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

Abstract : 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. Our code is publicly available https://github.com/TheoEst/coupling_registration_segmentation.
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

Contributor : Théo Estienne <>
Submitted on : Tuesday, November 19, 2019 - 11:52:48 AM
Last modification on : Friday, January 17, 2020 - 9:50:03 AM


Files produced by the author(s)



Théo Estienne, Maria Vakalopoulou, Stergios Christodoulidis, Enzo Battistella, Marvin Lerousseau, et al.. U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets. MICCAI 2019: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, MICCAI, Oct 2019, Shenzhen, China. pp.310-319, ⟨10.1007/978-3-030-32248-9_35⟩. ⟨hal-02365899v2⟩



Record views


Files downloads