To safely deploy deep learning-based computer vision models for computer-aided detection and diagnosis, we must ensure that they are robust and reliable. Towards that goal, algorithmic auditing has received substantial attention. To guide their audit procedures, existing methods rely on heuristic approaches or high-level objectives (e.g., non-discrimination in regards to protected attributes, such as sex, gender, or race). However, algorithms may show bias with respect to various attributes beyond the more obvious ones, and integrity issues related to these more subtle attributes can have serious consequences. To enable the generation of actionable, data-driven hypotheses which identify specific dataset attributes likely to induce model bias, we contribute a first technique for the rigorous, quantitative screening of medical image datasets. Drawing from literature in the causal inference and information theory domains, our procedure decomposes the risks associated with dataset attributes in terms of their detectability and utility (defined as the amount of information knowing the attribute gives about a task label). To demonstrate the effectiveness and sensitivity of our method, we develop a variety of datasets with synthetically inserted artifacts with different degrees of association to the target label that allow evaluation of inherited model biases via comparison of performance against true counterfactual examples. Using these datasets and results from hundreds of trained models, we show our screening method reliably identifies nearly imperceptible bias-inducing artifacts. Lastly, we apply our method to the natural attributes of a popular skin-lesion dataset and demonstrate its success. Our approach provides a means to perform more systematic algorithmic audits and guide future data collection efforts in pursuit of safer and more reliable models.

翻译：为了安全部署基于深度学习的计算机视觉模型以辅助计算机辅助检测与诊断，我们必须确保其稳健性和可靠性。为实现这一目标，算法审计已受到广泛关注。现有方法在指导审计程序时，依赖启发式方法或高层次目标（例如，在性别、种族等受保护属性方面避免歧视）。然而，算法可能对除明显属性外的多种属性产生偏差，而这些微妙属性相关的完整性问题可能带来严重后果。为生成可操作的、数据驱动的假设，以识别可能引发模型偏差的特定数据集属性，我们首次提出一种对医学影像数据集进行严格、定量筛选的技术。借鉴因果推断与信息论领域的文献，我们的方法将数据集属性相关的风险分解为可检测性与效用（定义为了解属性所提供关于任务标签的信息量）。为展示本方法的有效性与敏感性，我们构建了多个数据集，其中包含与目标标签具有不同程度关联的人工合成伪影，并通过与真实反事实例子的性能比较，评估模型继承的偏差。利用这些数据集及数百个训练模型的结果，我们证明筛选方法能够可靠识别几乎不可察觉的偏差诱发伪影。最后，我们将该方法应用于一个流行皮肤病变数据集的自然属性，并验证其成功。本方法提供了一种进行更系统化算法审计的手段，并指导未来数据收集工作，以追求更安全、更可靠的模型。