IEEE Trans Med Imaging. 2021 Feb;40(2):712-721. doi: 10.1109/TMI.2020.3035555. Epub 2021 Feb 2.
Developing a Deep Convolutional Neural Network (DCNN) is a challenging task that involves deep learning with significant effort required to configure the network topology. The design of a 3D DCNN not only requires a good complicated structure but also a considerable number of appropriate parameters to run effectively. Evolutionary computation is an effective approach that can find an optimum network structure and/or its parameters automatically. Note that the Neuroevolution approach is computationally costly, even for developing 2D networks. As it is expected that it will require even more massive computation to develop 3D Neuroevolutionary networks, this research topic has not been investigated until now. In this article, in addition to developing 3D networks, we investigate the possibility of using 2D images and 2D Neuroevolutionary networks to develop 3D networks for 3D volume segmentation. In doing so, we propose to first establish new evolutionary 2D deep networks for medical image segmentation and then convert the 2D networks to 3D networks in order to obtain optimal evolutionary 3D deep convolutional neural networks. The proposed approach results in a massive saving in computational and processing time to develop 3D networks, while achieved high accuracy for 3D medical image segmentation of nine various datasets.
开发深度卷积神经网络（DCNN）是一项具有挑战性的任务，需要进行深度学习，并需要大量的努力来配置网络拓扑结构。设计 3D DCNN 不仅需要良好的复杂结构，还需要相当数量的适当参数才能有效地运行。进化计算是一种有效的方法，可以自动找到最优的网络结构和/或其参数。需要注意的是，神经进化方法的计算成本很高，即使对于开发 2D 网络也是如此。由于预计开发 3D 神经进化网络将需要更多的大规模计算，因此到目前为止，这个研究课题还没有被研究过。在本文中，除了开发 3D 网络外，我们还研究了使用 2D 图像和 2D 神经进化网络来开发用于 3D 体积分割的 3D 网络的可能性。为此，我们建议首先为医学图像分割建立新的进化 2D 深度网络，然后将 2D 网络转换为 3D 网络，以获得最佳的进化 3D 深度卷积神经网络。所提出的方法在开发 3D 网络时可以节省大量的计算和处理时间，同时在九个不同数据集的 3D 医学图像分割中实现了高精度。
