arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.21365cs.CVcs.AIcs.LGeess.IV
收藏

面向常规和罕见OR事件可控视频合成

Towards Controllable Video Synthesis of Routine and Rare OR Events

Johns Hopkins University(约翰霍普金斯大学);Technical University Munich(慕尼黑技术大学);Johns Hopkins Medical Institutions(约翰霍普金斯医学机构)
Dominik Schneider, Lalithkumar Seenivasan, Sampath Rapuri, Vishalroshan Anil, Aiza Maksutova, Yiqing Shen, Jan Emily Mangulabnan, Hao Ding, Jose L. Porras, Masa… 展开作者

Dominik Schneider, Lalithkumar Seenivasan, Sampath Rapuri, Vishalroshan Anil, Aiza Maksutova, Yiqing Shen, Jan Emily Mangulabnan, Hao Ding, Jose L. Porras, Masaru Ishii, Mathias Unberath

AI总结:

本文提出了一种可控视频合成框架,用于生成手术室中常规和罕见事件,以支持环境智能模型的发展。

摘要:

目的:编纂包含罕见、安全关键或不典型事件的大型手术室(OR)工作流程数据集仍存在操作性和伦理上的挑战。这种数据瓶颈使开发用于检测、理解和缓解OR中罕见或安全关键事件的环境智能变得复杂。 方法:本文提出了一种OR视频扩散框架,能够可控地合成罕见和安全关键事件。该框架集成了几何抽象模块、条件模块和微调的扩散模型,首先将OR场景转换为抽象几何表示,然后对合成过程进行条件控制,最后生成逼真的OR事件视频。使用该框架,我们还编纂了一个合成数据集,用于训练和验证检测无菌场违规近似事件的AI模型。 结果:在合成常规OR事件时,我们的方法优于现成的视频扩散基线,实现了在输入和输出领域数据集中的更低FVD/LPIPS和更高的SSIM/PSNR。通过定性结果,我们展示了其对反事实事件的可控视频合成能力。在生成的合成数据上训练和验证的AI模型在检测接近安全关键事件时达到了70.13%的召回率。最后,我们进行了消融研究,以量化关键设计选择带来的性能提升。 结论:我们的解决方案能够从抽象几何表示中可控地合成常规和罕见OR事件。除了展示其生成罕见和安全关键场景的能力外,我们还展示了其支持环境智能模型发展的潜力。

英文摘要:

Purpose: Curating large-scale datasets of operating room (OR) workflow, encompassing rare, safety-critical, or atypical events, remains operationally and ethically challenging. This data bottleneck complicates the development of ambient intelligence for detecting, understanding, and mitigating rare or safety-critical events in the OR. Methods: This work presents an OR video diffusion framework that enables controlled synthesis of rare and safety-critical events. The framework integrates a geometric abstraction module, a conditioning module, and a fine-tuned diffusion model to first transform OR scenes into abstract geometric representations, then condition the synthesis process, and finally generate realistic OR event videos. Using this framework, we also curate a synthetic dataset to train and validate AI models for detecting near-misses of sterile-field violations. Results: In synthesizing routine OR events, our method outperforms off-the-shelf video diffusion baselines, achieving lower FVD/LPIPS and higher SSIM/PSNR in both in- and out-of-domain datasets. Through qualitative results, we illustrate its ability for controlled video synthesis of counterfactual events. An AI model trained and validated on the generated synthetic data achieved a RECALL of 70.13% in detecting near safety-critical events. Finally, we conduct an ablation study to quantify performance gains from key design choices. Conclusion: Our solution enables controlled synthesis of routine and rare OR events from abstract geometric representations. Beyond demonstrating its capability to generate rare and safety-critical scenarios, we show its potential to support the development of ambient intelligence models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