New dataset `hc-ucsf-psir`

[Nilser3]

Description

I would like to push a new dataset ucsf-gm-psir to git-annex server.

Is a dataset shared by our UCSF collaborators, contains 110 subjects with:

anat: axial PSIR images from healthy controls (one slice by subject) at C2-3 level GT: GM manual segmentation

Here the qc_ucsf-gm-psir-gm.zip checking GM segmentation

[Nilser3]

Generating SC GTs

sub-0047_acq-ax_PSIR

1. Applying seg_sc_contrast_agnostic model v2.4

2. Applying sct_deepseg_sc -c t1

QC here: qc_ucsf-gm-psir.zip

Legend

1. _contrast-agnostic.nii.gz -> contrast_agnostic model v2.4
2. _deepseg_sc.nii.gz -> sct_deepseg_sc -c t1

[Nilser3]

Generating SC GTs

Because the contrast-agnostic model v2.4 failed to segment the subject sub-0047 (which is a single 2D slice, see segmentations above), I made a merge in Z of 40 slices, building a 3D volume where I applied the same contrast-agnostic model.

We have good results in the central slices (first column), but irregularities in the upper and lower ends:

• Upper last slice

• Lower last slice

Maybe we should put an informative message about the use of contrast-agnostic model when applying it to 2D images? feedback pls @naga-karthik

[naga-karthik]

Hey Nilser, thanks for the detailed segmentation images! it's surprising that the contrast-agnostic model is not working that well -- i'm guessing that's mainly because these are single-slice images? the v2.4 model was trained will all 3D images AND didn't have axial PSIR images (only sagittal PSIR scans were available)

I made a merge in Z of 40 slices,

what do you mean by this? where is this 40 coming from? I have a few more questions:

1. what is the size of the original input image (i.e. matrix dimensions)?
2. what is the size after merging the z-slices?

but irregularities in the upper and lower ends:

yeah, this is an issue because of padding the images to a common size during training. Because you're are merging slices anyway to make it a 3D input, maybe you can also discard the top and bottom slices? i.e. your actual SC slice would be in the middle -- which I see has a good segmentation already. let me know what you think!

[Nilser3]

Thanks you @naga-karthik

Here in detail: I made a merge on the Z-axis of 40 2D slices (repeat the same slice).

Original input image 2D slice:

• shape: 256x256x1 , resolution: 0.7812x0.7812x5

3D vol:

• shape: 256x256x40, resolution: 0.7812x0.7812x5

Yes, I think the model makes a good segmentation in the middle of a 3D volume, maybe this would be the approach when the model confronts 2D images in input.

[jcohenadad]

I made a merge in Z of 40 slices, building a 3D volume where I applied the same contrast-agnostic model.

what if we pad using mirroring data to avoid edge cases? I think we already talked about it @naga-karthik @Nilser3 -- we should add this as preprocessing of sct_deepseg before inference

[naga-karthik]

Yeah, this could be done -- I opened an issue on SCT regarding this

[Nilser3]

Hi @mguaypaq , Could you please create a repo for the dataset: hc-ucsf-psir

Thanks you

[naga-karthik]

Maybe it shoudl be gm-psir-ucsf ? a lot of our datasets have center names at the end (e.g. sci-zurich, dcm-paris, lumbar-epfl etc. )

[jcohenadad]

~how about simply psir-ucsf? i'm afraid 'gm' will be confusing. We do have a 'gmseg' but it was specifically for a challenge~

actually, according to our convention, the contrast goes at the end. So it should be ucsf-psir then

EDIT 20240620_124453: I just edited our convention, to add hc- in the beginning, so it would be hc-ucsf-psir if that's ok with everyone

[Nilser3]

Hi @mguaypaq , could you create a repo for hc-ucsf-psir dataset please. Thanks you

[mguaypaq]

I created the repository and gave write access to @Nilser3: https://data.neuro.polymtl.ca/datasets/hc-ucsf-psir

[Nilser3]

Thanks you @mguaypaq PR done!