From giannividetta at gmail.com Fri Jul 1 06:09:13 2022 From: giannividetta at gmail.com (Giovanni Videtta) Date: Fri, 1 Jul 2022 12:09:13 +0200 Subject: [Neuroimaging] HeaderError Nibabel Message-ID: Good morning. I write to you for technical support regarding the upload of a Trackvis file with Nibabel. A brief premise. Last January 2022 I e-mailed Dr. Ruopeng in order to solve launch problems of Trackvis software on my Mac PC. He shared with me a new build of the software released in December 2021: Trackvis version 0.6.2.1 (Build 2021.12.08). This build was compatible with the latest MacOS system updates (Monterey from 12.1 to 12.4 version). Recently, I performed some segmentations with the new Trackvis build saving them as .trk files. However, using Nibabel, I tried to upload one of them in order to extract the number of streamlines, but I failed. The following message appeared: "*HeaderError: NiBabel only supports versions 1 and 2 of the Trackvis file format*". I repeated the same operation with another .trk file of my old segmentation performed with the previous Trackvis build and I didn't have any problem. Finally, I checked on GitHub the latest updates of Nibabel library ( https://github.com/nipy/nibabel/blob/master/nibabel/streamlines/trk.py) and I noticed that they are made in August 2021. Therefore, is it possible that the Trackvis format of .trk files produced with the new build is not compatible with the Nibabel library tool/s? Thank you for your support and availability. Best wishes, Giovanni Videtta P.S. I attached a snapshot of my Python script to show you what code I am using. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Schermata 2022-07-01 alle 11.53.01.png Type: image/png Size: 485019 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Schermata 2022-07-01 alle 11.53.12.png Type: image/png Size: 418818 bytes Desc: not available URL: From nsh531 at gmail.com Fri Jul 8 05:15:59 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Fri, 8 Jul 2022 12:15:59 +0300 Subject: [Neuroimaging] Nibabel -how to convert nii to jpg? Message-ID: I glad for any help -------------- next part -------------- An HTML attachment was scrubbed... URL: From matthew.brett at gmail.com Fri Jul 8 05:49:44 2022 From: matthew.brett at gmail.com (Matthew Brett) Date: Fri, 8 Jul 2022 10:49:44 +0100 Subject: [Neuroimaging] Nibabel -how to convert nii to jpg? In-Reply-To: References: Message-ID: Hi, ?On Fri, Jul 8, 2022 at 10:16 AM ???? ?????? wrote:? > > I glad for any help > _______________________________________________ As a pointer, you'll need to load the image: import nibabel as nib img = nib.load('my_image.nii') data = img.get_fdata() and then take some 2D slice (assuming, below, that you have a 3D image above): my_slice = data[..., 15] And finally you need to write it out using imagio (pip install imageio): import imageio imageio.imwrite('my_slice.jpg', my_slice) You'll get a warning at that point, about conversion to uint8 - you can either do that conversion yourself, by rescaling the floating point slice to uint8, or try another output format. Cheers, Matthew From christophe at pallier.org Fri Jul 8 06:26:20 2022 From: christophe at pallier.org (Christophe Pallier) Date: Fri, 8 Jul 2022 12:26:20 +0200 Subject: [Neuroimaging] Nibabel -how to convert nii to jpg? In-Reply-To: References: Message-ID: In case you can install it, the nilearn package, which relies on nibabel, offers a variety of functions to display nifti (.nii) files. see https://nilearn.github.io/stable/plotting/index.html -- Christophe Pallier (http://www.pallier.org) INSERM Cognitive Neuroimaging Lab (http://www.unicog.org) On Fri, Jul 8, 2022 at 11:50 AM Matthew Brett wrote: > Hi, > > ?On Fri, Jul 8, 2022 at 10:16 AM ???? ?????? wrote:? > > > > I glad for any help > > _______________________________________________ > > As a pointer, you'll need to load the image: > > import nibabel as nib > img = nib.load('my_image.nii') > data = img.get_fdata() > > and then take some 2D slice (assuming, below, that you have a 3D image > above): > > my_slice = data[..., 15] > > And finally you need to write it out using imagio (pip install imageio): > > import imageio > imageio.imwrite('my_slice.jpg', my_slice) > > You'll get a warning at that point, about conversion to uint8 - you > can either do that conversion yourself, by rescaling the floating > point slice to uint8, or try another output format. > > Cheers, > > Matthew > _______________________________________________ > Neuroimaging mailing list > Neuroimaging at python.org > https://mail.python.org/mailman/listinfo/neuroimaging > -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Fri Jul 8 09:06:09 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Fri, 8 Jul 2022 16:06:09 +0300 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? Message-ID: fullcode: import nilearn.plotting as plot import os,gzip,io import nibabel as nib path="C:/users/administrator/desktop/nii" path2="C:/users/administrator/desktop/nii/out/" for i in os.listdir(path): if(".nii.gz" in i): pass else: if(".nii" in i): img = nib.load(path+"/"+i) data = img.get_fdata() print(data) import imageio X=0 for s in data: import numpy aleph=numpy.array(s,dtype=numpy.int8) X=X+1 plot.plot_img(aleph) imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i +str(X)+'.jpg', s) error: Data given cannot be loaded because it is not compatible with nibabel format -------------- next part -------------- An HTML attachment was scrubbed... URL: From matthew.brett at gmail.com Fri Jul 8 09:26:24 2022 From: matthew.brett at gmail.com (Matthew Brett) Date: Fri, 8 Jul 2022 14:26:24 +0100 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: Hi, ?On Fri, Jul 8, 2022 at 2:05 PM ???? ?????? wrote:? > > fullcode: > > > > import nilearn.plotting as plot > import os,gzip,io > import nibabel as nib > path="C:/users/administrator/desktop/nii" > path2="C:/users/administrator/desktop/nii/out/" > for i in os.listdir(path): > if(".nii.gz" in i): > pass > else: > > if(".nii" in i): > img = nib.load(path+"/"+i) > data = img.get_fdata() > print(data) > import imageio > X=0 > for s in data: > import numpy > aleph=numpy.array(s,dtype=numpy.int8) > X=X+1 > plot.plot_img(aleph) > > imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i+str(X)+'.jpg', s) > > > > > > > error: > Data given cannot be loaded because it is not compatible with nibabel format Honestly - I wouldn't email python-list - this is a neuroimaging question. The obvious debugging step here is to see what "path+"/"+i" is. Is it in fact a filename of a nifti image? Try loading it in some other Nifti reader. If you get stuck, put the file up somewhere where we can get it and try loading it. Cheers, Matthew From nsh531 at gmail.com Fri Jul 8 09:38:57 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Fri, 8 Jul 2022 16:38:57 +0300 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: it's a fullpath to nifti image ??????? ??? ??, 8 ????? 