AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation

TL;DR

AssemblyNet is a novel ensemble of multiple CNNs inspired by parliamentary decision-making, designed to improve 3D whole brain MRI segmentation accuracy, robustness, and semi-supervised learning capabilities.

Contribution

We introduce AssemblyNet, a large ensemble of U-Nets with knowledge sharing and amendment procedures, enhancing brain segmentation performance over existing methods.

Findings

Competitive performance against state-of-the-art methods

High scan-rescan consistency and robustness to disease effects

Improved results with semi-supervised learning

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 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 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. 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.