U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets

Estienne, Théo; Vakalopoulou, Maria; Christodoulidis, Stergios; Battistela, Enzo; Lerousseau, Marvin; Carre, Alexandre; Klausner, Guillaume; Sun, Roger; Robert, Charlotte; Mougiakakou, Stavroula; Paragios, Nikos; Deutsch, Eric (10 October 2019). U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Lecture Notes in Computer Science: Vol. 11766 (pp. 310-319). Springer, Cham 10.1007/978-3-030-32248-9_35

[img] Text
978-3-030-32248-9_35.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (3MB) | Request a copy

In this study, we propose a 3D deep neural network called U-ReSNet, a joint framework that can accurately register and segment medical volumes. The proposed network learns to automatically generate linear and elastic deformation models, trained by minimizing the mean square error and the local cross correlation similarity metrics. In parallel, a coupled architecture is integrated, seeking to provide segmentation maps for anatomies or tissue patterns using an additional decoder part trained with the dice coefficient metric. U-ReSNet is trained in an end to end fashion, while due to this joint optimization the generated network features are more informative leading to promising results compared to other deep learning-based methods existing in the literature. We evaluated the proposed architecture using the publicly available OASIS 3 dataset, measuring the dice coefficient metric for both registration and segmentation tasks. Our promising results indicate the potentials of our method which is composed from a convolutional architecture that is extremely simple and light in terms of parameters.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research

UniBE Contributor:

Christodoulidis, Stergios, Mougiakakou, Stavroula

Subjects:

600 Technology > 610 Medicine & health
600 Technology > 620 Engineering

Series:

Lecture Notes in Computer Science

Publisher:

Springer, Cham

Language:

English

Submitter:

Stavroula Mougiakakou

Date Deposited:

17 Dec 2019 14:16

Last Modified:

23 May 2023 13:03

Publisher DOI:

10.1007/978-3-030-32248-9_35

Uncontrolled Keywords:

Image registration; Deformable registration; Brain tumor segmentation; 3D convolutional neural networks

BORIS DOI:

10.48350/135260

URI:

https://boris.unibe.ch/id/eprint/135260

Actions (login required)

Edit item Edit item
Provide Feedback