2022 ?-16:27 ??? ?Matthew Brett?? :? > Hi, > > ?On Fri, Jul 8, 2022 at 2:05 PM ???? ?????? wrote:? > > > > fullcode: > > > > > > > > import nilearn.plotting as plot > > import os,gzip,io > > import nibabel as nib > > path="C:/users/administrator/desktop/nii" > > path2="C:/users/administrator/desktop/nii/out/" > > for i in os.listdir(path): > > if(".nii.gz" in i): > > pass > > else: > > > > if(".nii" in i): > > img = nib.load(path+"/"+i) > > data = img.get_fdata() > > print(data) > > import imageio > > X=0 > > for s in data: > > import numpy > > aleph=numpy.array(s,dtype=numpy.int8) > > X=X+1 > > plot.plot_img(aleph) > > > > > imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i+str(X)+'.jpg', > s) > > > > > > > > > > > > > > error: > > Data given cannot be loaded because it is not compatible with nibabel > format > > Honestly - I wouldn't email python-list - this is a neuroimaging question. > > The obvious debugging step here is to see what "path+"/"+i" is. Is it > in fact a filename of a nifti image? Try loading it in some other > Nifti reader. If you get stuck, put the file up somewhere where we > can get it and try loading it. > > Cheers, > > Matthew > _______________________________________________ > Neuroimaging mailing list > Neuroimaging at python.org > https://mail.python.org/mailman/listinfo/neuroimaging > -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From markiewicz at stanford.edu Fri Jul 8 09:40:35 2022 From: markiewicz at stanford.edu (Christopher Markiewicz) Date: Fri, 8 Jul 2022 13:40:35 +0000 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: A lack of traceback makes it difficult to see where the error is occurring, but I believe the issue is that you're passing a numpy array to a nilearn function that expects an image. Get Outlook for Android ________________________________ From: Neuroimaging on behalf of ??? ???? Sent: Friday, July 8, 2022 9:38:57 AM To: Neuroimaging analysis in Python Subject: Re: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? it's a fullpath to nifti image ??????? ??? ??, 8 ????? 2022 ?-16:27 ??? ?Matthew Brett?? ??>:? Hi, ?On Fri, Jul 8, 2022 at 2:05 PM ???? ?????? > wrote:? > > fullcode: > > > > import nilearn.plotting as plot > import os,gzip,io > import nibabel as nib > path="C:/users/administrator/desktop/nii" > path2="C:/users/administrator/desktop/nii/out/" > for i in os.listdir(path): > if(".nii.gz" in i): > pass > else: > > if(".nii" in i): > img = nib.load(path+"/"+i) > data = img.get_fdata() > print(data) > import imageio > X=0 > for s in data: > import numpy > aleph=numpy.array(s,dtype=numpy.int8) > X=X+1 > plot.plot_img(aleph) > > imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i+str(X)+'.jpg', s) > > > > > > > error: > Data given cannot be loaded because it is not compatible with nibabel format Honestly - I wouldn't email python-list - this is a neuroimaging question. The obvious debugging step here is to see what "path+"/"+i" is. Is it in fact a filename of a nifti image? Try loading it in some other Nifti reader. If you get stuck, put the file up somewhere where we can get it and try loading it. Cheers, Matthew _______________________________________________ Neuroimaging mailing list Neuroimaging at python.org https://mail.python.org/mailman/listinfo/neuroimaging -- [https://ci3.googleusercontent.com/mail-sig/AIorK4ykFjL1iagUdlm0jcadJlaq1KyDf5c3YeE3nLFugFyn69aRMAcHd2OKO51XtKIvhzIdbuX81XE] -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Fri Jul 8 10:36:21 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Fri, 8 Jul 2022 17:36:21 +0300 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: HOW TO DO THIS? I'm new in numpy :) ??????? ??? ??, 8 ????? 2022 ?-16:55 ??? ?Christopher Markiewicz?? :? > A lack of traceback makes it difficult to see where the error is > occurring, but I believe the issue is that you're passing a numpy array to > a nilearn function that expects an image. > > Get Outlook for Android > ------------------------------ > *From:* Neuroimaging stanford.edu at python.org> on behalf of ??? ???? > *Sent:* Friday, July 8, 2022 9:38:57 AM > *To:* Neuroimaging analysis in Python > *Subject:* Re: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? > > it's a fullpath to nifti image > > ??????? ??? ??, 8 ????? 2022 ?-16:27 ??? ?Matthew Brett?? matthew.brett at gmail.com??>:? > > Hi, > > ?On Fri, Jul 8, 2022 at 2:05 PM ???? ?????? wrote:? > > > > fullcode: > > > > > > > > import nilearn.plotting as plot > > import os,gzip,io > > import nibabel as nib > > path="C:/users/administrator/desktop/nii" > > path2="C:/users/administrator/desktop/nii/out/" > > for i in os.listdir(path): > > if(".nii.gz" in i): > > pass > > else: > > > > if(".nii" in i): > > img = nib.load(path+"/"+i) > > data = img.get_fdata() > > print(data) > > import imageio > > X=0 > > for s in data: > > import numpy > > aleph=numpy.array(s,dtype=numpy.int8) > > X=X+1 > > plot.plot_img(aleph) > > > > > imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i+str(X)+'.jpg', > s) > > > > > > > > > > > > > > error: > > Data given cannot be loaded because it is not compatible with nibabel > format > > Honestly - I wouldn't email python-list - this is a neuroimaging question. > > The obvious debugging step here is to see what "path+"/"+i" is. Is it > in fact a filename of a nifti image? Try loading it in some other > Nifti reader. If you get stuck, put the file up somewhere where we > can get it and try loading it. > > Cheers, > > Matthew > _______________________________________________ > Neuroimaging mailing list > Neuroimaging at python.org > https://mail.python.org/mailman/listinfo/neuroimaging > > > > -- > > _______________________________________________ > Neuroimaging mailing list > Neuroimaging at python.org > https://mail.python.org/mailman/listinfo/neuroimaging > -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From christophe at pallier.org Fri Jul 8 10:55:54 2022 From: christophe at pallier.org (Christophe Pallier) Date: Fri, 8 Jul 2022 16:55:54 +0200 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: You can pass a filename directly to plot_img (there is no need to use nibabel, numpy, etc. to extract data). Also you can save the figure without imagio, using savefig() from matplotlib or even directly from nilearn (see examples in its doc) On Fri, Jul 8, 2022, 16:35 ??? ???? wrote: > HOW TO DO THIS? > I'm new in numpy :) > > ??????? ??? ??, 8 ????? 