AssemblyNet: A large ensemble of CNNs for 3D Whole Brain MRI Segmentation
This work addresses the problem of accurate and reliable 3D brain segmentation for medical imaging applications, representing an incremental improvement over existing ensemble methods.
The paper tackles the challenge of whole brain MRI segmentation with many anatomical labels by proposing AssemblyNet, a large ensemble of CNNs that processes overlapping brain areas using a parliamentary decision-making framework, achieving competitive performance compared to state-of-the-art methods like U-Net, Joint label fusion, and SLANT.
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.