External Email - Use Caution
Dear Sir,
As I have got the features file from free surfer recon all, of AD, CN, and MCI. I want use ML techniques for the detection of those three classes. Is it possible to do with ML techniques. Initially I have tried through certain Algorithms but what are the feature set which can contains the major differences in the two classes between CN and AD. If have tried but very less differences it was there in the cortical surfaces. Please throw some light on this. What features would create more difference between those two classes.
regards Amar Shukla
On Wed, 1 Jun 2022 at 3:39 AM, Douglas N. Greve dgreve@mgh.harvard.edu wrote:
There are 100s if not more parameters in recon-all supporting dozens of underlying functions. If you look in recon-all.cmd (or .log) you will find the binaries that get called; sometimes the command line has parameters, sometimes the parameters are embedded in the binary itself. Some of the defaults are in the recon-all script or the recon-config.yaml file. There is not really one paper that describes everything as many of the functions have evolved over the years, many with their own papers.
On 5/31/2022 8:07 AM, Amar Shukla wrote:
External Email - Use CautionDear Sir,
I am a PhD scholar using the freesurfer tool to conduct my research work. I tested the recon all method in the Free Surfer, and it was effective with the data set that was used by me. What are the exact default parameters for the different processes of recon all that were used in motion correction, intensity normalization, etc?. It would be really helpful if you could provide me with the link or the article where it is explained clearly, this will help me to get through these processes in more depth and in a more constructive manner. Although the Free Surfer website has an FAQ regarding this process, there are no clear explanations about what the default parameters are during recon all.
-- With Regards, Amar Shukla PHD Scholar UPES
Freesurfer mailing listFreesurfer@nmr.mgh.harvard.eduhttps://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://secure-web.cisco.com/1fD5qdq8uT4YHFwGtCg1MeKxEUZAyXB_ch2oiDkeE477YAr... 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 Mass General Brigham Compliance HelpLine at https://secure-web.cisco.com/1EwMNjXnxwYU2S-LOVSEDR-H9HmFjiPbJCBQIdRv5zTqX5n... < https://secure-web.cisco.com/1EwMNjXnxwYU2S-LOVSEDR-H9HmFjiPbJCBQIdRv5zTqX5n... . Please note that this e-mail is not secure (encrypted). If you do not wish to continue communication over unencrypted e-mail, please notify the sender of this message immediately. Continuing to send or respond to e-mail after receiving this message means you understand and accept this risk and wish to continue to communicate over unencrypted e-mail.