2022 ?-16:55 ??? ?Christopher Markiewicz?? markiewicz at stanford.edu??>:? > >> A lack of traceback makes it difficult to see where the error is >> occurring, but I believe the issue is that you're passing a numpy array to >> a nilearn function that expects an image. >> >> Get Outlook for Android >> ------------------------------ >> *From:* Neuroimaging > stanford.edu at python.org> on behalf of ??? ???? >> *Sent:* Friday, July 8, 2022 9:38:57 AM >> *To:* Neuroimaging analysis in Python >> *Subject:* Re: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN >> ERROR????? >> >> it's a fullpath to nifti image >> >> ??????? ??? ??, 8 ????? 2022 ?-16:27 ??? ?Matthew Brett?? > matthew.brett at gmail.com??>:? >> >> Hi, >> >> ?On Fri, Jul 8, 2022 at 2:05 PM ???? ?????? wrote:? >> > >> > fullcode: >> > >> > >> > >> > import nilearn.plotting as plot >> > import os,gzip,io >> > import nibabel as nib >> > path="C:/users/administrator/desktop/nii" >> > path2="C:/users/administrator/desktop/nii/out/" >> > for i in os.listdir(path): >> > if(".nii.gz" in i): >> > pass >> > else: >> > >> > if(".nii" in i): >> > img = nib.load(path+"/"+i) >> > data = img.get_fdata() >> > print(data) >> > import imageio >> > X=0 >> > for s in data: >> > import numpy >> > aleph=numpy.array(s,dtype=numpy.int8) >> > X=X+1 >> > plot.plot_img(aleph) >> > >> > >> imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i+str(X)+'.jpg', >> s) >> > >> > >> > >> > >> > >> > >> > error: >> > Data given cannot be loaded because it is not compatible with nibabel >> format >> >> Honestly - I wouldn't email python-list - this is a neuroimaging question. >> >> The obvious debugging step here is to see what "path+"/"+i" is. Is it >> in fact a filename of a nifti image? Try loading it in some other >> Nifti reader. If you get stuck, put the file up somewhere where we >> can get it and try loading it. >> >> Cheers, >> >> Matthew >> _______________________________________________ >> Neuroimaging mailing list >> Neuroimaging at python.org >> https://mail.python.org/mailman/listinfo/neuroimaging >> >> >> >> -- >> >> _______________________________________________ >> Neuroimaging mailing list >> Neuroimaging at python.org >> https://mail.python.org/mailman/listinfo/neuroimaging >> > > > -- > > _______________________________________________ > Neuroimaging mailing list > Neuroimaging at python.org > https://mail.python.org/mailman/listinfo/neuroimaging > -------------- next part -------------- An HTML attachment was scrubbed... URL: From matthew.brett at gmail.com Fri Jul 8 11:05:51 2022 From: matthew.brett at gmail.com (Matthew Brett) Date: Fri, 8 Jul 2022 16:05:51 +0100 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: Hi, ?On Fri, Jul 8, 2022 at 3:35 PM ???? ?????? wrote:? > > HOW TO DO THIS? > I'm new in numpy :) > > ??????? ??? ??, 8 ????? 2022 ?-16:55 ??? ?Christopher Markiewicz?? :? >> >> A lack of traceback makes it difficult to see where the error is occurring, but I believe the issue is that you're passing a numpy array to a nilearn function that expects an image. >> Chris is right I think - the error probably comes from your line: > plot.plot_img(aleph) `aleph` is an array, but that Nilearn function expects a "Niimg-like object" not an array: https://nilearn.github.io/stable/modules/generated/nilearn.plotting.plot_img.html#nilearn.plotting.plot_img https://nilearn.github.io/dev/manipulating_images/input_output.html But, as a meta-point - I highly recommend this article about asking good questions. In particular - please remember that we are all volunteers, and most of us are very busy - so we very much appreciate it when you show us you've investigated fairly carefully already, and what you've tried: http://catb.org/%7Eesr/faqs/smart-questions.html Cheers, Matthew From nsh531 at gmail.com Fri Jul 8 11:38:59 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Fri, 8 Jul 2022 18:38:59 +0300 Subject: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN ERROR????? In-Reply-To: References: Message-ID: Its cool. I'll try this on sunday ?????? ??? ??, 8 ????? 2022, 17:56, ??? Christophe Pallier ?< christophe at pallier.org>: > You can pass a filename directly to plot_img (there is no need to use > nibabel, numpy, etc. to extract data). > > Also you can save the figure without imagio, using savefig() from > matplotlib or even directly from nilearn (see examples in its doc) > > > > > > > On Fri, Jul 8, 2022, 16:35 ??? ???? wrote: > >> HOW TO DO THIS? >> I'm new in numpy :) >> >> ??????? ??? ??, 8 ????? 2022 ?-16:55 ??? ?Christopher Markiewicz?? > markiewicz at stanford.edu??>:? >> >>> A lack of traceback makes it difficult to see where the error is >>> occurring, but I believe the issue is that you're passing a numpy array to >>> a nilearn function that expects an image. >>> >>> Get Outlook for Android >>> ------------------------------ >>> *From:* Neuroimaging >> stanford.edu at python.org> on behalf of ??? ???? >>> *Sent:* Friday, July 8, 2022 9:38:57 AM >>> *To:* Neuroimaging analysis in Python >>> *Subject:* Re: [Neuroimaging] NILEARN - WHY THIS CODE THROWS AN >>> ERROR????? >>> >>> it's a fullpath to nifti image >>> >>> ??????? ??? ??, 8 ????? 2022 ?-16:27 ??? ?Matthew Brett?? >> matthew.brett at gmail.com??