scikit-image/scikit-image

Image Processing SciKit (Toolbox for SciPy)

Curtis Rueden

@ctrueden

@ewuramaminka Is this image all zeroes?

Nevermind, I see that it is not.

@ewuramaminka I got it working by opening the image through ImageJ using pyimagej. :-)

Curtis Rueden

@ctrueden

I will post a gist shortly.

Curtis Rueden

@ctrueden

https://gist.github.com/ctrueden/cfd4b42c49767b55b2d351c8b886bedf

This gets you a numpy array from your NIFTI data, which is presumably what you want? Then you can analyze it with skimage (and/or ImageJ) as per usual.

Curtis Rueden

@ctrueden

@ewuramaminka I checked your code and saw you using SimpleITK. Is that working? If so, you could also stick with that.

You mention nibabel above… your error suggests to me the object you get back isn’t an numpy array, but a Nifti1Image object. There is probably a function you can call on it that will give you a numpy array? Sorry, I don’t know that library.

E | M

@ewuramaminka

@ctrueden i realised you plotted one slice ?

Curtis Rueden

@ctrueden

Yeah, there might be a bug with converting the whole 3D thing to numpy at once. As a workaround, it can be converted slice by slice.

But it sounds like you have other/better ways of getting the data into Python already. Particularly nibabel which looks pretty tailored to your needs?

It’s just a matter of getting the pixels as a numpy array, right?

E | M

@ewuramaminka

nibabel doesnt even let me create the histograms i want

my current need is to use threshold_otsu to threshold my nifty .. if u could please try that

using simple ITK

Curtis Rueden

@ctrueden

It looks like you need to write:

import nibabel as nib
img = nib.load(filename)
data = img.get_fdata()

and then type(data) will be numpy.ndarray instead of Nifti1Image. And you can compute stuff on the data. Does that help?

https://nipy.org/nibabel/gettingstarted.html

E | M

@ewuramaminka

ok i just tried

i still got this 'AttributeError: 'Nifti1Image' object has no attribute 'get_fdata'

Curtis Rueden

@ctrueden

Which version of nibabel?

We can check the source code.

From the changelog: it looks like the get_fdata was added in version 2.2? Are you using an older version? If so, try upgrading.

Gotta run to a meeting. Good luck.

E | M

@ewuramaminka

2.0.2

nibabel ver - 2.0.2

Curtis Rueden

@ctrueden

See if you can update to 2.2 or newer.

E | M

@ewuramaminka

I finally got stik to load it

Thanks very much

E | M

@ewuramaminka

can anyone help with this ? https://stackoverflow.com/questions/55120404/threshold-otsu-attributeerror-axessubplot-object-has-no-attribute-ravel

Dr .Muhammad Anjum Iqbal

@DrMuhammadAnju1_twitter

Hi i DO NOT KNOW , it is proper platform about my problem ! but if any body knows . please let me know . my question is "to get R in python for window "

Mark Harfouche

@hmaarrfk

Mixing languages is hard.

Hi everyone; we're going to try something new for the chat forum. Please direct your browsers to:

https://skimage.zulipchat.com

(or download the app)

We'll try this forum for a few weeks to see how it goes!

E | M

@ewuramaminka

I have dicom files to auto segment using atlas and CNN approach. I’m looking to measure correspondence between these automatic contours and manual contours created by experts. Kindly advise what techniques are best

-Hausdoff distance
-structural similarity index (SSIM)
-Bidirectional local distance measurement (BLD)
-Mean square errors (MSE)
-Dice similarity coefficient
-Distance transforms

Please advise if there are any I haven’t listed and which ones are best for the operation I want to carry out.

Vishesh Mangla

@XtremeGood

someone here?

E | M

@ewuramaminka

im wondering.. nobody replied to my question

Josh Moore

@joshmoore

Perhaps try on https://forum.image.sc ?

Kira Evans

@kne42

the scikit-image devs have switched to using zulip and no longer monitor this channel

tonyVeco

@tonyVeco

Hi everyone!!

Mark Harfouche

@hmaarrfk

Hi everyone; we're going to try something new for the chat forum. Please direct your browsers to:

https://skimage.zulipchat.com

(or download the app)

We'll try this forum for a few weeks to see how it goes!

tonyVeco

@tonyVeco

ok, so I could submit my question there ;)

Andrew Schaub

@drewschaub

Http://scikit-image.org/docs/0.7.0/api/skimage.feature.peak.htm goes to wrong url if banner is clicked, scikits-image.org. I know its an older version, but i also noticed the banner is edited to say scikits-image and not scikit

Andrew Schaub

@drewschaub

https://scikit-image.org/docs/0.7.0/api/skimage.feature.peak.html

Mark Harfouche

@hmaarrfk

Hi Andrew, Thanks can you please raise an issue on the repo?

Not to ignore your message, but I want this zulip chat message to be the first one people see

Hi everyone; we're going to try something new for the chat forum. Please direct your browsers to:
https://skimage.zulipchat.com
(or download the app)
We'll try this forum for a few weeks to see how it goes!

Andrew Schaub

@drewschaub

will do! Ill switch to the other chatroom as well.

Mark Harfouche

@hmaarrfk

Andrew Chalmers

@chalmersgit

Looking at the SSIM metric, does anyone know much about its parameters? Specifically, I've seen that the default window size = 11 is recommended. But to me, this seems like this variable should be dependent on the resolution of the image. Anyone have any thoughts on this?

Andrew Chalmers

@chalmersgit

Just looking at the original ssim paper, they use ~768x512 resolution images. My intuition is to use this as a way of scaling the window size. That is, using the target resolution against the 768x512 as a ratio to scale the window size lower or higher resolution images appropriately.

Andrew Chalmers

@chalmersgit

Oh i see that you are trying to use zulipchat, ill check it out

Where communities thrive

People

Repo info

Activity