Explainable deep learning models in medical image analysis
It tackles the problem of limited clinical adoption of deep learning due to lack of interpretability for medical professionals, but is incremental as it reviews existing methods rather than introducing new ones.
The paper reviews the application of explainable deep learning models in medical image analysis to address the black-box nature that restricts clinical use, discussing approaches, challenges, and research gaps from a practical standpoint.
Deep learning methods have been very effective for a variety of medical diagnostic tasks and has even beaten human experts on some of those. However, the black-box nature of the algorithms has restricted clinical use. Recent explainability studies aim to show the features that influence the decision of a model the most. The majority of literature reviews of this area have focused on taxonomy, ethics, and the need for explanations. A review of the current applications of explainable deep learning for different medical imaging tasks is presented here. The various approaches, challenges for clinical deployment, and the areas requiring further research are discussed here from a practical standpoint of a deep learning researcher designing a system for the clinical end-users.