Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations

no code implementations • 29 Sep 2020 • Antoine Pirovano, Hippolyte Heuberger, Sylvain Berlemont, Saïd Ladjal, Isabelle Bloch

We formalize the design of WSI classification architectures and propose a piece-wise interpretability approach, relying on gradient-based methods, feature visualization and multiple instance learning context.

Classification General Classification +2

Regression Constraint for an Explainable Cervical Cancer Classifier

no code implementations • 7 Aug 2019 • Antoine Pirovano, Leandro G. Almeida, Said Ladjal

This article adresses the problem of automatic squamous cells classification for cervical cancer screening using Deep Learning methods.

Classification General Classification +1