As AI-based medical devices are becoming more common in imaging fields like radiology and histology, interpretability of the underlying predictive models is crucial to expand their use in clinical practice. Existing heatmap-based interpretability methods such as GradCAM only highlight the location of predictive features but do not explain how they contribute to the prediction. In this paper, we propose a new interpretability method that can be used to understand the predictions of any black-box model on images, by showing how the input image would be modified in order to produce different predictions. A StyleGAN is trained on medical images to provide a mapping between latent vectors and images. Our method identifies the optimal direction in the latent space to create a change in the model prediction. By shifting the latent representation of an input image along this direction, we can produce a series of new synthetic images with changed predictions. We validate our approach on histology and radiology images, and demonstrate its ability to provide meaningful explanations that are more informative than GradCAM heatmaps. Our method reveals the patterns learned by the model, which allows clinicians to build trust in the model's predictions, discover new biomarkers and eventually reveal potential biases.
翻译:由于AI型医疗设备在放射学和神学等成像领域越来越普遍,因此基本预测模型的可解释性对于扩大临床实践的使用至关重要。现有的基于热映射的解释方法,如GradCAM,只突出预测特征的位置,而没有解释它们如何有助于预测。在本文中,我们提出一种新的可解释性方法,通过显示如何修改输入图像,以产生不同的预测,来理解任何黑盒图像的预测。StyleGAN在医学图像方面受过培训,以提供潜在矢量和图像之间的映射。我们的方法确定了潜在空间的最佳方向,以促成模型预测的变化。通过沿着这个方向转移输入图像的潜在代表面,我们可以产生一系列新的合成图像,同时改变预测。我们验证了我们对于任何图像中的黑盒模型和放射学图像的预测方法,并表明它能够提供比GradCAM热映射图更有意义的解释。我们的方法揭示了模型所学的模型模式模式模式,使临床医生能够建立对模型的预测进行信任,最终发现新的生物标记和潜力。