Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning
Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning
复制标题
使用基于三向决策的贝叶斯深度学习对皮肤癌分类的不确定性进行量化
DOI：
10.1016/j.compbiomed.2021.104418
复制
发表时间：
2021-08-21
影响因子：
7.7
通讯作者：
Nahavandi, Saeid
中科院分区：
文献类型：
--
作者：
Abdar, Moloud;Samami, Maryam;Nahavandi, Saeid
准确的自动医学图像识别，包括分类和分割，是医学图像分析中最具挑战性的任务之一。最近，深度学习方法在医学图像分类和分割方面取得了显着的成功，显然成为最先进的方法。然而，大多数这些方法无法提供不确定性量化（UQ）的输出，往往是过于自信，这可能会导致灾难性的后果。贝叶斯深度学习（BDL）方法可用于量化传统深度学习方法的不确定性，从而解决这个问题。我们采用三种不确定性量化方法来处理皮肤癌图像分类过程中的不确定性。它们是：蒙特卡罗（MC）dropout，Encavity MC（EMC）dropout和深度Encavity（DE）。为了进一步解决MC、EMC和DE方法后剩余的不确定性问题，基于三向决策（TWD）理论，提出了一种考虑不确定性的混合动态BDL模型。所提出的动态模型使我们能够在不同的分类阶段使用不同的UQ方法和不同的深度神经网络。因此，每个阶段的元素可以根据所考虑的数据集进行调整。在这项研究中，两个最好的UQ方法（即，DE和EMC）在两个分类阶段（第一阶段和第二阶段）中应用，以分析两个众所周知的皮肤癌数据集，防止人们在诊断疾病时做出过于自信的决定。我们最终解决方案的准确度和F1得分分别为88.95%和89.00%（第一个数据集），90.96%和91.00%（第二个数据集）。我们的研究结果表明，所提出的TWDBDL模型可以有效地用于医学图像分析的不同阶段。
Accurate automated medical image recognition, including classification and segmentation, is one of the most challenging tasks in medical image analysis. Recently, deep learning methods have achieved remarkable success in medical image classification and segmentation, clearly becoming the state-of-the-art methods. However, most of these methods are unable to provide uncertainty quantification (UQ) for their output, often being overconfident, which can lead to disastrous consequences. Bayesian Deep Learning (BDL) methods can be used to quantify uncertainty of traditional deep learning methods, and thus address this issue. We apply three uncertainty quantification methods to deal with uncertainty during skin cancer image classification. They are as follows: Monte Carlo (MC) dropout, Ensemble MC (EMC) dropout and Deep Ensemble (DE). To further resolve the remaining uncertainty after applying the MC, EMC and DE methods, we describe a novel hybrid dynamic BDL model, taking into account uncertainty, based on the Three-Way Decision (TWD) theory. The proposed dynamic model enables us to use different UQ methods and different deep neural networks in distinct classification phases. So, the elements of each phase can be adjusted according to the dataset under consideration. In this study, two best UQ methods (i.e., DE and EMC) are applied in two classification phases (the first and second phases) to analyze two well-known skin cancer datasets, preventing one from making overconfident decisions when it comes to diagnosing the disease. The accuracy and the F1-score of our final solution are, respectively, 88.95% and 89.00% for the first dataset, and 90.96% and 91.00% for the second dataset. Our results suggest that the proposed TWDBDL model can be used effectively at different stages of medical image analysis.