Exploring Deep Registration Latent Spaces

Théo Estienne, Maria Vakalopoulou, Stergios Christodoulidis, Enzo Battistella, Théophraste Henry, Marvin Lerousseau, Amaury Leroy, Guillaume Chassagnon, Marie-Pierre Revel, Nikos Paragios, Eric Deutsch

MICCAI 2021, workshop on Domain Adaptation and Representation Transfer (DART)

[arxiv]

Abstract: Explainability of deep neural networks is one of the most challenging and interesting problems in the field. In this study, we investigate the topic focusing on the interpretability of deep learning-based registration methods. In particular, with the appropriate model architecture and using a simple linear projection, we decompose the encoding space, generating a new basis, and we empirically show that this basis captures various decomposed anatomically aware geometrical transformations. We perform experiments using two different datasets focusing on lungs and hippocampus MRI. We show that such an approach can decompose the highly convoluted latent spaces of registration pipelines in an orthogonal space with several interesting properties. We hope that this work could shed some light on a better understanding of deep learning-based registration methods.

@inproceedings{estienne2021exploring,
  title={Exploring Deep Registration Latent Spaces},
  author={Estienne, Th{\'e}o and Vakalopoulou, Maria and Christodoulidis, Stergios and Battistella, Enzo and Henry, Th{\'e}ophraste and Lerousseau, Marvin and Leroy, Amaury and Chassagnon, Guillaume and Revel, Marie-Pierre and Paragios, Nikos and others},
  booktitle={Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health: Third MICCAI Workshop, DART 2021, and First MICCAI Workshop, FAIR 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27 and October 1, 2021, Proceedings 3},
  pages={112--122},
  year={2021},
  organization={Springer}
}