干旱区生态环境知识资源中心(Arid): U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets

Arid

DOI	10.1007/978-3-030-32248-9_35
	U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets
	Estienne, Theo; Vakalopoulou, Maria; Christodoulidis, Stergios; Battistela, Enzo; Lerousseau, Marvin; Carre, Alexandre; Klausner, Guillaume; Sun, Roger; Robert, Charlotte; Mougiakakou, Stavroula; Paragios, Nikos; Deutsch, Eric
通讯作者	Estienne, T (corresponding author), Univ Paris Saclay, Cent Supelec, Lab MICS, F-91190 Gif Sur Yvette, France. ; Estienne, T (corresponding author), Paris Saclay Univ, Paris Sud Univ, INSERM, Mol Radiotherapy,Gustave Roussy,U1030, Villejuif, France.
会议名称	10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
会议日期	OCT 13-17, 2019
会议地点	Shenzhen, PEOPLES R CHINA
英文摘要	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.
英文关键词	Image registration Deformable registration Brain tumor segmentation 3D convolutional neural networks
来源出版物	MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT III
ISSN	0302-9743
EISSN	1611-3349
出版年	2019
卷号	11766
页码	310-319
ISBN	978-3-030-32248-9; 978-3-030-32247-2
出版者	SPRINGER INTERNATIONAL PUBLISHING AG
类型	Proceedings Paper
语种	英语
开放获取类型	Green Submitted
收录类别	CPCI-S
WOS记录号	WOS:000548733600035
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Engineering, Biomedical ; Neuroimaging ; Imaging Science & Photographic Technology
WOS研究方向	Computer Science ; Engineering ; Neurosciences & Neurology ; Imaging Science & Photographic Technology
资源类型	会议论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/370060
作者单位	[Estienne, Theo; Vakalopoulou, Maria; Battistela, Enzo; Lerousseau, Marvin; Sun, Roger] Univ Paris Saclay, Cent Supelec, Lab MICS, F-91190 Gif Sur Yvette, France; [Estienne, Theo; Battistela, Enzo; Lerousseau, Marvin; Carre, Alexandre; Klausner, Guillaume; Sun, Roger; Robert, Charlotte; Deutsch, Eric] Paris Saclay Univ, Paris Sud Univ, INSERM, Mol Radiotherapy,Gustave Roussy,U1030, Villejuif, France; [Christodoulidis, Stergios; Mougiakakou, Stavroula] Univ Bern, ARTORG Ctr Biomed Engn Res, CH-3008 Bern, Switzerland; [Paragios, Nikos] TheraPanacea, Epiniere Sante Cochin, Paris, France
推荐引用方式 GB/T 7714	Estienne, Theo,Vakalopoulou, Maria,Christodoulidis, Stergios,et al. U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets[C]:SPRINGER INTERNATIONAL PUBLISHING AG,2019:310-319.