用轨迹蒸馏预测下颌重建后一年骨重塑，提升长期精度。
OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction
- 通过李雅普诺夫引导的连续轨迹蒸馏，从静态速度场中学习时间演化路径。
- 在344个区域上将手术切除区均方误差降低约20%，优于现有方法。
- 适合低数据临床场景，对骨科术后长期预测有实用价值。
预测下颌重建后的长期骨重塑具有重要临床意义，但标准生成模型在长时程预测中难以保持轨迹一致性和解剖保真度，尤其在数据稀缺情况下。本文提出OsteoFlow，一种基于流模型的方法，从术后第5天的CT扫描预测第一年后的CT影像。核心创新在于李雅普诺夫引导的轨迹蒸馏：不同于单步蒸馏，该方法从注册生成的静态速度场教师中，蒸馏出随时间演化的连续轨迹。结合切除区域感知的图像损失，既保证几何对应性，又不牺牲生成能力。在344个感兴趣区域上评估，OsteoFlow显著优于现有最先进方法，使手术切除区的平均绝对误差降低约20%。结果表明，轨迹蒸馏在低数据临床场景中具有长期预测潜力。代码已开源：https://github.com/hamidreza-aftabi/OsteoFlow。
原文摘要 · Abstract (English)
Predicting long-term bone remodeling after mandibular reconstruction would be of great clinical benefit, yet standard generative models struggle to maintain trajectory-level consistency and anatomical fidelity over long horizons, particularly in low-data regimes. We introduce OsteoFlow, a flow-based framework predicting Year-1 post-operative CT scans from Day-5 scans. Our core contribution is Lyapunov-guided trajectory distillation: Unlike one-step distillation, our method distills a continuous trajectory over transport time from a registration-derived stationary velocity field teacher. Combined with a resection-aware image loss, this enforces geometric correspondence without sacrificing generative capacity. Evaluated on 344 paired regions of interest, OsteoFlow significantly outperforms state-of-the-art baselines, reducing mean absolute error in the surgical resection zone by ~20%. This highlights the promise of trajectory distillation for long-term prediction in low-data clinical settings. Code is available on GitHub: https://github.com/hamidreza-aftabi/OsteoFlow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。