Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations
Autor: | Antoine Pirovano, Hippolyte Heuberger, Saïd Ladjal, Sylvain Berlemont, Isabelle Bloch |
---|---|
Přispěvatelé: | Image, Modélisation, Analyse, GEométrie, Synthèse (IMAGES), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Bloch, Isabelle |
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]
FOS: Computer and information sciences Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Context (language use) 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Field (computer science) Machine Learning (cs.LG) [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] 03 medical and health sciences Discriminative model Feature (machine learning) ComputingMilieux_MISCELLANEOUS 030304 developmental biology 0105 earth and related environmental sciences Interpretability 0303 health sciences business.industry Deep learning 3. Good health Visualization Computer-aided diagnosis Artificial intelligence business computer |
Zdroj: | Workshop iMIMIC at MICCAI Workshop iMIMIC at MICCAI, 2020, Lima, Peru. pp.43-53 Interpretable and Annotation-Efficient Learning for Medical Image Computing ISBN: 9783030611651 iMIMIC/MIL3iD/LABELS@MICCAI |
Popis: | Deep learning methods are widely used for medical applications to assist medical doctors in their daily routines. While performances reach expert's level, interpretability (highlight how and what a trained model learned and why it makes a specific decision) is the next important challenge that deep learning methods need to answer to be fully integrated in the medical field. In this paper, we address the question of interpretability in the context of whole slide images (WSI) classification. 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. We aim at explaining how the decision is made based on tile level scoring, how these tile scores are decided and which features are used and relevant for the task. After training two WSI classification architectures on Camelyon-16 WSI dataset, highlighting discriminative features learned, and validating our approach with pathologists, we propose a novel manner of computing interpretability slide-level heat-maps, based on the extracted features, that improves tile-level classification performances by more than 29% for AUC. Comment: 8 pages (references excluded), 3 figures, presented in iMIMIC Workshop at MICCAI 2020 |
Databáze: | OpenAIRE |
Externí odkaz: |