Reconstruction of a noisier sinogram gives the same image. #1404
-
|
Hi, I'm doing PET simulation with SimSET. I've simulated two PET images, one with 300s of time acqusition and another one with 75s (25%). Altough the sinogram of the 75s image is noisier then the one of 300s, when I visualize both images with a viwer (MRICro) the images look the same. In addition, the SNR (Signar-to-Noise Ratio) is practically the same for both images. Does someone faced something similar? Sorry, if the reason if something trivial for you. You can find the sinograms, reconstructed images and OSMAPOSL parameter file here. Thanks in advance. |
Beta Was this translation helpful? Give feedback.
Replies: 3 comments 3 replies
-
|
Hi, |
Beta Was this translation helpful? Give feedback.
-
|
Here you have the detected photons (W) and the simulated decays (N_decays) in M (just look to 75s and 300s ignore the rest): |
Beta Was this translation helpful? Give feedback.
-
|
I can see that you are using a big zoom in the parfile, maybe that is acting a bit like a filter. I would try with zoom =1. Also 7M events it still quite a good number. |
Beta Was this translation helpful? Give feedback.
-
|
I haven't checked anything, but just a note that of course for initial iterations, noise isn't a big issue. You would see more differences at late iteration number. |
Beta Was this translation helpful? Give feedback.
-
|
Final note on this, depending on SimSET parameters, you might be using variance reduction, in which case SimSET will do its best to generate sinogram wiht much less noise than you expect from the number of counts.. |
Beta Was this translation helpful? Give feedback.
-
|
Totally, in addition, a big zoom was also contributing. |
Beta Was this translation helpful? Give feedback.
Final note on this, depending on SimSET parameters, you might be using variance reduction, in which case SimSET will do its best to generate sinogram wiht much less noise than you expect from the number of counts..