Do black-box neural network models learn clinically relevant features for fracture diagnosis? The answer not only establishes reliability quenches scientific curiosity but also leads to explainable and verbose findings that can assist the radiologists in the final and increase trust. This work identifies the concepts networks use for vertebral fracture diagnosis in CT images. This is achieved by associating concepts to neurons highly correlated with a specific diagnosis in the dataset. The concepts are either associated with neurons by radiologists pre-hoc or are visualized during a specific prediction and left for the user's interpretation. We evaluate which concepts lead to correct diagnosis and which concepts lead to false positives. The proposed frameworks and analysis pave the way for reliable and explainable vertebral fracture diagnosis.
@article{arxiv.2203.16273,
title = {Interpretable Vertebral Fracture Diagnosis},
author = {Paul Engstler and Matthias Keicher and David Schinz and Kristina Mach and Alexandra S. Gersing and Sarah C. Foreman and Sophia S. Goller and Juergen Weissinger and Jon Rischewski and Anna-Sophia Dietrich and Benedikt Wiestler and Jan S. Kirschke and Ashkan Khakzar and Nassir Navab},
journal= {arXiv preprint arXiv:2203.16273},
year = {2022}
}
Comments
Check out the project's webpage for the code and demo: https://github.com/CAMP-eXplain-AI/Interpretable-Vertebral-Fracture-Diagnosis