Fairness, a criterion focuses on evaluating algorithm performance on different demographic groups, has gained attention in natural language processing, recommendation system and facial recognition. Since there are plenty of demographic attributes in medical image samples, it is important to understand the concepts of fairness, be acquainted with unfairness mitigation techniques, evaluate fairness degree of an algorithm and recognize challenges in fairness issues in medical image analysis (MedIA). In this paper, we first give a comprehensive and precise definition of fairness, following by introducing currently used techniques in fairness issues in MedIA. After that, we list public medical image datasets that contain demographic attributes for facilitating the fairness research and summarize current algorithms concerning fairness in MedIA. To help achieve a better understanding of fairness, and call attention to fairness related issues in MedIA, experiments are conducted comparing the difference between fairness and data imbalance, verifying the existence of unfairness in various MedIA tasks, especially in classification, segmentation and detection, and evaluating the effectiveness of unfairness mitigation algorithms. Finally, we conclude with opportunities and challenges in fairness in MedIA.
翻译:公平是评估不同人口群体算法绩效的一个重点标准,在自然语言处理、建议系统和面部识别方面引起了注意;由于医学图像样本中有大量人口特征,必须理解公平概念,熟悉减少不公平现象的技术,评估算法的公平程度,并认识医学图像分析中的公平问题的挑战(MedIA),在本文中,我们首先通过在美第列引入目前使用的公平问题公平问题技术,对公平性作出全面和准确的定义。随后,我们列出了含有人口特征的公众医疗图像数据集,以利公平研究,并总结有关美第列公平性的现有算法。为了帮助更好地理解公平性,并提请注意美第列的公平问题,我们进行了实验,比较公平性和数据不平衡之间的差异,核查美第列各项任务中存在的不公平现象,特别是在分类、分解和检测方面,以及评估不公平现象减少算法的有效性。最后,我们总结了美第列的公平性机会和挑战。