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

Text 978-3-030-32248-9_35.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (3MB)

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.

Interest & Impact

Downloads

1 since deposited on 17 Dec 2019
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item