DIFFUSION MAGNETIC RESONANCE IMAGING USING SPHERICAL NEURAL NETWORKS

摘要

The invention provides a medical imaging system (100, 300). The medical imaging system includes a memory (110) for storing machine-executable instructions (120). The memory also contains an implementation of a trained neural convolution network (122, 122 ', 122 ", 122" ", 122" ""). The trained neural convolution network comprises more than one spherical neural convolution network section (502, 502 '). The trained convolutional neural network is configured to receive diffusion magnetic resonance imaging data (124). The diffusion magnetic resonance imaging data comprise a spherical diffusion section (500, 500 '). The more than one spherical convolutional neural network section is configured to receive the spherical diffusion section. The trained convolutional neural network includes an output layer (508) configured to generate a neural network output (126) in response to inputting the diffusion magnetic resonance imaging data into the trained convolutional neural network. The medical imaging system further includes a processor (104) for controlling the machine-executable instructions. Execution of the machine-executable instructions causes the processor to: receive (200) the diffusion magnetic resonance imaging data; and generating (202) the neural network output by inputting the diffusion magnetic resonance imaging data into the trained convolutional neural network.