>:? >>> >>> Hi, >>> >>> ?On Fri, Jul 8, 2022 at 2:05 PM ???? ?????? wrote:? >>> > >>> > fullcode: >>> > >>> > >>> > >>> > import nilearn.plotting as plot >>> > import os,gzip,io >>> > import nibabel as nib >>> > path="C:/users/administrator/desktop/nii" >>> > path2="C:/users/administrator/desktop/nii/out/" >>> > for i in os.listdir(path): >>> > if(".nii.gz" in i): >>> > pass >>> > else: >>> > >>> > if(".nii" in i): >>> > img = nib.load(path+"/"+i) >>> > data = img.get_fdata() >>> > print(data) >>> > import imageio >>> > X=0 >>> > for s in data: >>> > import numpy >>> > aleph=numpy.array(s,dtype=numpy.int8) >>> > X=X+1 >>> > plot.plot_img(aleph) >>> > >>> > >>> imageio.imwrite("C:\\users\\administrator\\desktop\\nii\\"+i+str(X)+'.jpg', >>> s) >>> > >>> > >>> > >>> > >>> > >>> > >>> > error: >>> > Data given cannot be loaded because it is not compatible with nibabel >>> format >>> >>> Honestly - I wouldn't email python-list - this is a neuroimaging >>> question. >>> >>> The obvious debugging step here is to see what "path+"/"+i" is. Is it >>> in fact a filename of a nifti image? Try loading it in some other >>> Nifti reader. If you get stuck, put the file up somewhere where we >>> can get it and try loading it. >>> >>> Cheers, >>> >>> Matthew >>> _______________________________________________ >>> Neuroimaging mailing list >>> Neuroimaging at python.org >>> https://mail.python.org/mailman/listinfo/neuroimaging >>> >>> >>> >>> -- >>> >>> _______________________________________________ >>> Neuroimaging mailing list >>> Neuroimaging at python.org >>> https://mail.python.org/mailman/listinfo/neuroimaging >>> >> >> >> -- >> >> _______________________________________________ >> Neuroimaging mailing list >> Neuroimaging at python.org >> https://mail.python.org/mailman/listinfo/neuroimaging >> > _______________________________________________ > Neuroimaging mailing list > Neuroimaging at python.org > https://mail.python.org/mailman/listinfo/neuroimaging > -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Sun Jul 10 06:01:20 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Sun, 10 Jul 2022 13:01:20 +0300 Subject: [Neuroimaging] ml on medical images - keras Message-ID: What's the problem on this code: import os from pickletools import float8, uint8 from PIL import Image import numpy as np import tensorflow as tf from tensorflow import keras from tensorflow.keras import layers inputs=[] for i in os.listdir("c:/inetpub/wwwroot/out"): for j in os.listdir("c:/inetpub/wwwroot/out/"+i+"/"): A=Image.open("c:/inetpub/wwwroot/out/"+i+"/"+j) from matplotlib import pyplot as plt filename = 'image-test' # img = ( filename + '.png' ) x=np.array(A,dtype=np.shape(A)) inputs.append(x) simple_rnn = tf.keras.layers.SimpleRNN(4) #np.int output = simple_rnn(inputs=np.array(inputs,dtype=np.ndarray(260, 730, 4))) # The output has shape `[32, 4]`. simple_rnn = tf.keras.layers.SimpleRNN( 4, return_sequences=True, return_state=True) # whole_sequence_output has shape `[32, 10, 4]`. # final_state has shape `[32, 4]`. whole_sequence_output, final_state = simple_rnn(inputs) -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Sun Jul 10 06:01:52 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Sun, 10 Jul 2022 13:01:52 +0300 Subject: [Neuroimaging] ml on medical images - keras In-Reply-To: References: Message-ID: p.s. all the pictures are in PNG FORMAT ??????? ??? ??, 10 ????? 2022 ?-13:01 ??? ??? ???? :? > What's the problem on this code: > > import os > from pickletools import float8, uint8 > from PIL import Image > > import numpy as np > import tensorflow as tf > from tensorflow import keras > from tensorflow.keras import layers > inputs=[] > for i in os.listdir("c:/inetpub/wwwroot/out"): > for j in os.listdir("c:/inetpub/wwwroot/out/"+i+"/"): > A=Image.open("c:/inetpub/wwwroot/out/"+i+"/"+j) > from matplotlib import pyplot as plt > > filename = 'image-test' > > > # img = ( filename + '.png' ) > x=np.array(A,dtype=np.shape(A)) > inputs.append(x) > > simple_rnn = tf.keras.layers.SimpleRNN(4) > #np.int > output = simple_rnn(inputs=np.array(inputs,dtype=np.ndarray(260, 730, 4))) > # The output has shape `[32, 4]`. > > simple_rnn = tf.keras.layers.SimpleRNN( > 4, return_sequences=True, return_state=True) > > # whole_sequence_output has shape `[32, 10, 4]`. > # final_state has shape `[32, 4]`. > whole_sequence_output, final_state = simple_rnn(inputs) > > -- > > -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From matthew.brett at gmail.com Mon Jul 11 04:56:26 2022 From: matthew.brett at gmail.com (Matthew Brett) Date: Mon, 11 Jul 2022 09:56:26 +0100 Subject: [Neuroimaging] ml on medical images - keras In-Reply-To: References: Message-ID: Hi, ?On Sun, Jul 10, 2022 at 11:02 AM ???? ?????? wrote:? > > p.s. all the pictures are in PNG FORMAT > > ??????? ??? ??, 10 ????? 2022 ?-13:01 ??? ??? ???? :? >> >> What's the problem on this code: >> >> import os >> from pickletools import float8, uint8 >> from PIL import Image >> >> import numpy as np >> import tensorflow as tf >> from tensorflow import keras >> from tensorflow.keras import layers >> inputs=[] >> for i in os.listdir("c:/inetpub/wwwroot/out"): >> for j in os.listdir("c:/inetpub/wwwroot/out/"+i+"/"): >> A=Image.open("c:/inetpub/wwwroot/out/"+i+"/"+j) >> from matplotlib import pyplot as plt >> >> filename = 'image-test' >> >> >> # img = ( filename + '.png' ) >> x=np.array(A,dtype=np.shape(A)) >> inputs.append(x) >> >> simple_rnn = tf.keras.layers.SimpleRNN(4) >> #np.int >> output = simple_rnn(inputs=np.array(inputs,dtype=np.ndarray(260, 730, 4))) # The output has shape `[32, 4]`. >> >> simple_rnn = tf.keras.layers.SimpleRNN( >> 4, return_sequences=True, return_state=True) >> >> # whole_sequence_output has shape `[32, 10, 4]`. >> # final_state has shape `[32, 4]`. >> whole_sequence_output, final_state = simple_rnn(inputs) You don't give an error message I can see - but in any case - it seems to me this is a Tensorflow question, not a Nibabel / Neuroimaging question. You could try asking on a Tensorflow list - but again - for the best chance of a useful answer, please consider following the advice at: http://catb.org/%7Eesr/faqs/smart-questions.html Cheers, Matthew From nsh531 at gmail.com Tue Jul 12 12:36:02 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Tue, 12 Jul 2022 19:36:02 +0300 Subject: [Neuroimaging] What this connectome means? Message-ID: Http://83.229.82.78/out/figure 1.png -------------- next part -------------- An HTML attachment was scrubbed... URL: From milteralp at gmail.com Wed Jul 13 00:14:15 2022 From: milteralp at gmail.com (Melike Ilteralp) Date: Wed, 13 Jul 2022 00:14:15 -0400 Subject: [Neuroimaging] How to fix the rotation change caused by resample_to_output()? Message-ID: Hi all, I am working on a dataset with different voxel sizes, so I need to resample the voxel sizes to (1, 1, 1). I found nibabel.processing.resample_to_output() which accomplishes this job. However, I realized that resampling changes the rotation of some images. Here is a slice from an image that rotates when resampled and its resampled version . Is there any way to make the rotation of the resampled image the same as the original image? Here is what I