External Email - Use Caution
Hi Evie,
--save-probabilities and --save-posteriors will save two different things for lesions. The former is an initialization of lesions based on intensity and location constraints, and the latter is a probability map of seg.mgz after we also introduce lesion shape constraints (Cf Fig.4 of MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be https://www.sciencedirect.com/science/article/pii/S1053811920309563).
The output of --save-probabilities should give you a very noisy lesion probability map with lots of false positives (at least this is my experience). In your case, it seems that too many *true* lesions are removed when the shape model is introduced. Would you be able to provide the command you're using to segment your T2-FLAIR scans? Which --lesion-mask-pattern values are you using for this input combination?
Stefano
Evie Neylon Tue, 28 Mar 2023 07:15:17 -0700
External Email - Use Caution
Dear experts,
I am running SAMSEG to segment MS lesions from T2 FLAIR scans. I wanted tocreate a lesion mask in order to obtain lesion volumes and lesion counts,so I used mri_binarize on seg.mgz to obtain all voxels with the value 99.However, upon visualising this mask I see that there are holes in the maskin regions that are quite clearly lesions based on the FLAIR image. I seein seg.mgz that these voxels are instead assigned incorrectly to adifferent tissue, as the lateral ventricle, for example.
I wondered if this misassignation of tissue was due to the chosen threshold(0.3) so I added the --save-probabilties flag to look at theprobability maps too, and I see that actually the probability mapthresholded at 0.3 does not contain holes. The probability map actuallyseems more accurate in general and picks up on more of thehyperintensities. This is important for my desired outputs (i.e. accuratelesion counts/volumes).
So I wondered if it was possible to explain a little why these holes mightbe occurring in the final segmentation but not the probability map?Would it be incorrect to derive the lesion mask from the probability mapinstead?
Apologies I cannot attach the images of the data.
TIA,Evie_______________________________________________Freesurfer mailing listThe information in this e-mail is intended only for the person to whom it isaddressed. If you believe this e-mail was sent to you in error and the e-mailcontains patient information, please contact the Mass General BrighamCompliance HelpLine at MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be https://www.massgeneralbrigham.org/compliancelinePlease note that this e-mail is not secure (encrypted). If you do not wish tocontinue communication over unencrypted e-mail, please notify the sender ofthis message immediately. Continuing to send or respond to e-mail afterreceiving this message means you understand and accept this risk and wish tocontinue to communicate over unencrypted e-mail.
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 MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be https://www.massgeneralbrigham.org/complianceline .