Re: [Insight-users] Re: Preprocessing intensity images

[Tomáš Kazmar]

Also it depends on what kind of intensity changes you have to deal with. If it
were a change due to a opacification/contrast agens than you should consider
using metric insensitive to specific intensity values, such as mutual information.


Regards,

Tomas


# Hi Arne,
# 
# I do not know if it would solve your problem, but have you considered  
# just rescaling the images with the RescaleIntensityImageFilter?
# 
# Regards,
# Xabi
# 
# 
# 
# Arne Hansen <bsd.diverse at gmail.com> ha escrito:
# 
# > Has nobody had experience with these kind of problems before?
# >
# > -Regards
# >
# > 2007/5/8, Arne Hansen <bsd.diverse at gmail.com>:
# >>
# >> Hello.
# >> I have a set of 20 MRI images. I am developing a segmentation method which
# >> is based on intensity distributions off subsamples of all the images. The
# >> problem is that the intensity distribution varies across the images, so I
# >> need to somehow process it so that it becomes standard. I have thought about
# >> just substracting the mean and divide with the standard deviation for each
# >> image to get standardized data, but I cannot see if this will affect the
# >> probability distribution.
# >>
# >> So my question is, how are images normally preprocessed in order to have
# >> corresponding intensities across all images, so that an intensity based
# >> algorithm can work on all the images?
# >>
# >> I hope you know what I mean, otherwise I will gladly try to explain it
# >> again.
# >>
# >> Looking forward to hear from you.
# >>
# >> Best of regards
# >>
# 
# 
# 
# ----------------------------------------------------------------
# Este mensaje ha sido enviado desde https://webmail.unav.es
# 
# _______________________________________________
# Insight-users mailing list
# Insight-users at itk.org
# http://www.itk.org/mailman/listinfo/insight-users
# 
# 
#