| CPC G06T 7/0012 (2013.01) [G06N 3/04 (2013.01); G06T 5/92 (2024.01); G06T 7/30 (2017.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30096 (2013.01)] | 20 Claims |
|
1. A neural network system for assigning at least one perfusion metric to dynamic contrast-enhanced (DCE) magnetic resonance (MR) images, the DCE MR images obtained from a MR scanner and under a free-breathing protocol, the neural network system comprising:
an input layer configured to receive at least one DCE MR image representative of a first contrast enhancement state and of a first respiratory motion state and at least one further DCE MR image representative of a second contrast enhancement state and of a second respiratory motion state; and
an output layer configured to output at least one perfusion metric based on the at least one DCE MR image and the at least one further DCE MR image,
wherein the neural network system with interconnections between the input layer and the output layer was trained by a plurality of datasets, each of the datasets comprising an instance of the at least one DCE MR image and of the at least one further DCE MR image for the input layer (114) and the at least one perfusion metric for the output layer; and
wherein the neural network comprises a first sub-network and a second sub-network, and wherein the interconnections comprise cross-connection between the first sub-network and the second sub-network at the input layer and/or at least one hidden layer between the input layer and the output layer.
|