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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-87722-4_11 | DOMAIN ADAPTATION AND REPRESENTATION TRANSFER, AND AFFORDABLE HEALTHCARE AND AI FOR RESOURCE DIVERSE GLOBAL HEALTH (DART 2021) |
Keywords | DocType | Volume |
Deep learning-based medical image registration, Deformable registration, Explainability | Conference | 12968 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Théo Estienne | 1 | 3 | 1.43 |
Maria Vakalopoulou | 2 | 0 | 0.34 |
S Christodoulidis | 3 | 160 | 10.20 |
Enzo Battistella | 4 | 4 | 1.78 |
Théophraste Henry | 5 | 0 | 0.34 |
Marvin Lerousseau | 6 | 3 | 1.76 |
Amaury Leroy | 7 | 0 | 0.34 |
Guillaume Chassagnon | 8 | 0 | 0.34 |
Marie-Pierre Revel | 9 | 0 | 0.34 |
Nikos Paragios | 10 | 0 | 0.34 |
Eric Deutsch | 11 | 0 | 0.34 |