用于提升息肉分割任务泛化能力的贝叶斯不确定性加权损失
Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task
- School of Computing, University of Leeds（利兹大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出在训练中利用贝叶斯预测不确定性加权损失，以缓解多中心息肉分割中的样本偏差，并在 PolypGen 上保持先进性能同时提升分布外泛化能力。
AI中文摘要：
尽管此前已有多项研究设计了息肉分割方法，但这些方法大多未在多中心数据集上经过严格评估。不同中心之间息肉外观的差异、内窥镜设备等级的差别以及采集质量的差异，导致相关方法在分布内测试数据上表现良好，而在分布外或代表性不足的样本上表现较差。不公平的模型会带来严重影响，并对临床应用构成关键挑战。我们改进了一种隐式偏差缓解方法，该方法在训练过程中利用贝叶斯预测不确定性，鼓励模型关注代表性不足的样本区域。我们在包含不同中心和图像模态、具有挑战性的多中心息肉分割数据集 PolypGen 上证明，该方法有潜力在不牺牲当前最先进性能的情况下提升泛化能力。
英文摘要：
While several previous studies have devised methods for segmentation of polyps, most of these methods are not rigorously assessed on multi-center datasets. Variability due to appearance of polyps from one center to another, difference in endoscopic instrument grades, and acquisition quality result in methods with good performance on in-distribution test data, and poor performance on out-of-distribution or underrepresented samples. Unfair models have serious implications and pose a critical challenge to clinical applications. We adapt an implicit bias mitigation method which leverages Bayesian predictive uncertainties during training to encourage the model to focus on underrepresented sample regions. We demonstrate the potential of this approach to improve generalisability without sacrificing state-of-the-art performance on a challenging multi-center polyp segmentation dataset (PolypGen) with different centers and image modalities.