tried, import nibabel as nib from nibabel.processing import resample_to_output img_nii = nib.load('original.nii.gz') img_resampled_nii = resample_to_output(img_nii, voxel_sizes=(1, 1, 1)) nib.save(img_resampled_nii, 'resampled.nii.gz') You can download `original.nii.gz` from here , Thank you for your support, Melike -------------- next part -------------- An HTML attachment was scrubbed... URL: From markiewicz at stanford.edu Wed Jul 13 10:26:04 2022 From: markiewicz at stanford.edu (Christopher Markiewicz) Date: Wed, 13 Jul 2022 14:26:04 +0000 Subject: [Neuroimaging] How to fix the rotation change caused by resample_to_output()? In-Reply-To: References: Message-ID: I think the problem here is that you have a source image with a bad affine. Simply plotting the middle slice shows a head with the nose pointing directly at one of the edges of the image. However, your affine shows a 2.4 radian rotation around the z axis. When nibabel attempts to reslice to a [[1, 0, 0, tx], [0, 1, 0, ty], [0, 0, 1, tz], [0, 0, 0, 1]] affine, it assumes the source affine correct and creates a data array large enough to contain the bounding box of the original image. The two images are still in alignment and can be viewed on top of each other. That said, you can write something that will keep the original rotations and only update the zooms like so: # Need to calculate a shape. Since we're going to isotropic 1mm, it's just the FoV. new_shape = np.uint8(np.array(img_nii.shape) * np.array(img_nii.header.get_zooms())) new_affine = nib.affines.rescale_affine(img_nii.affine, img_nii.shape, zooms=(1, 1, 1), new_shape=new_shape) img_resampled_nii = nib.processing.resample_from_to(img, (tuple(new_shape), new_aff)) Best, Chris ________________________________ From: Neuroimaging on behalf of Melike Ilteralp Sent: Wednesday, July 13, 2022 00:14 To: neuroimaging at python.org Subject: [Neuroimaging] How to fix the rotation change caused by resample_to_output()? Hi all, I am working on a dataset with different voxel sizes, so I need to resample the voxel sizes to (1, 1, 1). I found nibabel.processing.resample_to_output() which accomplishes this job. However, I realized that resampling changes the rotation of some images. Here is a slice from an image that rotates when resampled and its resampled version. Is there any way to make the rotation of the resampled image the same as the original image? Here is what I tried, import nibabel as nib from nibabel.processing import resample_to_output img_nii = nib.load('original.nii.gz') img_resampled_nii = resample_to_output(img_nii, voxel_sizes=(1, 1, 1)) nib.save(img_resampled_nii, 'resampled.nii.gz') You can download `original.nii.gz` from here, Thank you for your support, Melike -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Wed Jul 13 13:47:18 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Wed, 13 Jul 2022 20:47:18 +0300 Subject: [Neuroimaging] what's the problem?????? Message-ID: CODE: for nii in os.listdir("c:/users/administrator/desktop/nii"): from nilearn import plotting from nilearn import datasets atlas = datasets.fetch_atlas_msdl() # Loading atlas image stored in 'maps' atlas_filename = "C:/Users/Administrator/Desktop/64/64/2mm/maps.nii.gz" # Loading atlas data stored in 'labels' labels = pd.read_csv( "C:/Users/Administrator/Desktop/64/64/labels_64_dictionary.csv") a=labels.to_dict() b=a["Difumo_names"] from nilearn.maskers import NiftiMapsMasker masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True, memory='nilearn_cache', verbose=5) time_series = masker.fit_transform("c:/users/administrator/desktop/nii/" +nii) try: from sklearn.covariance import GraphicalLassoCV except ImportError: # for Scitkit-Learn < v0.20.0 from sklearn.covariance import GraphLassoCV as GraphicalLassoCV estimator = GraphicalLassoCV() estimator.fit(time_series) # Display the covariancec aas={} jsa=0 for i in estimator.covariance_: r=list(a["Difumo_names"].values())[jsa] jsa=jsa+1 a=dict() for x in range(64): g=list(a["Difumo_names"].values())[x] print(aas) t= nilearn.plotting.plot_img(estimator.covariance_, labels=list(a[ "Difumo_names"].values()), figure=(9, 7), vmax=1, vmin=-1, title='Covariance')# The covariance can be found at estimator.covariance_ # The covariance can be found at estimator.covariance_ t2= nilearn.plotting.plot_matrix(estimator.covariance_, labels=list(a[ "Difumo_names"].values()), figure=(9, 7), vmax=1, vmin=-1, title='Covariance') -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Wed Jul 13 14:35:18 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Wed, 13 Jul 2022 21:35:18 +0300 Subject: [Neuroimaging] what's the problem?????? In-Reply-To: References: Message-ID: I want to set dict ?????? ??? ??, 13 ????? 2022, 20:47, ??? ??? ???? ?: > CODE: > > for nii in os.listdir("c:/users/administrator/desktop/nii"): > > from nilearn import plotting > from nilearn import datasets > atlas = datasets.fetch_atlas_msdl() > # Loading atlas image stored in 'maps' > atlas_filename = > "C:/Users/Administrator/Desktop/64/64/2mm/maps.nii.gz" > # Loading atlas data stored in 'labels' > labels = pd.read_csv( > "C:/Users/Administrator/Desktop/64/64/labels_64_dictionary.csv") > a=labels.to_dict() > b=a["Difumo_names"] > from nilearn.maskers import NiftiMapsMasker > masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True, > memory='nilearn_cache', verbose=5) > > time_series = masker.fit_transform( > "c:/users/administrator/desktop/nii/"+nii) > try: > from sklearn.covariance import GraphicalLassoCV > except ImportError: > # for Scitkit-Learn < v0.20.0 > from sklearn.covariance import GraphLassoCV as GraphicalLassoCV > > estimator = GraphicalLassoCV() > estimator.fit(time_series) > # Display the covariancec > aas={} > jsa=0 > for i in estimator.covariance_: > r=list(a["Difumo_names"].values())[jsa] > jsa=jsa+1 > a=dict() > > > for x in range(64): > g=list(a["Difumo_names"].values())[x] > > print(aas) > t= nilearn.plotting.plot_img(estimator.covariance_, labels=list(a[ > "Difumo_names"].values()), > figure=(9, 7), vmax=1, vmin=-1, > title='Covariance')# The covariance can be found > at estimator.covariance_ > > # The covariance can be found at estimator.covariance_ > t2= nilearn.plotting.plot_matrix(estimator.covariance_, labels=list(a > ["Difumo_names"].values()), > figure=(9, 7), vmax=1, vmin=-1, > title='Covariance') > > > > -- > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Thu Jul 14 00:18:34 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Thu, 14 Jul 2022 07:18:34 +0300 Subject: [Neuroimaging] what's the problem?????? In-Reply-To: References: Message-ID: I want to swap indexes of dict ?????? ??? ??, 13 ????? 