Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning
Article
Abdar, Moloud, Samami, Maryam, Mahmoodabad, Sajjad Dehghani, Doan, Thang, Mazoure, Bogdan, Hashemifesharaki, Reza, Liu, Li, Khosravi, Abbas, Acharya, U. Rajendra, Makarenkov, Vladimir and Nahavandi, Saeid. 2021. "Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning." Computers in Biology and Medicine. 135. https://doi.org/10.1016/j.compbiomed.2021.104418
| Article Title | Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning |
|---|---|
| ERA Journal ID | 5040 |
| Article Category | Article |
| Authors | Abdar, Moloud, Samami, Maryam, Mahmoodabad, Sajjad Dehghani, Doan, Thang, Mazoure, Bogdan, Hashemifesharaki, Reza, Liu, Li, Khosravi, Abbas, Acharya, U. Rajendra, Makarenkov, Vladimir and Nahavandi, Saeid |
| Journal Title | Computers in Biology and Medicine |
| Journal Citation | 135 |
| Article Number | 104418 |
| Number of Pages | 17 |
| Year | 2021 |
| Publisher | Elsevier |
| Place of Publication | United Kingdom |
| ISSN | 0010-4825 |
| 1879-0534 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.compbiomed.2021.104418 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/abs/pii/S0010482521002122 |
| Abstract | 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. |
| Keywords | Bayesian deep learning; Medical image classification ; Uncertainty quantification (UQ) ; Deep learning ; Monte Carlo dropout ; Skin cancer |
| ANZSRC Field of Research 2020 | 400306. Computational physiology |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | Deakin University |
| Islamic Azad University, Iran | |
| K. N. Toosi University of Technology, Iran | |
| McGill University, Canada | |
| Mute Hammer, United States | |
| University of Oulu, Finland | |
| Ngee Ann Polytechnic, Singapore | |
| Singapore University of Social Sciences (SUSS), Singapore | |
| Asia University, Taiwan | |
| University of Quebec, Canada |
Permalink -
https://research.usq.edu.au/item/z1v4v/uncertainty-quantification-in-skin-cancer-classification-using-three-way-decision-based-bayesian-deep-learning
Download files
37
total views27
total downloads0
views this month0
downloads this month