Logo

Bora: Biomedical Generalist Video Generation Model

1Northeastern University 2Shanghai University of Finance and Economics 3Fudan University 4University of Notre Dame 5Massachusetts General Hospital and Harvard Medical School 6Lehigh University

Abstract

Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for medical AI development. Diffusion models can now generate realistic images from text prompts, while recent advancements have demonstrated their ability to create diverse, high-quality videos. However, these models often struggle with generating accurate representations of medical procedures and detailed anatomical structures. This paper introduces Bora, the first spatio-temporal diffusion probabilistic model designed for text-guided biomedical video generation. Bora leverages Transformer architecture and is pre-trained on general-purpose video generation tasks. It is fine-tuned through model alignment and instruction tuning using a newly established medical video corpus, which includes paired text-video data from various biomedical fields. To the best of our knowledge, this is the first attempt to establish such a comprehensive annotated biomedical video dataset. Bora is capable of generating high-quality video data across four distinct biomedical domains, adhering to medical expert standards and demonstrating consistency and diversity. This generalist video generative model holds significant potential for enhancing medical consultation and decision-making, particularly in resource-limited settings. Additionally, Bora could pave the way for immersive medical training and procedure planning. Extensive experiments on distinct medical modalities such as endoscopy, ultrasound, MRI, and cell tracking validate the effectiveness of our model in understanding biomedical instructions and its superior performance across subjects compared to state-of-the-art generation models.

Generated Demos

Endoscopy

Ultrasound

RT-MRI

Cell

Acknowledgement

We are greatful for the following works and generous contribution to open source.

Open-Sora: Democratizing Efficient Video Production for All.

LLaVA: Large Language and Vision Assistant.

Apex: A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch.

BibTeX


      @article{sun2024bora,
        title={Bora: Biomedical Generalist Video Generation Model},
        author={Sun, Weixiang and You, Xiaocao and Zheng, Ruizhe and Yuan, Zhengqing and Li, Xiang and He, Lifang and Li, Quanzheng and Sun, Lichao},
        journal={arXiv preprint arXiv:2407.08944},
        year={2024}
      }