Generative adversarial network
Generative adversarial network has been studied in 1 paper since 2023: 1 observational study in people. The newest paper, Aug 17, 2023: “Generative Adversarial Network-Enhanced Ultra-Low-Dose [¹⁸F]-PI-2620 τ PET/MRI in Aging and Neurodegenerative Populations”.
1 paper studies it2 findingsUpdated
“when focusing on the healthy-but-amyloid-positive population (with relatively lower τ uptake), this bias was reduced in the enhanced ultra-low-dose images.”
None of its findings points the other way.
- 1 lab in 1 country
- Funders: Alzheimer's Association and 8 more
- Humans1
What did studies of Generative adversarial network find?
2Studies of Generative adversarial network measured 2 outcomes; the most studied are diagnostic image quality (1 study) and underestimation of regional standard uptake value ratios (1).
Diagnostic image quality
upin humans1
1 study
Diagnostic image quality
upin humans1
Generative adversarial network improves diagnostic image quality in humans.
“The clinical readings of deep learning-enhanced ultra-low-dose τ PET images were consistent with those performed with full-dose imaging”
Humansbrainn = 44
AJNR. American journal of neuroradiology
Underestimation of regional standard uptake value ratios
downin humans1
1 study
Underestimation of regional standard uptake value ratios
downin humans1
Generative adversarial network decreases underestimation of regional standard uptake value ratios in humans.
“when focusing on the healthy-but-amyloid-positive population (with relatively lower τ uptake), this bias was reduced in the enhanced ultra-low-dose images.”
Humanshealthy-but-amyloid-positive populationbrainn = 44
AJNR. American journal of neuroradiology
More on Underestimation of regional standard uptake value ratios