Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable machine learning, in particular PIP-Net, for automated diagnosis support on real-world medical imaging data. PIP-Net learns human-understandable prototypical image parts and we evaluate its accuracy and interpretability for fracture detection and skin cancer diagnosis. We find that PIP-Net's decision making process is in line with medical classification standards, while only provided with image-level class labels. Because of PIP-Net's unsupervised pretraining of prototypes, data quality problems such as undesired text in an X-ray or labelling errors can be easily identified. Additionally, we are the first to show that humans can manually correct the reasoning of PIP-Net by directly disabling undesired prototypes. We conclude that part-prototype models are promising for medical applications due to their interpretability and potential for advanced model debugging.
@article{arxiv.2307.10404,
title = {Interpreting and Correcting Medical Image Classification with PIP-Net},
author = {Meike Nauta and Johannes H. Hegeman and Jeroen Geerdink and Jörg Schlötterer and Maurice van Keulen and Christin Seifert},
journal= {arXiv preprint arXiv:2307.10404},
year = {2023}
}
Comments
Accepted to the International Workshop on Explainable and Interpretable Machine Learning (XI-ML), co-located with ECAI 2023