Nuclear magnetic resonance imaging enhancement method and device based on dictionary learning and storage medium

Abstract

The invention discloses a nuclear magnetic resonance imaging enhancement method based on dictionary learning, a computer device and a storage medium, and the method comprises the steps: obtaining original scanning data, an original image and a dictionary, executing a first iteration process for many times, and the like, wherein each first iteration process performs image reconstruction processing according to an optimization target, the optimization target is determined by the original scanning data and a sparse vector in the corresponding first iteration process, and the sparse vector is determined by the dictionary and a to-be-processed image in the corresponding first iteration process. According to the method, the original scanning data and the original image acquired by the nuclear magnetic resonance equipment are acquired, multi-round iteration is performed on the original scanning data and the original image to perform dictionary learning, image enhancement can be performed on the basis of an image processing result of the nuclear magnetic resonance equipment, and the image quality is further improved; therefore, clinical diagnosis and other researches are facilitated. The method is widely applied to the technical field of image processing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for enhancing magnetic resonance imaging based on dictionary learning, a computer device and a storage medium. Background technique [0002] Nuclear magnetic resonance imaging is a biological magnetic spin imaging technology. "Nucleus" refers to the hydrogen nucleus. Magnetic resonance imaging relies on the hydrogen nucleus to detect the distribution of the number of water molecules in the human body to map the internal tissues of the human body. Based on this characteristic of nuclear magnetic resonance, it does not use electromagnetic radiation, has no harm to human organs and tissues, and has good imaging quality, clear images and strong contrast. Therefore, it has replaced traditional medical electronic computer tomography technology once it came out. At the same time, nuclear magnetic resonance technology has also greatly improved the accuracy of doctors' d...

AI Technical Summary

Problems solved by technology

In the prior art, the MRI image is directly acquired by the instrument, and its imaging quality is limited by the performance of the instrument and the equipped algorithm, and it may not be possible to obtain high-quality MRI images. Therefore, it is necessary to perform image enhancement on the MRI images directly acquired by the instrument.

Images