AI Paper Atlas

Research map / Image generation / Image restoration

Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior

Tatsuya Yokota, Kazuya Kawai, Muneyuki Sakata, Yuichi Kimura, Hidekata Hontani

ICCV 2019 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 63 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add more parallel U-Nets (1 to 5) in the deep image prior (ablation)DIP PET reconstruction · Noise-free phantom sinogramSNR (dB): 28.7 -> 37.3Improved
use NMF with DIP instead of TV regularizationdynamic PET reconstruction · Brain phantom PET image, 20 dBSNR (dB): 14.84 -> 18.96Improved
use NMF with DIP instead of TV regularizationdynamic PET reconstruction · Brain phantom PET image, 10 dBSNR (dB): 3.07 -> 6.21Improved
use NMF with DIP instead of EMdynamic PET reconstruction · Brain phantom PET image, 30 dBSNR (dB): 3.89 -> 24.62Improved
use NMF with DIP instead of EMdynamic PET reconstruction · Brain phantom PET image, noise-freeSNR (dB): 29.43 -> 26.44Hurt
use NMF with DIP instead of TVdynamic PET reconstruction · Brain phantom PET image, noise-freeSNR (dB): 22.22 -> 26.44Improved
use NMF with DIP instead of TVdynamic PET reconstruction · Brain phantom sinogram, noise-freeSNR (dB): 44.58 -> 40.41Hurt
use NMF with DIP instead of TVdynamic PET reconstruction · Brain phantom sinogram, 20 dBSNR (dB): 29.51 -> 34.76Improved
use NMF with DIP instead of FBPdynamic PET reconstruction · Brain phantom PET image, 20 dBSNR (dB): 0.85 -> 18.96Improved
run DIP optimization to 20000 iterations instead of stopping at 5000 (ablation)NMF + DIP · Brain phantom, 20 dB noisy sinogramreconstruction accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy