Keywords: Machine Learning/Artificial Intelligence, Low-Field MRI, Liver MRI; 0.55T MRI; Deep Learning; Diagnostic performance
Motivation: MRI is crucial for diagnosing liver lesions. Improved MRI tools, such as 0.55T MRI with deep learning (DL) reconstruction, are anticipated to be applied and validated.
Goal(s): We aims to compare the image quality and diagnostic performance with/without DL at 0.55T and 1.5T MRI for liver lesions.
Approach: We prospectively collected MRI data from 12 patients, non-contrast enhancement at 0.55T with/without using DL and at 1.5T without using DL-based reconstruction, using enhanced 1.5T scans as the reference standard.
Results: 0.55T-DL images demonstrated Signal-to-Noise Ratio (SNR) and subjective ratings comparable to or better than those of 1.5T-nonDL, with no significant difference in diagnostic performance.
Impact: Fast 0.55T-DL MRI can enhance the detection and diagnosis of focal liver lesions in the upper abdomen.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords