Meeting Banner
Abstract #0248

An open-source platform for image simulation, denoising, and super-resolution for point-of-care MRI devices

Mathieu Mach1 and Andrew Webb1
1LUMC, Leiden, Netherlands

Synopsis

Keywords: Software Tools, Low-Field MRI, Simulation, denoising, super-resolution

Motivation: Low-field MRI is increasingly being applied in lower- and middle-income countries, but due to limited resources, training is scare.

Goal(s): Provide an open-source plateform for simulation, teaching, and a denoising and super-resolution pieline of low-field MRI images.

Approach: Using 3D maps of relaxation times, proton density, B0 and low-field system-specific parameters, such as limited gradient linearity, simulation of low-field images are created. Application of bm4d denoising and AI super-resolution on low-field images is additionally proposed.

Results: We provide an open-source graphical interface that can simulate and generate multiple sequences of low-field MRI, and a denoised and super-resolution pipeline increasing low-field image enhancement.

Impact: This study provides a simple open-source python platform to simulate point-of-care low-field MRI images, reflecting specific system-specific parameters for teaching purposes, and a fast advanced denoising and AI-based super-resolution pipeline for low-field images.

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.

Click here for more information on becoming a member.

Keywords