2022, 21:51, ??? David Welch ?< david.m.welch at gmail.com>: > >> - Describe the research *you did* to try and understand the problem >> *before* you asked the question. >> - Describe the diagnostic steps *you took* to try and pin down the >> problem yourself *before* you asked the question. >> >> > On Wed, Jul 13, 2022 at 1:47 PM David Welch > wrote: > >> From http://catb.org/~esr/faqs/smart-questions.html#beprecise: >> >>> Be precise and informative about your problem >>> >>> - >>> >>> Describe the symptoms of your problem or bug carefully and clearly. >>> - >>> >>> Describe the environment in which it occurs (machine, OS, >>> application, whatever). Provide your vendor's distribution and release >>> level (e.g.: ?Fedora Core 7?, ?Slackware 9.1?, etc.). >>> - >>> >>> Describe the research you did to try and understand the problem >>> before you asked the question. >>> - >>> >>> Describe the diagnostic steps you took to try and pin down the >>> problem yourself before you asked the question. >>> - >>> >>> Describe any possibly relevant recent changes in your computer or >>> software configuration. >>> - >>> >>> If at all possible, provide a way to *reproduce the problem in a >>> controlled environment*. >>> >>> Do the best you can to anticipate the questions a hacker will ask, and >>> answer them in advance in your request for help. >>> >>> Giving hackers the ability to reproduce the problem in a controlled >>> environment is especially important if you are reporting something you >>> think is a bug in code. When you do this, your odds of getting a useful >>> answer and the speed with which you are likely to get that answer both >>> improve tremendously. >>> >>> Simon Tatham has written an excellent essay entitled How to Report Bugs >>> Effectively . I >>> strongly recommend that you read it. >>> >>> >> >> ---------- Forwarded message --------- >> From: ??? ???? >> Date: Wed, Jul 13, 2022 at 1:36 PM >> Subject: Re: [Neuroimaging] what's the problem?????? >> To: Neuroimaging analysis in Python , < >> python-list at python.org> >> >> >> I want to set dict >> >> ?????? ??? ??, 13 ????? 2022, 20:47, ??? ??? ???? ?: >> >>> CODE: >>> >>> for nii in os.listdir("c:/users/administrator/desktop/nii"): >>> >>> from nilearn import plotting >>> from nilearn import datasets >>> atlas = datasets.fetch_atlas_msdl() >>> # Loading atlas image stored in 'maps' >>> atlas_filename = >>> "C:/Users/Administrator/Desktop/64/64/2mm/maps.nii.gz" >>> # Loading atlas data stored in 'labels' >>> labels = pd.read_csv( >>> "C:/Users/Administrator/Desktop/64/64/labels_64_dictionary.csv") >>> a=labels.to_dict() >>> b=a["Difumo_names"] >>> from nilearn.maskers import NiftiMapsMasker >>> masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True, >>> memory='nilearn_cache', verbose=5) >>> >>> time_series = masker.fit_transform( >>> "c:/users/administrator/desktop/nii/"+nii) >>> try: >>> from sklearn.covariance import GraphicalLassoCV >>> except ImportError: >>> # for Scitkit-Learn < v0.20.0 >>> from sklearn.covariance import GraphLassoCV as GraphicalLassoCV >>> >>> estimator = GraphicalLassoCV() >>> estimator.fit(time_series) >>> # Display the covariancec >>> aas={} >>> jsa=0 >>> for i in estimator.covariance_: >>> r=list(a["Difumo_names"].values())[jsa] >>> jsa=jsa+1 >>> a=dict() >>> >>> >>> for x in range(64): >>> g=list(a["Difumo_names"].values())[x] >>> >>> print(aas) >>> t= nilearn.plotting.plot_img(estimator.covariance_, labels=list(a[ >>> "Difumo_names"].values()), >>> figure=(9, 7), vmax=1, vmin=-1, >>> title='Covariance')# The covariance can be >>> found at estimator.covariance_ >>> >>> # The covariance can be found at estimator.covariance_ >>> t2= nilearn.plotting.plot_matrix(estimator.covariance_, labels=list >>> (a["Difumo_names"].values()), >>> figure=(9, 7), vmax=1, vmin=-1, >>> title='Covariance') >>> >>> >>> >>> -- >>> >>> >> _______________________________________________ >> Neuroimaging mailing list >> Neuroimaging at python.org >> https://mail.python.org/mailman/listinfo/neuroimaging >> > -------------- next part -------------- An HTML attachment was scrubbed... URL: From nsh531 at gmail.com Thu Jul 14 01:49:39 2022 From: nsh531 at gmail.com (=?UTF-8?B?16DXqteZINep15jXqNef?=) Date: Thu, 14 Jul 2022 08:49:39 +0300 Subject: [Neuroimaging] what's the problem?????? In-Reply-To: <006601d8973c$65707390$30515ab0$@gmail.com> References: <006601d8973c$65707390$30515ab0$@gmail.com> Message-ID: Instead of numbers, I want to enter as indexes the names of the Index as being in b variable: labels = pd.read_csv( "C:/Users/Administrator/Desktop/64/64/labels_64_dictionary.csv") a=labels.to_dict() b=a["Difumo_names"] ??????? ??? ??, 14 ????? 2022 ?-7:44 ??? :? > Nati, > > I know you think you are communicating. > > ???? >> I want to swap indexes of dict > > When you say SWAP, do you mean replace the index with something else, or > swap the key and value or something entirely else? > > You have not shared an example of what is in your dictionary, but say it > is: > > myDict = {1:"a", 2:"b", 3:"c"} > > invDict = { value:key for key, value in myDict.items() } > > print(myDict) > print(invDict) > > > The above prints out: > > print(myDict) > {1: 'a', 2: 'b', 3: 'c'} > > print(invDict) > {'a': 1, 'b': 2, 'c': 3} > > It obviously generalizes only for dictionaries where all values are > unique. And you can obviously save the results back into the same variable > if you wish. The above comprehension may, of course, not be what you want > as swapping indexes with may not mean anything to us trying > to help. > > Avi (a ???? on my mother's side.) > > > -----Original Message----- > From: Python-list > On Behalf Of ??? ???? > Sent: Thursday, July 14, 2022 12:19 AM > To: David Welch ; Neuroimaging analysis in > Python ; python-list at python.org > Subject: Re: [Neuroimaging] what's the problem?????? > > I want to swap indexes of dict > > ?????? ??? ??, 13 ????? 2022, 21:51, ??? David Welch ?