US 11,776,679 B2
Methods for risk map prediction in AI-based MRI reconstruction
Morteza Mardani Korani, Santa Clara, CA (US); David Donoho, Stanford, CA (US); John M. Pauly, Stanford, CA (US); and Shreyas S. Vasanawala, Stanford, CA (US)
Assigned to The Board of Trustees of the Leland Stanford Junior University, Stanford, CA (US)
Filed by The Board of Trustees of the Leland Stanford Junior University, Stanford, CA (US)
Filed on Mar. 9, 2021, as Appl. No. 17/196,838.
Claims priority of provisional application 62/987,597, filed on Mar. 10, 2020.
Prior Publication US 2021/0287780 A1, Sep. 16, 2021
Int. Cl. G16H 30/40 (2018.01); G16H 30/20 (2018.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01); G06T 11/00 (2006.01)
CPC G16H 30/40 (2018.01) [G06N 3/08 (2013.01); G06T 7/0012 (2013.01); G06T 11/003 (2013.01); G16H 30/20 (2018.01); G06T 2207/10088 (2013.01)] 2 Claims
OG exemplary drawing
 
1. A method for generating pixel risk maps for diagnostic image reconstruction comprising:
feeding into a trained encoder a short-scan image acquired from a medical imaging scan to generate latent code statistics including the mean μy and variance αy;
selecting random samples z based on the latent code statistics, where the random samples z are sampled from a normal distribution as z˜N(μy,σy2) where N represents a normal distribution function;
feeding the random samples into a trained decoder to generate a pool of reconstructed images;
calculating, for each pixel across the pool of reconstructed images, pixel-wise mean and variance statistics across the pool of reconstructed images;
computing an end-to-end Jacobian of a reconstruction network that is fed with a density-compensated short-scan image, and estimating a risk of each pixel across the pool of reconstructed images, based on a Stein Unbiased Risk Estimator (SURE).