Name
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. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/978-3-030-32248-9_52 | Lecture Notes in Computer Science |
Keywords | DocType | Volume |
Whole brain segmentation,CNN,Ensemble learning,Transfer learning,Multiscale framework | Journal | 11766 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.35 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Pierrick Coupé | 1 | 1 | 0.35 |
| Boris Mansencal | 2 | 60 | 10.90 |
| Michaël Clément | 3 | 1 | 0.35 |
| Rémi Giraud | 4 | 1 | 0.35 |
| Baudouin Denis de Senneville | 5 | 22 | 8.12 |
| Vinh-Thong Ta | 6 | 242 | 20.48 |
| Vincent Lepetit | 7 | 6178 | 306.48 |
| José V. Manjón | 8 | 1 | 0.35 |