用知识蒸馏让单模型实现多模型的血管分割可靠性
Uncertainty-Aware Retinal Vessel Segmentation via Ensemble Distillation
- 将多个模型的预测能力浓缩到一个模型中
- 在DRIVE和FIVES数据集上表现接近多模型，计算量大幅降低
- 适合追求高效可靠的医学图像分割应用
不确定性估计对可靠的医学图像分割至关重要，尤其在视网膜血管分析中，准确预测对诊断应用极为关键。深度集成（Deep Ensembles）通过训练多个独立网络来提升分割性能，但其训练与推理成本随集成数量增加而上升。本文提出集成蒸馏（Ensemble Distillation），将多个集成模型的知识提炼至单一模型，作为常用不确定性估计方法的稳健替代方案。在DRIVE和FIVES数据集上的大量实验表明，该方法在校准性和分割指标上达到与多模型相当的性能，同时显著降低计算复杂度。结果表明，集成蒸馏为视网膜血管分割中的不确定性估计提供了一种高效且可靠的方法，具有良好的医学影像应用前景。
原文摘要 · Abstract (English)
Uncertainty estimation is critical for reliable medical image segmentation, particularly in retinal vessel analysis, where accurate predictions are essential for diagnostic applications. Deep Ensembles, where multiple networks are trained individually, are widely used to improve medical image segmentation performance. However, training and testing costs increase with the number of ensembles. In this work, we propose Ensemble Distillation as a robust alternative to commonly used uncertainty estimation techniques by distilling the knowledge of multiple ensemble models into a single model. Through extensive experiments on the DRIVE and FIVES datasets, we demonstrate that Ensemble Distillation achieves comparable performance via calibration and segmentation metrics, while significantly reducing computational complexity. These findings suggest that Ensemble distillation provides an efficient and reliable approach for uncertainty estimation in the segmentation of the retinal vessels, making it a promising tool for medical imaging applications.
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。