BackgroundThe willingness to trust predictions formulated by automatic algorithms is key in a wide range of domains. However, a vast number of deep architectures are only able to formulate predictions without associated uncertainty.PurposeIn this study, we propose a method to convert a standard neural network into a Bayesian neural network and estimate the variability of predictions by sampling different networks similar to the original one at each forward pass.MethodsWe combine our method with a tunable rejection-based approach that employs only the fraction of the data, i.e., the share that the model can classify with an uncertainty below a user-set threshold. We test our model in a large cohort of brain images from patients with Alzheimer's disease and healthy controls, discriminating the former and latter classes based on morphometric images exclusively.ResultsWe demonstrate how combining estimated uncertainty with a rejection-based approach increases classification accuracy from 0.86 to 0.95 while retaining 75% of the test set. In addition, the model can select the cases to be recommended for, e.g., expert human evaluation due to excessive uncertainty. Importantly, our framework circumvents additional workload during the training phase by using our network “turned into Bayesian” to implicitly investigate the loss landscape in the neighborhood of each test sample in order to determine the reliability of the predictions.ConclusionWe believe that being able to estimate the uncertainty of a prediction, along with tools that can modulate the behavior of the network to a degree of confidence that the user is informed about (and comfortable with), can represent a crucial step in the direction of user compliance and easier integration of deep learning tools into everyday tasks currently performed by human operators.

中文翻译：

---

通过权重扰动实现神经网络中的不确定性估计，以改进阿尔茨海默氏病分类

背景在许多领域中，信任自动算法制定的预测的意愿是关键。然而，大量的深层架构只能在没有相关不确定性的情况下制定预测。目的在本研究中，我们提出了一种将标准神经网络转换为贝叶斯神经网络的方法，并通过对类似于模型的不同网络进行采样来估计预测的可变性。方法我们将我们的方法与基于可调拒绝的方法相结合，该方法仅采用数据的一部分，即模型可以在低于用户设置阈值的不确定性下进行分类的份额。我们在来自阿尔茨海默病患者和健康对照的大量大脑图像中测试我们的模型，仅根据形态测量图像区分前一类和后一类。结果我们演示了如何将估计的不确定性与基于拒绝的方法相结合将分类精度从 0.86 提高到0.95，同时保留 75% 的测试集。此外，该模型还可以选择推荐的案例，例如由于不确定性过多而进行专家评估。重要的是，我们的框架通过使用我们的网络“变成贝叶斯”来隐式调查每个测试样本邻域的损失情况，以确定预测的可靠性，从而避免了训练阶段的额外工作量。结论我们相信能够估计预测的不确定性，以及可以将网络行为调节到用户了解（并感到满意）的置信度的工具，可以代表朝着用户合规性和更轻松地集成深度学习方向迈出的关键一步。将工具学习到当前由人类操作员执行的日常任务中。