The application of compressed sensing reconstruction algorithms for MRI of glioblastoma

Magnetic resonance imaging has a long examination time, causing additional pain to glioma patients and causing artifacts in the image. In this paper, a combination of compressed sensing and MRI is used. Base pursuit algorithm, matching pursuit algorithm, orthogonal matching pursuit algorithm, stagewise orthogonal matching pursuit algorithm are used to reconstruct the MRI of glioblastoma, and the subjective and objective evaluation of the reconstructed results is carried out by using gray level co-occurrence matrix, peak signal-to-noise ratio and visual image. In this way, the best expression of the image is selected, thus shortening the time of MRI scanning, reducing the pain of the patient and improving the quality of the image.