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 various UQ methods and different deep neural networks in distinct phases. So, the elements of each phase can be adjusted according to the dataset under consideration. In this study, two UQ methods are applied in two phases to analyze two well-known skin datasets, thus preventing one from making overconfident decisions when it comes to diagnosing the disease. The accuracy and the F1-score of the final solution are, respectively, 88.95% and 89.00% for the first considered dataset, and 90.96% and 91.00% for the second considered dataset. Our results suggest that the proposed model has the potential to be used effectively at different stages of medical image analysis.

准确的自动化医学图像识别，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，这些方法中的大多数无法为其输出提供不确定性量化 (UQ)，通常过于自信，这可能导致灾难性的后果。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，从而解决此问题。我们应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。它们如下：Monte Carlo (MC) dropout、Ensemble MC (EMC) dropout 和 Deep Ensemble (DE)。为了进一步解决应用 MC、EMC 和 DE 方法后剩余的不确定性，我们基于三向决策 (TWD) 理论描述了一种新的混合动态 BDL 模型，同时考虑了不确定性。所提出的动态模型使我们能够在不同的阶段使用各种 UQ 方法和不同的深度神经网络。因此，可以根据所考虑的数据集调整每个阶段的元素。在这项研究中，两种 UQ 方法分两个阶段应用来分析两个众所周知的皮肤数据集，从而防止人们在诊断疾病时做出过度自信的决定。最终解决方案的准确率和 F1 分数对于第一个考虑的数据集分别为 88.95% 和 89.00%，对于第二个考虑的数据集分别为 90.96% 和 91.00%。