghua and Mu, Zeyu and Liu, Boqi and Chi, Yunfeng and Li, Donglin and Wang, Wenjuan and Ni, Jian-Quan and Wan, Yinan and Yu, Li and Navajas Acedo, Joaquin and Yu, Guoqiang},
  journal={bioRxiv},
  year={2026},
  doi={10.64898/2026.08.25.746907}
}