NETWORK ARCHITECTURE FOR 3D IMAGE PROCESSING

A mechanism for processing input 3D image data. In a first stage, input 3D image data is processed using one or more neural networks, respectively, to produce one or more modified 3D image data. In a second stage, the input 3D image data and the modified 3D image data are processed using a neural network to produce an output. A neural network that produces modified 3D image data is configured to process slices or sub-volumes of input 3D image data to produce modified 3D image data. 一种用于处理输入3D图像数据的机制。在第一阶段，使用一个或多个神经网络分别处理输入3D图像数据，以产生一个或多个经修改的3D图像数据。在第二阶段，使用神经网络处理输入3D图像数据和经修改的3D图像数据以产生输出。产生经修改的3D图像数据的神经网络被配置为处理输入3D图像数据的切片或子体积以产生经修改的3D图像数据。