Training method of super-resolution reconstruction network model and scanning image processing method

Abstract

The invention discloses a training method of a super-resolution reconstruction network model and a scanning image processing method. The training method comprises the following steps: acquiring a low-resolution training image and a corresponding high-resolution training image; inputting the low-resolution training image into a super-resolution reconstruction network model to be trained; performing image reconstruction processing on the low-resolution training image through the super-resolution reconstruction network model to obtain a super-resolution training image corresponding to the low-resolution training image; calculating a first loss between the super-resolution training image and the high-resolution training image; recognizing an attention region from the super-resolution training image and recognizing the same attention region from the high-resolution training image, and calculating a second loss between the super-resolution training image and the high-resolution training image of the recognized attention region; and training the super-resolution reconstruction network model according to the first loss and the second loss. According to the invention, image detail recovery can be flexibly selected, and the recovery effect of the image attention region is obviously improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a training method for a super-resolution reconstruction network model and a scanning image processing method. Background technique [0002] Morphological magnetic resonance (MR) analysis is an important means for diagnosing brain diseases and studying brain development in the field of neuroimaging. Low-resolution images limit the field of view and provide limited pathological information; high-resolution images mean that the image has a high pixel density and can provide more details, such as: anatomical information, physiological information, and functional metabolic information. If high-resolution images can be provided, it can greatly help doctors to make a correct diagnosis, and can also improve the performance of computer-aided diagnosis. [0003] Modern medical imaging relies on high-tech equipment—X-ray machines, CT (Computed Tomography), MR, etc. Although the qual...

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to overcome the defect that the method based on neural network learning in the prior art cannot be effectively applied to the restoration and reconstruction of medical images, and provide a training method for super-resolution reconstruction network model, scanning image processing Methods, electronic devices and computer readable media

Images