Oral
in
Workshop: 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH)
Signature Activation: A Sparse Signal View for Holistic Saliency
Jose Tello Ayala · Akl Fahed · Weiwei Pan · Eugene Pomerantsev · Patrick Ellinor · Anthony Philippakis · Finale Doshi-Velez
Keywords: [ Interpretability ] [ Healthcare ] [ model explanation ] [ saliency ]
The adoption of machine learning in healthcare calls for model transparency and explainability. In this work, we introduce Signature Activation, a saliency method that generates holistic and class-agnostic explanations for Convolutional Neural Networks' outputs. We exploit the sparsity of images and give theoretical explanation to justify our methods. We show the potential use of our method in clinical settings through evaluating its efficacy for aiding the detection of lesions in Coronary Angiorams.