CPC G06T 11/005 (2013.01) [G06T 11/008 (2013.01); G06V 10/761 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06T 2210/41 (2013.01)] | 11 Claims |
1. A method for training a medical image reconstruction network, being applied to a server, and the method comprising:
performing feature coding extraction on a real image sample to obtain a feature coding vector of the real image sample;
performing, through an image reconstruction network, image reconstruction based on the feature coding vector to obtain a first image, and performing image reconstruction based on a first hidden layer vector of the real image sample to obtain a second image; and
performing, through an image discrimination network, image discrimination on the real image sample, the first image, and the second image to obtain a loss function of the image discrimination network, a structural similarity metric loss function, and a perceptual metric loss function, and optimizing the image reconstruction network according to the loss function of the image discrimination network, the structural similarity metric loss function, and the perceptual metric loss function;
wherein
the step of optimizing the image reconstruction network according to the loss function of the image discrimination network, the structural similarity metric loss function, and the perceptual metric loss function comprises:
performing adversarial training on the image reconstruction network according to the loss function of the image discrimination network, the structural similarity metric loss function, and the perceptual metric loss function, which comprises:
determining a second loss function of the image reconstruction network according to the loss function of the image discrimination network, the structural similarity metric loss function, and the perceptual metric loss function, updating a network parameter of the image reconstruction network by a gradient descent method, and training the image reconstruction network;
wherein, the second loss function is as follows:
LG=−Eze[D(G(ze))]−Ezr[D(G(zr))]+λ1LSSIM(G(zr),xreal)+λ2Lperceptual(G(zr),xreal),
LSSIM=Eze[C(ze)]−Ezr[C(zr)],
![]() and
LD=Eze[D(G(ze))]+Ezr[D(G(zr))]−2Exreal[D(xreal)],
in which, LG represents the second loss function, ze represents the feature coding vector, zr represents the first hidden layer vector, C represents an image coding network, D represents the image discrimination network, G represents the image reconstruction network, E represents a mathematical expectation, LSSIM represents the structural similarity metric loss function, Lperceptual represents the perceptual metric loss function, Xreal represents a real image, λ1 and λ2 represent weight coefficients, Φ represents a Gram matrix, and LD represents the loss function of the image discrimination network.
|