Dear experts,

I'm currently using FS 7.1.1 and have already done hippocampal segmentation with segmentHA_T2.sh command for over 100 subjects.

Most results are excellent but some segmentations are inaccurate, for example, including neighbouring white and gray matter as CA1, even though T2 images are clear enough and the pial surface results show recon-all has successfully segmented hippocampus and parahippocampal gyrus.

I'm wondering if there is any way to fix them, but I couldn't find any official writing to deal with this issue.

Is there any method to fix this?

Or the only way is to exclude these subjects?

Best regards,

Taka