AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation

Pierrick Coupé, Boris Mansencal, Michaël Clément, Rémi Giraud, Baudouin Denis de Senneville, Vinh-Thong Ta, Vincent Lepetit, José V Manjon

Research output: Contribution to journalArticleResearch

Abstract

Whole brain segmentation 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 global 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 and reaching a consensus quickly. 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. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28% in terms of the Dice metric, patch-based joint label fusion by 15% and SLANT-27 by 10%. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.
Subjects: Image and Video Processing (eess. IV); Computer Vision and Pattern Recognition (cs. CV); Machine Learning (cs. LG); Neurons and Cognition (q-bio. NC)
Original languageEnglish
Number of pages8
JournalarXiv.org e-Print archive
Publication statusPublished - 2019
Externally publishedYes

Fingerprint

Magnetic resonance imaging
Brain
Decision making
Labels
Processing
Convolution
Computer vision
Neurons
Pattern recognition
Learning systems
Fusion reactions
Neural networks
Testing
Deep learning

Cite this

Coupé, P., Mansencal, B., Clément, M., Giraud, R., de Senneville, B. D., Ta, V-T., ... V Manjon, J. (2019). AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation. arXiv.org e-Print archive.

AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation. / Coupé, Pierrick; Mansencal, Boris; Clément, Michaël ; Giraud, Rémi ; de Senneville, Baudouin Denis; Ta, Vinh-Thong; Lepetit, Vincent; V Manjon, José .

In: arXiv.org e-Print archive, 2019.

Research output: Contribution to journalArticleResearch

Coupé, P, Mansencal, B, Clément, M, Giraud, R, de Senneville, BD, Ta, V-T, Lepetit, V & V Manjon, J 2019, 'AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation' arXiv.org e-Print archive.
Coupé P, Mansencal B, Clément M, Giraud R, de Senneville BD, Ta V-T et al. AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation. arXiv.org e-Print archive. 2019.
Coupé, Pierrick ; Mansencal, Boris ; Clément, Michaël ; Giraud, Rémi ; de Senneville, Baudouin Denis ; Ta, Vinh-Thong ; Lepetit, Vincent ; V Manjon, José . / AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation. In: arXiv.org e-Print archive. 2019.
@article{67b8458b2cd5478bb0c7956fa7175616,
title = "AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation",
abstract = "Whole brain segmentation 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 global 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 and reaching a consensus quickly. 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. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28{\%} in terms of the Dice metric, patch-based joint label fusion by 15{\%} and SLANT-27 by 10{\%}. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.Subjects: Image and Video Processing (eess. IV); Computer Vision and Pattern Recognition (cs. CV); Machine Learning (cs. LG); Neurons and Cognition (q-bio. NC)",
author = "Pierrick Coup{\'e} and Boris Mansencal and Micha{\"e}l Cl{\'e}ment and R{\'e}mi Giraud and {de Senneville}, {Baudouin Denis} and Vinh-Thong Ta and Vincent Lepetit and {V Manjon}, Jos{\'e}",
year = "2019",
language = "English",
journal = "arXiv.org e-Print archive",
publisher = "Cornell University Library",

}

TY - JOUR

T1 - AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation

AU - Coupé, Pierrick

AU - Mansencal, Boris

AU - Clément, Michaël

AU - Giraud, Rémi

AU - de Senneville, Baudouin Denis

AU - Ta, Vinh-Thong

AU - Lepetit, Vincent

AU - V Manjon, José

PY - 2019

Y1 - 2019

N2 - Whole brain segmentation 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 global 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 and reaching a consensus quickly. 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. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28% in terms of the Dice metric, patch-based joint label fusion by 15% and SLANT-27 by 10%. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.Subjects: Image and Video Processing (eess. IV); Computer Vision and Pattern Recognition (cs. CV); Machine Learning (cs. LG); Neurons and Cognition (q-bio. NC)

AB - Whole brain segmentation 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 global 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 and reaching a consensus quickly. 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. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28% in terms of the Dice metric, patch-based joint label fusion by 15% and SLANT-27 by 10%. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.Subjects: Image and Video Processing (eess. IV); Computer Vision and Pattern Recognition (cs. CV); Machine Learning (cs. LG); Neurons and Cognition (q-bio. NC)

M3 - Article

JO - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

ER -