发现乳腺癌分割模型对年轻患者存在系统性偏差，影响诊疗公平性。
Who Does Your Algorithm Fail? Investigating Age and Ethnic Bias in the MAMA-MIA Dataset
- 分析MAMA-MIA数据集的自动分割结果，评估年龄、种族和数据来源的影响
- 年轻患者分割准确率显著更低，即使控制数据源后偏差仍存在
- 多源数据融合可能掩盖种族偏差，需逐级细查数据质量
深度学习模型旨在优化诊断流程，但公平性评估仍局限于分类任务，图像分割领域的公平性研究不足。未解决的分割偏差可能导致特定人群医疗质量差异，并在临床决策链中累积放大，加剧迭代开发中的不公平现象。本文审计了乳腺癌肿瘤分割数据集MAMA-MIA中自动化标注的公平性，评估了年龄、种族及数据来源对自动分割质量的影响。分析发现，模型对年轻患者的分割表现存在固有偏差，且该偏差在控制数据来源等混杂因素后依然存在。我们推测此偏差或与生理特征相关，这正是放射科医生与自动化系统共同面临的挑战。最后，我们揭示多数据源整合可能掩盖特定站点的种族偏差，强调必须在细粒度层面审视数据分布与质量。
原文摘要 · Abstract (English)
Deep learning models aim to improve diagnostic workflows, but fairness evaluation remains underexplored beyond classification, e.g., in image segmentation. Unaddressed segmentation bias can lead to disparities in the quality of care for certain populations, potentially compounded across clinical decision points and amplified through iterative model development. Here, we audit the fairness of the automated segmentation labels provided in the breast cancer tumor segmentation dataset MAMA-MIA. We evaluate automated segmentation quality across age, ethnicity, and data source. Our analysis reveals an intrinsic age-related bias against younger patients that continues to persist even after controlling for confounding factors, such as data source. We hypothesize that this bias may be linked to physiological factors, a known challenge for both radiologists and automated systems. Finally, we show how aggregating data from multiple data sources influences site-specific ethnic biases, underscoring the necessity of investigating data at a granular level.
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。