*Dear Freesurfers,*
Could you please suggest me the best way to prepare structural data for SVM classification? I googled, searched the archives - there're no examples of such preparation using freesurfer algorithms (to my knowledge)... Thank you beforehand. --- *Regards,* *A. Hasfatin*
what are you trying to classify and what is your hypothesis?
cheers, Bruce On Thu, 24 Mar 2011, Alexander Ivanov wrote:
*Dear Freesurfers,*
Could you please suggest me the best way to prepare structural data for SVM classification? I googled, searched the archives - there're no examples of such preparation using freesurfer algorithms (to my knowledge)... Thank you beforehand.
*Regards,* *A. Hasfatin*
Sorry for the advertisement :)
I wrote a paper using this technique:
Use of SVM methods with surface-based cortical and volumetric subcortical measurements to detect Alzheimer's disease.http://www.ncbi.nlm.nih.gov/pubmed/20061613
Oliveira PP Jr, Nitrini R, Busatto G, Buchpiguel C, Sato JR, Amaro E Jr.
J Alzheimers Dis. 2010;19(4):1263-72. PMID: 20061613 [PubMed - indexed for MEDLINE]
On Thu, Mar 24, 2011 at 09:10, Bruce Fischl fischl@nmr.mgh.harvard.eduwrote:
what are you trying to classify and what is your hypothesis?
cheers, Bruce On Thu, 24 Mar 2011, Alexander Ivanov wrote:
*Dear Freesurfers,*
Could you please suggest me the best way to prepare structural data for
SVM
classification? I googled, searched the archives - there're no examples
of
such preparation using freesurfer algorithms (to my knowledge)... Thank you beforehand.
*Regards,* *A. Hasfatin*
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
The information in this e-mail is intended only for the person to whom it is addressed. If you believe this e-mail was sent to you in error and the e-mail contains patient information, please contact the Partners Compliance HelpLine at http://www.partners.org/complianceline . If the e-mail was sent to you in error but does not contain patient information, please contact the sender and properly dispose of the e-mail.
Thank you very much for such a quick response!
I am going to classify two group of patients: responders versus non-responders... As the matter of fact, I also have fMRI and DTI data of these subjects - but I would prefer to start from structural images... Therefore I'd like to clarify structural (and possibly functional) patterns of non-responders and try to make predictions...
Thank you for your time!
... and for the advertisement=) I'm reading that right now... --- *Regards,* *Alex*
freesurfer@nmr.mgh.harvard.edu