CPC G06T 7/0012 (2013.01) [G06T 5/50 (2013.01); G06T 5/70 (2024.01); G06T 5/73 (2024.01); G06T 5/90 (2024.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06T 2207/10116 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20182 (2013.01); G06T 2207/30004 (2013.01); G06T 2207/30168 (2013.01)] | 19 Claims |
1. A method for medical image optimization, comprising:
obtaining an initial image to be processed acquired by a medical scanning device;
determining a quality feature of the initial image;
inputting the initial image and the quality feature into an image processing model, wherein a loss function of the image processing model for training is positively related to a quality weight, and the quality weight being determined based on a sample quality feature of each of a plurality of training samples for the training of the image processing model and wherein the quality weight of the training sample is determined based on a first quality sub-weight corresponding to a first sample quality feature of the training sample and a second quality sub-weight corresponding to a second sample quality feature of the training sample; and
determining an optimized image of the initial image based on an output of the image processing model.
|