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

Kevin Chen, Robel Tesfay, Mary Ellen I. Koran, Jiahong Ouyang, Sara Shams, Tie Liang, Mehdi Khalighi, Elizabeth C. Mormino, Greg ZaharchukProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

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 18 F-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.
BibTeX
@inproceedings{chen2023diagnostic,
  author = {Kevin Chen and Robel Tesfay and Mary Ellen I. Koran and Jiahong Ouyang and Sara Shams and Tie Liang and Mehdi Khalighi and Elizabeth C. Mormino and Greg Zaharchuk},
  title = {{Diagnostic Ultra-low-dose 18F-PI-2620 Tau PET/MRI with Generative Adversarial Network-based Enhancement}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/3871},
}

Loading related content...

Figure