< > david.m.welch at gmail.com>: > > > > >> - Describe the research *you did* to try and understand the problem > >> *before* you asked the question. > >> - Describe the diagnostic steps *you took* to try and pin down the > >> problem yourself *before* you asked the question. > >> > >> > > On Wed, Jul 13, 2022 at 1:47 PM David Welch > > wrote: > > > >> From http://catb.org/~esr/faqs/smart-questions.html#beprecise: > >> > >>> Be precise and informative about your problem > >>> > >>> - > >>> > >>> Describe the symptoms of your problem or bug carefully and clearly. > >>> - > >>> > >>> Describe the environment in which it occurs (machine, OS, > >>> application, whatever). Provide your vendor's distribution and > release > >>> level (e.g.: ?Fedora Core 7?, ?Slackware 9.1?, etc.). > >>> - > >>> > >>> Describe the research you did to try and understand the problem > >>> before you asked the question. > >>> - > >>> > >>> Describe the diagnostic steps you took to try and pin down the > >>> problem yourself before you asked the question. > >>> - > >>> > >>> Describe any possibly relevant recent changes in your computer or > >>> software configuration. > >>> - > >>> > >>> If at all possible, provide a way to *reproduce the problem in a > >>> controlled environment*. > >>> > >>> Do the best you can to anticipate the questions a hacker will ask, > >>> and answer them in advance in your request for help. > >>> > >>> Giving hackers the ability to reproduce the problem in a controlled > >>> environment is especially important if you are reporting something > >>> you think is a bug in code. When you do this, your odds of getting a > >>> useful answer and the speed with which you are likely to get that > >>> answer both improve tremendously. > >>> > >>> Simon Tatham has written an excellent essay entitled How to Report > >>> Bugs Effectively > >>> . I strongly > recommend that you read it. > >>> > >>> > >> > >> ---------- Forwarded message --------- > >> From: ??? ???? > >> Date: Wed, Jul 13, 2022 at 1:36 PM > >> Subject: Re: [Neuroimaging] what's the problem?????? > >> To: Neuroimaging analysis in Python , < > >> python-list at python.org> > >> > >> > >> I want to set dict > >> > >> ?????? ??? ??, 13 ????? 2022, 20:47, ??? ??? ???? ?: > >> > >>> CODE: > >>> > >>> for nii in os.listdir("c:/users/administrator/desktop/nii"): > >>> > >>> from nilearn import plotting > >>> from nilearn import datasets > >>> atlas = datasets.fetch_atlas_msdl() > >>> # Loading atlas image stored in 'maps' > >>> atlas_filename = > >>> "C:/Users/Administrator/Desktop/64/64/2mm/maps.nii.gz" > >>> # Loading atlas data stored in 'labels' > >>> labels = pd.read_csv( > >>> "C:/Users/Administrator/Desktop/64/64/labels_64_dictionary.csv") > >>> a=labels.to_dict() > >>> b=a["Difumo_names"] > >>> from nilearn.maskers import NiftiMapsMasker > >>> masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True, > >>> memory='nilearn_cache', verbose=5) > >>> > >>> time_series = masker.fit_transform( > >>> "c:/users/administrator/desktop/nii/"+nii) > >>> try: > >>> from sklearn.covariance import GraphicalLassoCV > >>> except ImportError: > >>> # for Scitkit-Learn < v0.20.0 > >>> from sklearn.covariance import GraphLassoCV as > >>> GraphicalLassoCV > >>> > >>> estimator = GraphicalLassoCV() > >>> estimator.fit(time_series) > >>> # Display the covariancec > >>> aas={} > >>> jsa=0 > >>> for i in estimator.covariance_: > >>> r=list(a["Difumo_names"].values())[jsa] > >>> jsa=jsa+1 > >>> a=dict() > >>> > >>> > >>> for x in range(64): > >>> g=list(a["Difumo_names"].values())[x] > >>> > >>> print(aas) > >>> t= nilearn.plotting.plot_img(estimator.covariance_, > labels=list(a[ > >>> "Difumo_names"].values()), > >>> figure=(9, 7), vmax=1, vmin=-1, > >>> title='Covariance')# The covariance can be > >>> found at estimator.covariance_ > >>> > >>> # The covariance can be found at estimator.covariance_ > >>> t2= nilearn.plotting.plot_matrix(estimator.covariance_, > >>> labels=list (a["Difumo_names"].values()), > >>> figure=(9, 7), vmax=1, vmin=-1, > >>> title='Covariance') > >>> > >>> > >>> > >>> -- > >>> > >>> > >> _______________________________________________ > >> Neuroimaging mailing list > >> Neuroimaging at python.org > >> https://mail.python.org/mailman/listinfo/neuroimaging > >> > > > -- > https://mail.python.org/mailman/listinfo/python-list > > -- -------------- next part -------------- An HTML attachment was scrubbed... URL: From skycrazer at gmail.com Tue Jul 19 03:49:17 2022 From: skycrazer at gmail.com (Sied Kebir) Date: Tue, 19 Jul 2022 09:49:17 +0200 Subject: [Neuroimaging] NIFTI transformation Message-ID: Hi, I would like to transform a bunch of NIFTI files and their corresponding masks in the following manner: 1. Add Gaussian noise (mean 0, standard deviation as present in the image) 2. Perform random volume changes of the GTV (0%, ? 15%, 15%) 3. Translate (0.0, 0.25, and 0.75 mm) in all three spatial dimensions Could some guide me on how to do this with Nibabel? Appreciate your help! Best regards Sied -------------- next part -------------- An HTML attachment was scrubbed... URL: From matthew.brett at gmail.com Sat Jul 23 05:14:53 2022 From: matthew.brett at gmail.com (Matthew Brett) Date: Sat, 23 Jul 2022 10:14:53 +0100 Subject: [Neuroimaging] Neuroimaging practice and theory course, August/September 2022 In-Reply-To: References: Message-ID: Dear all, This is just to let you know that we are now accepting requests to join our first full version of the Neuroimaging Practice and Theory Course, running over 8 weeks, from 8th August through the end of September 2022. The course teaches reproducible brain imaging analysis, and is for anyone with basic knowledge of Python and the Numpy array library. We (the Nibabel) team are the course teachers: Chris Markiewicz Matthew Brett Oscar Esteban along with Zvi Baratz, of the dicom_parser project. The course is free, funded by the Chan Zuckerberg Initiative. See https://nipraxis.org for more on the course in general, and https://nipraxis.org/fall-2022 for more on this iteration. To apply, please read the introduction in https://nipraxis.org/fall-2022/ and then fill out this form: https://forms.gle/R7ggZGrqSNhgRSGn9 Cheers, Matthew (for the Nipraxis team) From redhatw at gmail.com Mon Jul 25 17:48:50 2022 From: redhatw at gmail.com (redhatw at gmail.com) Date: Mon, 25 Jul 2022 17:48:50 -0400 Subject: [Neuroimaging] FW: Research Associate or Postdoc in University of Maryland In-Reply-To: <00b201d8a06f$e5e39160$b1aab420$@gmail.com> References: <00b201d8a06f$e5e39160$b1aab420$@gmail.com> Message-ID: <00c101d8a070$5387ce20$fa976a60$@gmail.com> Research Associate or Postdoc of fMRI signal processing We have two positions open in fMRI signal processing. Location: Inner Harbor Area in