The adoption of machine learning in healthcare calls for model transparency and explainability. In this work, we introduce Signature Activation, a saliency method that generates holistic and class-agnostic explanations for Convolutional Neural Network (CNN) outputs. Our method exploits the fact that certain kinds of medical images, such as angiograms, have clear foreground and background objects. We give theoretical explanation to justify our methods. We show the potential use of our method in clinical settings through evaluating its efficacy for aiding the detection of lesions in coronary angiograms.

翻译：机器学习在医疗健康领域的应用要求模型具有透明性和可解释性。本文提出签名激活（Signature Activation）——一种针对卷积神经网络（CNN）输出生成整体性且类别无关解释的显著性方法。该方法利用特定医学影像（如血管造影图）具有清晰前景与背景目标的特点，并从理论上论证了方法的有效性。通过评估该方法在辅助冠状动脉造影术中病变检测方面的效能，我们展示了其在临床场景中的应用潜力。