The use of deep learning algorithms in the clinical context is hindered by their lack of interpretability. One way of increasing the acceptance of such complex algorithms is by providing explanations of the decisions through the presentation of similar examples. Besides helping to understand model behaviour, the presentation of similar disease-related examples, also supports the decision-making process of the radiologist or clinician under challenging diagnosis scenarios. In this talk, the speaker will discuss and present his work on strategies to provide decisions and case-based explanations in the medical domain. Particularly, he will discuss the work developed in several clinical applications, such as, aesthetic evaluation of breast cancer treatments, melanoma detection in dermoscopic images, and pleural effusion diagnosis in chest x-ray images.
