Accelerated magnetic resonance thermometry

Abstract

Systems and methods provide accelerated MR thermometry utilizing prior knowledge about the images to be reconstructed from incomplete k-space data, thereby facilitating accurate reconstruction. In various embodiments, missing data is computationally estimated using a machine learning algorithm such as a neural network, and an image is generated based on iteratively updated estimated missing information.

Description

[0001] Cross References to Related Applications [0002] This application claims U.S. Provisional Application No. 62 / 838,409, filed April 25, 2019; 62 / 931,525, filed November 6, 2019; U.S. Provisional Application No. 62 / 971,449, filed February 7, 2020 priorities and interests. The entire disclosures of all aforementioned documents are incorporated herein by reference. technical field [0003] The present invention relates generally to magnetic resonance (MR) thermometry, and more particularly to methods for accelerating MR thermometry. Background technique [0004] Tissue, such as benign or malignant tumors or blood clots within a patient's skull or other body region, can be treated non-invasively by surgically removing the tissue or by using, for example, thermal ablation. Both are effective in treating some localized disease within the body, but both involve delicate procedures to avoid destroying or damaging otherwise healthy tissue. Surgery may not be appropriate in s...

AI Technical Summary

Problems solved by technology

While reducing the acquisition of k-space data points can improve MR imaging rates, the process of supplementing information about "missing" (or unacquired) k-space data during imaging reconstruction can be cumbersome due to lack of prior knowledge about the image to be reconstructed. Time consuming; thus, increased MR imaging rates suffer

Images