利用深度学习训练不确定性提升脑影像分割效果
Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation
- 通过随机种子扰动捕捉训练过程中的数值不确定性
- 基于不确定性集成显著提升脑龄预测性能
- 适合关注模型可靠性与数据增强的神经影像研究者
深度学习已大幅改善神经影像分析，实现高性能且计算更快。然而，深度学习训练中的数值不确定性仍被忽视，尽管其可能严重影响模型结果可靠性。我们发现，FastSurfer分割模型的训练引入了显著的数值不确定性，其在皮层区域的波动超过非深度学习方法FreeSurfer 7.3.2。通过随机种子扰动表征该不确定性，发现其结构与数值波动相似。进一步证明，利用种子变化的多样性进行集成，可作为数据增强手段，有效提升下游脑龄回归性能。这些结果表明，训练阶段的数值不确定性是影响神经影像可靠性的关键因素，且可被转化为有益的数据增强策略。
原文摘要 · Abstract (English)
Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance with reduced computation times. Yet, the numerical uncertainty inherent to DL training remains largely underexplored despite its potential to significantly impact the reliability of model outcomes. We show that training the FastSurfer segmentation model introduces substantial numerical uncertainty that exceeds its non-DL counterpart (FreeSurfer 7.3.2) in cortical regions, potentially impacting downstream clinical results. We also characterize this training-time uncertainty using random seed perturbations and demonstrate that seed-induced variability is structurally comparable to numerical variability. We then show that seed variability can be leveraged as a data augmentation technique through ensembling to improve downstream brain age regression performance. These findings position numerical uncertainty during DL training as a substantive factor in neuroimaging reliability, with measurable consequences for downstream tasks, and demonstrate that it can simultaneously be harnessed as a data augmentation technique.
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。