Li Yi, Zhang Huahong, Bermudez Camilo, Chen Yifan, Landman Bennett A, Vorobeychik Yevgeniy
Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, 37235, USA.
Biomedical Engineering, Vanderbilt University, Nashville, TN, 37235, USA.
Neurocomputing (Amst). 2020 Feb 28;379:370-378. doi: 10.1016/j.neucom.2019.10.085. Epub 2019 Oct 31.
Deep learning has achieved impressive performance across a variety of tasks, including medical image processing. However, recent research has shown that deep neural networks are susceptible to small adversarial perturbations in the image. We study the impact of such adversarial perturbations in medical image processing where the goal is to predict an individual's age based on a 3D MRI brain image. We consider two models: a conventional deep neural network, and a hybrid deep learning model which additionally uses features informed by anatomical context. We find that we can introduce significant errors in predicted age by adding imperceptible noise to an image, can accomplish this even for large batches of images using a single perturbation, and that the hybrid model is much more robust to adversarial perturbations than the conventional deep neural network. Our work highlights limitations of current deep learning techniques in clinical applications, and suggests a path forward.
深度学习在包括医学图像处理在内的各种任务中都取得了令人瞩目的成绩。然而，最近的研究表明，深度神经网络容易受到图像中微小对抗性扰动的影响。我们研究了这种对抗性扰动在医学图像处理中的影响，该处理的目标是基于三维磁共振成像（MRI）脑部图像预测个体年龄。我们考虑了两种模型：一种是传统的深度神经网络，另一种是混合深度学习模型，该模型还使用了解剖学背景提供的特征。我们发现，通过向图像添加难以察觉的噪声，可以在预测年龄时引入显著误差，甚至使用单个扰动就可以对大批量图像做到这一点，而且混合模型比传统深度神经网络对对抗性扰动的鲁棒性要强得多。我们的工作突出了当前深度学习技术在临床应用中的局限性，并提出了前进的方向。
