论文标题
一种用于糖尿病性视网膜病变分类的主动学习方法，具有不确定性定量
An Active Learning Method for Diabetic Retinopathy Classification with Uncertainty Quantification
论文作者
论文摘要
近年来，深度学习（DL）技术在不同的医学成像任务上提供了最先进的性能。但是，由于涉及时间限制和专家注释者（例如放射科医生）的可用性，因此高质量注释的医学数据的可用性非常具有挑战性。此外，DL是渴望数据的，他们的培训需要广泛的计算资源。 DL的另一个问题是它们的黑盒性质以及其内部工作缺乏透明度，抑制因果理解和推理。在本文中，我们通过提出一个混合模型来共同解决这些挑战，该模型使用贝叶斯卷积神经网络（BCNN）进行不确定性量化，以及一种主动学习方法来注释未标记的数据。 BCNN用作功能描述符，然后将这些功能用于在主动学习设置中训练模型。我们评估了糖尿病性视网膜病变分类问题的拟议框架，并在不同的指标方面实现了最先进的性能。
In recent years, deep learning (DL) techniques have provided state-of-the-art performance on different medical imaging tasks. However, the availability of good quality annotated medical data is very challenging due to involved time constraints and the availability of expert annotators, e.g., radiologists. In addition, DL is data-hungry and their training requires extensive computational resources. Another problem with DL is their black-box nature and lack of transparency on its inner working which inhibits causal understanding and reasoning. In this paper, we jointly address these challenges by proposing a hybrid model, which uses a Bayesian convolutional neural network (BCNN) for uncertainty quantification, and an active learning approach for annotating the unlabelled data. The BCNN is used as a feature descriptor and these features are then used for training a model, in an active learning setting. We evaluate the proposed framework for diabetic retinopathy classification problem and have achieved state-of-the-art performance in terms of different metrics.
