NF: Updating EVAC+ model and adding util function #2963
Conversation
|
Hello @pjsjongsung, Thank you for updating !
Comment last updated at 2023-11-15 18:07:44 UTC |
pjsjongsung
force-pushed
the
evac_new_student
branch
4 times, most recently
from
cb2c8a7
to
6c63841
Compare
Codecov Report
Additional details and impacted files@@ Coverage Diff @@
## master #2963 +/- ##
==========================================
- Coverage 81.71% 81.70% -0.01%
==========================================
Files 147 147
Lines 20484 20540 +56
Branches 3277 3285 +8
==========================================
+ Hits 16739 16783 +44
- Misses 2913 2924 +11
- Partials 832 833 +1
|
|
I think the PR looks ok? The failures seems to be coming from unrelated tests that uses numpy random, which I plan to fix through #2964 |
pjsjongsung
force-pushed
the
evac_new_student
branch
from
6c63841
to
ce136b5
Compare
There was a problem hiding this comment.
Hi @pjsjongsung,
see below an initial reveiw before I test the code. Thank you for this!
pjsjongsung
force-pushed
the
evac_new_student
branch
3 times, most recently
from
60e2b69
to
4a2a68b
Compare
|
The comments should be all resolved! |
There was a problem hiding this comment.
Hi @pjsjongsung,
This PR seems ready to go. See below my last comments.
This commit changes the EVAC+ model and its default weights for better brain extraction output. It also adds an option to only select the largest foreground and remove its holes, so that most prediction noises can be removed. Slice wise filling holes were added as well for more desired results. Utils functions have changed to use voxsize, and tests have changed accordingly as well.
pjsjongsung
force-pushed
the
evac_new_student
branch
from
4a2a68b
to
529aa01
Compare
This commit changes the EVAC+ model and its default weights for better brain extraction output. It also adds an option to only select the largest foreground and remove its holes, so that most prediction noises can be removed.