Problem with neonatal image isegmentation

I will explain better with an example. This second subject , with respect to the first one I showed you, has better signal along z axis also below the prevoius one. Is it ok if the cropping is a bit different like in the image attached?


As regards DTI metrics, extraction will be limited to C1-C3 for all subjects for the sake of coherence.
Thanks,
Rosella

Hi Rosella,

Moreover, I am trying the segmentation and processing script on another subject. I have decided to keep the cropping as the first subject (C1-C4) for coherence. However, segmentation with deepseg seems giving worst results I think. Could it be ok to process this subject differently?Of course I’d rather find a processing suitable for all subjects.

I tried running the script i uploaded here, and results are not that bad. See below:

There are issues at slices 9-10 on the picture above, which is due to a poor fat saturation, causing the fat to alias on the spinal cord area. So this is a problem related to the acquisition, not the processing. You will need to fix it manually.

I cannot understand how you decided to crop the image in this case:
sct_crop_image -i kurtosis.nii -xmin 60 -xmax 100 -ymin 60 -ymax 100 -zmin 8 -o kurtosis_crop.nii
Especially, how can I be sure to crop all subjects the same way?

I suggested this cropping area, without knowing how your data were acquired. You will need to adjust it based on how your MR tech was instructed to acquire the data. If the FOV positioning is inconsistent across subjects, you could relax the parameters (e.g. use a less narrow cropping box).

Best,
Julien

HI.
thank you very much! So do you suggest using the same segmentation method across subjects, if possible?
thanks,
Rosella

So something like this, a cropping area variable according to the subject, should be ok?
thanks,
Rosella

For exapmle,
which cropping did you use for this second subject?
thanks,
Rosella

which cropping did you use for this second subject?

i used the same cropping-- my goal was only to check the segmentation (you mentioned it was not working as well)

OK thank you ! I will correct manually the 2 problematic slices. What instead to do with this subject, where in 2 slices the SC seems not detectable?
thanks,
Rosella


I have shared the correspoding data via email.
thanks,
Rosella

there is no point in computing anything in these slices (i.e. diffusion metrics will be irrelevant). so you can just ignore them

Ok so, do you tjink the rest of the segmentation is ok?
thanks,
Rosella

i would only trust slices 10-18, and yes: the segmentation looks ok on these

In which way can I just use those slices? In the metrics’ extraction computation command?
thanks,
Rosella

in the script sct_extract_metric, you specify the level (from the script i sent you: -vert 1:3). You can decide to specify which slices to compute the metrics from, in that case, use the flag -z instead.

But if you decide to do so, you need a good scientific justification. By choosing to discard slices on a per-subject basis, you also introduce a bias. Alternatively, you can exclude subjects if the data quality is not sufficient. So, depending on the context of your study, your hypotheses, assumptions, etc. you need to make the right decision.

1 Like

Hi,
I am sending to you via e mail a folder with all 10 subjects segmentation results in order to inspect if they are suitable for further DTI and DKI metrics extraction. I used the command cointained in the script (Problem with neonatal image isegmentation) as regards segmentation. As far as it concerns FOV reduction, I used a different cropping according to the subject.
Best,
Rosella