Meeting Banner
Abstract #3871

Diagnostic Ultra-low-dose 18F-PI-2620 Tau PET/MRI with Generative Adversarial Network-based Enhancement

Kevin T Chen1,2, Robel Tesfay3, Mary Ellen I Koran2, Jiahong Ouyang2, Sara Shams2, Tie Liang2, Mehdi Khalighi2, Elizabeth Mormino2, and Greg Zaharchuk2
1National Taiwan University, Taipei, Taiwan, 2Stanford University, Stanford, CA, United States, 3Meharry Medical College, Nashville, TN, United States

Synopsis

With the focal and lower uptake in tau PET imaging compared to other tracers such as amyloid, we aim to use multimodal simultaneous PET/MR imaging combined with training a generative adversarial network (GAN) to enhance ultra-low-dose 18F-PI-2620 tau PET images. We showed that the deep learning-enhanced images greatly reduced image noise as compared to the ultra-low-dose images, outperformed the ultra-low-dose images metrics-wise, and were able to be read clinically for regional uptake patterns of tau accumulation similarly as the full-dose 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