Towards Privacy-preserving Explanations in Medical Image Analysis
arXiv:2107.09652
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.
arXiv comment7 pages, 5 figures, accepted at Workshop on Interpretable ML in Healthcare at ICML2021
References in corpus (6)
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
- Assessment of iris recognition reliability for eyes affected by ocular pathologies
- Implications of Ocular Pathologies for Iris Recognition Reliability
- Real or Not Real, that is the Question