GuidedRec: Guiding Ill-Posed Unsupervised Volumetric Recovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915357799743488 |
|---|---|
| author | Cafaro, Alexandre Leroy, Amaury Beldjoudi, Guillaume Maury, Pauline Robert, Charlotte Deutsch, Eric Grégoire, Vincent Lepetit, Vincent Paragios, Nikos |
| author_facet | Cafaro, Alexandre Leroy, Amaury Beldjoudi, Guillaume Maury, Pauline Robert, Charlotte Deutsch, Eric Grégoire, Vincent Lepetit, Vincent Paragios, Nikos |
| contents | We introduce a novel unsupervised approach to reconstructing a 3D volume from only two planar projections that exploits a previous\-ly-captured 3D volume of the patient. Such volume is readily available in many important medical procedures and previous methods already used such a volume. Earlier methods that work by deforming this volume to match the projections typically fail when the number of projections is very low as the alignment becomes underconstrained. We show how to use a generative model of the volume structures to constrain the deformation and obtain a correct estimate. Moreover, our method is not bounded to a specific sensor calibration and can be applied to new calibrations without retraining. We evaluate our approach on a challenging dataset and show it outperforms state-of-the-art methods. As a result, our method could be used in treatment scenarios such as surgery and radiotherapy while drastically reducing patient radiation exposure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11977 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GuidedRec: Guiding Ill-Posed Unsupervised Volumetric Recovery Cafaro, Alexandre Leroy, Amaury Beldjoudi, Guillaume Maury, Pauline Robert, Charlotte Deutsch, Eric Grégoire, Vincent Lepetit, Vincent Paragios, Nikos Computer Vision and Pattern Recognition We introduce a novel unsupervised approach to reconstructing a 3D volume from only two planar projections that exploits a previous\-ly-captured 3D volume of the patient. Such volume is readily available in many important medical procedures and previous methods already used such a volume. Earlier methods that work by deforming this volume to match the projections typically fail when the number of projections is very low as the alignment becomes underconstrained. We show how to use a generative model of the volume structures to constrain the deformation and obtain a correct estimate. Moreover, our method is not bounded to a specific sensor calibration and can be applied to new calibrations without retraining. We evaluate our approach on a challenging dataset and show it outperforms state-of-the-art methods. As a result, our method could be used in treatment scenarios such as surgery and radiotherapy while drastically reducing patient radiation exposure. |
| title | GuidedRec: Guiding Ill-Posed Unsupervised Volumetric Recovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.11977 |