Skip to Main content Skip to Navigation
Journal articles

AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation

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.
Document type :
Journal articles
Complete list of metadata

Cited literature [58 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02930959
Contributor : Pierrick Coupé <>
Submitted on : Friday, September 4, 2020 - 4:43:29 PM
Last modification on : Monday, May 10, 2021 - 5:32:03 PM
Long-term archiving on: : Wednesday, December 2, 2020 - 8:51:35 PM

File

AssemblyNet_NI_HAL.pdf
Files produced by the author(s)

Identifiers

Citation

Pierrick Coupé, Boris Mansencal, Michaël Clément, Rémi Giraud, Baudouin Denis de Senneville, et al.. AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation. NeuroImage, Elsevier, 2020, 219, pp.117026. ⟨10.1016/j.neuroimage.2020.117026⟩. ⟨hal-02930959⟩

Share

Metrics

Record views

90

Files downloads

79