Shreyas Fadnavis1, Joshua Batson2, and Eleftherios Garyfallidis3
1Intelligent Systems Engineering, Indiana University Bloomington, Bloomington, IN, United States, 2Chan Zuckerberg Biohub, San Francisco, CA, United States, 3Indiana University Bloomington, Bloomington, IN, United States
1Intelligent Systems Engineering, Indiana University Bloomington, Bloomington, IN, United States, 2Chan Zuckerberg Biohub, San Francisco, CA, United States, 3Indiana University Bloomington, Bloomington, IN, United States
Patch2Self is the first self-supervised denoiser that uses the fact that noise across different gradient directions in Diffusion MRI is statistically independent. It is a completely automated (no hyperparameters) method that suppresses only noise from various sources.
Explains the flow of Patch2Self Framework. Also depicts the self-supervised loss used in the J-invariant training.
Regressor Comparisons