BayesCap: A Bayesian Approach to Brain Tumor Classification Using Capsule Networks
BayesCap: A Bayesian Approach to Brain Tumor Classification Using Capsule Networks
复制标题
DOI：
10.1109/lsp.2020.3034858
复制
发表时间：
2020-01-01
影响因子：
3.9
通讯作者：
Plataniotis, Konstantinos N.
中科院分区：
文献类型：
--
作者：
Afshar, Parnian;Mohammadi, Arash;Plataniotis, Konstantinos N.
卷积神经网络（CNN），这已经在许多图像相关的应用中的最先进的，容易丢失图像实例之间的重要空间信息。另一方面，胶囊网络（CapsNets）能够通过协议路由过程利用这些信息，使其成为小型数据集（如医学成像数据集）的强大架构。在医学成像问题的领域内，由于这种癌症的致命性质和肿瘤错误分类的后果，脑肿瘤分类是至关重要的。在我们最近的工作中，我们展示了开发CapsNet架构用于脑肿瘤类型分类任务的潜力。然而，与其他深度学习模型类似，CapsNets不会通过返回不确定样本来捕获预测不确定性（来自模型权重的不确定性，这对于让人类专家保持在循环中非常重要。在本文中，我们提出了一个贝叶斯CapsNet框架，简称为BayesCap，它不仅可以提供平均预测，还可以提供熵作为预测不确定性的度量。结果表明，过滤掉不确定的预测可以提高准确性，确认返回不确定的预测是一个适当的策略，以提高网络的可解释性。
Convolutional neural networks (CNNs), which have been the state-of-the-art in many image-related applications, are prone to losing important spatial information between image instances. Capsule networks (CapsNets), on the other hand, are capable of leveraging such information through their routing by agreement process, making them powerful architectures for small datasets, such asmedical imaging ones. Within the domain of medical imaging problems, brain tumor classification is of paramount importance, due to the deadly nature of this cancer and the consequences of the tumor misclassification. In our recent works, we showed potentials of developing CapsNet architecture for the task of brain tumor type classification. Similar to other deep learning models, however, CapsNets do not capture prediction uncertainty (coming from the uncertainty in the model weights, which is significantly important in keeping the human experts in the loop, by returning the uncertain samples. In this paper, we propose a Bayesian CapsNet framework, referred to as the BayesCap, that can provide not only the mean predictions, but also entropy as a measure of prediction uncertainty. Results show that filtering out the uncertain predictions can improve the accuracy, confirming that returning the uncertain predictions is an appropriate strategy for improving interpretability of the network.