--- a +++ b/doc/AssemblyNet.bib @@ -0,0 +1,12 @@ +@article{COUPE2020117026, +title = {AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation}, +journal = {NeuroImage}, +volume = {219}, +pages = {117026}, +year = {2020}, +issn = {1053-8119}, +doi = {https://doi.org/10.1016/j.neuroimage.2020.117026}, +url = {https://www.sciencedirect.com/science/article/pii/S1053811920305127}, +author = {Pierrick Coupé and Boris Mansencal and Michaël Clément and Rémi Giraud and Baudouin {Denis de Senneville} and Vinh-Thong Ta and Vincent Lepetit and José V. Manjon}, +abstract = {Abstract Whole brain segmentation of fine-grained structures using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a single convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called AssemblyNet, made of two “assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions, unseen problem and reaching a relevant consensus. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an “amendment” procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. During our validation, AssemblyNet showed competitive performance compared to state-of-the-art methods such as U-Net, Joint label fusion and SLANT. Moreover, we investigated the scan-rescan consistency and the robustness to disease effects of our method. These experiences demonstrated the reliability of AssemblyNet. Finally, we showed the interest of using semi-supervised learning to improve the performance of our method.} +} \ No newline at end of file