1. Towards Privacy-preserving Explanations in Medical Image Analysis
- Author
-
Montenegro, H., Silva, W., and Cardoso, J. S.
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
The use of Deep Learning in the medical field is hindered by the lack of interpretability. Case-based interpretability strategies can provide intuitive explanations for deep learning models' decisions, thus, enhancing trust. However, the resulting explanations threaten patient privacy, motivating the development of privacy-preserving methods compatible with the specifics of medical data. In this work, we analyze existing privacy-preserving methods and their respective capacity to anonymize medical data while preserving disease-related semantic features. We find that the PPRL-VGAN deep learning method was the best at preserving the disease-related semantic features while guaranteeing a high level of privacy among the compared state-of-the-art methods. Nevertheless, we emphasize the need to improve privacy-preserving methods for medical imaging, as we identified relevant drawbacks in all existing privacy-preserving approaches., Comment: 7 pages, 5 figures, accepted at Workshop on Interpretable ML in Healthcare at ICML2021
- Published
- 2021