Keywords: Other AI/ML, Machine Learning/Artificial Intelligence, Neuro, Tumors, synthetic contrast-enhanced MR images
Motivation: Contrast-enhanced MR images with gadolinium-based contrast agents is crucial for brain tumor evaluation, but contraindicated in some patients. AI-based synthetic contrast-enhanced MR images offer an alternative, though studies have mainly focused on gliomas.
Goal(s): To generate synthetic contrast-enhanced MR images from noncontrast MR images across various brain tumor types using multi-center datasets.
Approach: A 3D-UNet-based AI model was developed using noncontrast T1-weighted and T2-weighted images as input and contrast-enhanced T1-weighted images as target.
Results: Synthetic contrast-enhanced MR images demonstrated high SSIM and PSNR across various brain tumor types, with significant correlation of tumor contrast-enhanced volume compared to real ones.
Impact: Our study suggests potential clinical applicability of AI-based synthetic contrast-enhanced MR images generated from noncontrast MR images across various brain tumor types, offering a promising alternative for patients unable to receive gadolinium-based contrast agents.
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