Aim 3: Posterior Sampling and Uncertainty
October 24, 2023
Measurement Model
y \sim \text{Poission}(I_0~e^{-Ax})
To compare different sampling methods in terms of uncertainty as a function of:
Dose (i.e. \(I_0\))\(\quad\quad\) and \(\quad\quad\) Number of views
Preliminary Results
Baseline methods:
1. FBP
2. FBP + U-net with quantile regression (in progress)
Non-linear DPS + {Poisson, Gaussian} Measurement:
- Fixed DPS step @ 0.3
- 20 validation images
- 120 samples per image to compute uncertainty
- 500 steps (\(\approx\) 3 mins / 12 parallel samples)
Trying to reduce to 200 steps with DDIM
Preliminary Results
FBP
FBP
poisson
gaussian
\(I_0 = 4096\)
\(I_0 = 512\)
\(I_0 = 128\)
Preliminary Results
FBP
FBP
poisson
gaussian
\(I_0 = 4096\)
\(I_0 = 512\)
\(I_0 = 128\)
Preliminary Results
[10/24/23] Aim 3: Posterior Sampling and Uncertainty
By Jacopo Teneggi
