Skull stripping with purely synthetic data

While many skull stripping algorithms have been developed for multi-modal and multi-species cases, there is still a lack of a fundamentally generalizable approach. We present PUMBA(PUrely synthetic Multimodal/species invariant Brain extrAction), a strategy to train a model for brain extraction with no real brain images or labels. Our results show that even without any real images or anatomical priors, the model achieves comparable accuracy in multi-modal, multi-species and pathological cases. This work presents a new direction of research for any generalizable medical image segmentation task.

@article{park2025_2505.07159,
  title={ Skull stripping with purely synthetic data },
  author={ Jong Sung Park and Juhyung Ha and Siddhesh Thakur and Alexandra Badea and Spyridon Bakas and Eleftherios Garyfallidis },
  journal={arXiv preprint arXiv:2505.07159},
  year={ 2025 }
}