US 12,475,683 B2
Deep learning-based method for generating 7T magnetic resonance images from 3T magnetic resonance images
Xin Lou, Beijing (CN); Caohui Duan, Beijing (CN); Xiangbing Bian, Beijing (CN); and Jinhao Lyu, Beijing (CN)
Assigned to THE FIRST MEDICAL CENTER OF PLA GENERAL HOSPITAL, Beijing (CN)
Filed by THE FIRST MEDICAL CENTER OF PLA GENERAL HOSPITAL, Beijing (CN)
Filed on Jun. 4, 2025, as Appl. No. 19/228,673.
Application 19/228,673 is a continuation of application No. PCT/CN2023/106952, filed on Jul. 12, 2023.
Claims priority of application No. 202210863235 (CN), filed on Jul. 20, 2022.
Prior Publication US 2025/0299471 A1, Sep. 25, 2025
Int. Cl. G06V 10/764 (2022.01); G06T 3/4053 (2024.01); G06T 11/00 (2006.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/764 (2022.01) [G06T 3/4053 (2013.01); G06T 11/008 (2013.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 1 Claim
OG exemplary drawing
 
1. A deep learning-based method for generating 7T magnetic resonance (MR) images from 3T MR images, comprising the following steps:
Step 1: constructing a training dataset which comprises multiple training sample pairs, each pair including a paired 3T image xi and real 7T image yi, where “i” denotes the index of the training sample pair;
Step 2: constructing a deep learning model which comprises:
a generator, configured to take a 3T image xi as input and output a synthetic 7T image ŷi;
a spatial alignment network (SAN) module, configured to: take the synthetic 7T image ŷi and a real 7T image yi as inputs; compute a displacement field Ø between the synthetic 7T image ŷi and the real 7T image yi; apply a spatial transformation to the synthetic 7T image ŷi based on the displacement field Ø to obtain a spatially aligned synthetic 7T image yi; and
a discriminator, configured to distinguish between synthetic image pairs (xi,yi) and real image pairs (xi,yi);
Step 3: constructing loss functions for the generator and the discriminator of the deep learning model;
Step 4: training the deep learning model using backpropagation and gradient descent, such that: the discriminator maximizes a probability of assigning correct labels to the spatially aligned synthetic 7T image yi and the real 7T image yi that are inputted; and the difference between the synthetic 7T image and the real 7T image is minimized, resulting in a trained deep learning model;
the generator's loss function LG(θ) is defined by the following formula:

OG Complex Work Unit Math
where, | |1 denotes the L1 norm; N is the total number of training sample pairs; D(⋅, θD) represents the discriminator, where ⋅ denotes the input and θD denotes the discriminator's network parameters; α and β are weighting coefficients for the adversarial loss and smoothness loss, respectively; ∇Ø denotes the gradient of the displacement field;
the discriminator's loss function is defined by the following formula:

OG Complex Work Unit Math