Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning

• Published in: Computers in biology and medicine Vol. 135; p. 104418
• Main Authors: Abdar, Moloud, Samami, Maryam, Dehghani Mahmoodabad, Sajjad, Doan, Thang, Mazoure, Bogdan, Hashemifesharaki, Reza, Liu, Li, Khosravi, Abbas, Acharya, U. Rajendra, Makarenkov, Vladimir, Nahavandi, Saeid
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.08.2021; Elsevier Limited
• Subjects: Algorithms; Artificial neural networks; Automation; Bayesian analysis; Bayesian deep learning; Cancer; Cardiovascular disease; Cervical cancer; Classification; Colonoscopy; Colorectal cancer; Datasets; Decision making; Decision theory; Deep learning; Diabetes; Diabetic retinopathy; Dynamic models; Image analysis; Image classification; Image processing; Image segmentation; Lung cancer; Machine learning; Medical image classification; Medical imaging; Monte Carlo dropout; Neural networks; Object recognition; Phases; Skin cancer; Uncertainty; Uncertainty quantification (UQ); Deep learning; Bayesian deep learning; Monte Carlo dropout; Medical image classification; Uncertainty quantification (UQ); Skin cancer
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.104418

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. •We proposed an uncertainty quantification-based model for skin cancer classification.•We applied three UQ methods: MC dropout, Ensemble MC dropout and DE.•A novel combination of Bayesian Deep Learning (BDL) methods based on three-way decision theory was considered.•Bayesian optimization (BO) was used to tune hyperparameters of BDL methods.•We obtained promising results using the proposed method.