Baltimore, Maryland. Hosting Institute: University of Maryland Baltimore (UMB). UMB and UMD are the two flagship research campuses of the University of Maryland and have become a joint research entity since 2016 which has been ranked among top 10 research institutions in the National Science Foundation's (NSF) Higher Education Research and Development Survey. UMB locates in the Inner Harbor Area, which is the most beautiful and the safest part of Baltimore. University of Maryland School of Medicine (UMSOM) is consistently growing in US News ranking (nearly one step up per year from #42 in 2006 to #27 in 2020). The total funding increased by 74%. Our center: Center for Advanced Imaging Research (CAIR) was newly launched in 2018. The number of faculty and the total amount of fundings both nearly doubled in the past two years. Hosting lab: Professor Ze Wang's imaging computing laboratory. https://www.medschool.umaryland.edu/pi/Ze-Wang-PhD/. We started in UMB since 2019 and have been rapidly expanding with a more than 2x increase of total funding since I started here 2.5 years ago. Benefit: highly competitive salary; position can be either a junior faculty or a postdoc depending on CV and candidate's potential; great opportunities to work on the frontiers in machine learning, image reconstruction, advanced fMRI signal processing, and fun brain development and cognitive neuroscience; great opportunities to build academic careers. Position 2: fMRI processing. This position is supported by a new R01 for up to 4 years or longer. Our overarching goals are to develop and evaluate deep learning-based method and new resting state fMRI processing strategies. We are particularly interested in data mining (auto-clustering and classification, signal detection etc), machine learning (including deep learning), time series analysis, and graph analysis (graph network and graph spectral processing). Related projects ongoing in the lab include deep learning-based ASL perfusion MRI processing, brain entropy and coherence mapping. The ideal candidates should have method development experience in fMRI or neuroimaging signal processing. Background in electrical engineering, computer science, or mathematics is highly preferred. Python or Matlab programming skills are required. Experience on multi-band fMRI data processing is considered a plus. Position 3: neuroimaging-based aging and development research. This position will be supported by a R21 grant. This project can either focus on aging/AD or brain development. The major research vehicle is cerebral blood flow and resting state BOLD fMRI. Candidates should have publication experience in related topics. Experience of longitudinal analysis is preferred. Candidates for the three positions will have opportunities to learn new skills from MRI, signal processing, machine learning, and translational research, and will have lots of opportunities to build an academic career toward independence. Interested candidates should send CV, personal statement (including research statement), and future plan to Dr. Ze Wang: ze.wang at som.umaryland.edu. -------------- next part -------------- An HTML attachment was scrubbed... URL: From pestilli at utexas.edu Wed Jul 27 13:34:22 2022 From: pestilli at utexas.edu (Franco Pestilli) Date: Wed, 27 Jul 2022 12:34:22 -0500 Subject: [Neuroimaging] Workshop on Big Data Neuroscience UT Austin Message-ID: Dear Colleagues, We are excited to announce the 7th annual Big Data Neuroscience (BDN) workshop organized by the Advanced Computational Neuroscience Network . The BDN workshop brings together researchers in neuroscience, computer science, statistics, computer engineering, structural biology, neuroinformatics, and related disciplines. The BDN workshop will be held in Austin, Texas, September 15-16, 2022. The themes of the workshops will be on the following topics: (1) Data Governance and Infrastructure, (2) Measurements and Acquisition, (3) Advanced Analysis and Applications, (4) Software, Sharing and Publication, (5) Standards and Validation. We have an exciting line-up of speakers spanning multiple disciplines of science and engineering: James Carson (Kristen Harris? NeuroNex, UT Austin), Dan Stanzione (TACC), Damian Eke (De Montfort University), Axel Brunger (Stanford University), Martin Paulus (Laureate Institute), Jason McLellan (UT Austin), Jingyu Liu (Georgia State), Jessica Church-Lang (UT Austin), Chen Yu (UT Austin), Angie Laird (Florida International University), Maryann Martone (University of California San Diego), Laura Colgin (The University of Texas at Austin), Franco Pestilli (UT Austin), Piotr Sliz (Harvard University), Yaroslav Halchenko (Dartmouth), Dora Hermes (Mayo Clinic), and David Kennedy (UMass Medical School). In addition to science and engineering, the workshop will host a panel discussion on ?Challenges and opportunities for international-scale infrastructure to advance data sharing and equity? with representatives from the National Science Foundation, the National Institutes of Health, Kavli Foundation, Nature Publishing Group, and Wellcome Trust. Registration You can register for the workshop using this form . The deadline is September 1st, 2022. Call for Posters and Lightning Talks You can submit your abstract here . The deadline is August 18, 2022. Travel Scholarships A few travel scholarships for trainees with underrepresented backgrounds and diverse geographical locations are available. Use the abstract submission form to apply for a travel scholarship . The deadline is August 18, 2022. Please visit www.neurosciencenetwork.org for more information. Best regards, Franco Pestilli, The University of Texas at Austin Susanne Ressl, The University of Texas at Austin Josiah Leong, University of Arkansas Sharlene Newman, University of Alabama Jessica Turner, Georgia State Ivo Dinov, University of Michigan *FRANCO PESTILLI*, *Ph.D.* | *Associate Professor* Department of Psychology | College of Liberal Arts | The University of Texas at Austin he/him | pestilli at utexas.edu | web | GitHub | brainlife.io CONFIDENTIALITY NOTICE: This e-mail message, including any attachments, is for the sole use of the intended recipient(s) and may contain confidential and privileged information. Any unauthorized review, use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply e-mail and destroy all copies of the original message. -------------- next part -------------- An HTML attachment was scrubbed... URL: