Comments (1)
I started working on a branch for this, but realized this is a bit more involved than I first thought:
- The "center of mass" issue was quite easy to fix -- just a simple call to
get_centerline
. - I noticed that the axial mosaic crop size of 30x30 is too small to fully show the rootlets seg (since they exist outside the cord, in the CSF region). Increasing it to 40x40 helped.
- However, the colormapping is trickier:
- The resampling that we're currently doing messes up the label values. (For comparison,
sct_label_vertebrae
skips resampling.) - Even if the labels were perfect, matplotlib's colormaps aren't suited to our labels out of the box.
- The resampling that we're currently doing messes up the label values. (For comparison,
I think the main issue here is that the rootlets seg isn't a binary/softseg, it's a "labeled seg" (akin to sct_label_vertebrae
). So, it's not straightforward to simply adapt the existing sct_deepseg
SC/lesion seg QC to it; I think it requires an entirely separate QC report.
So, I think it might be better to fix this as part of the effort for bringing sct_label_vertebrae
's QC to the qc2.py
rework.
from spinalcordtoolbox.
Related Issues (20)
- `RuntimeError: PytorchStreamReader` when running `sct_deepseg` on contrast agnostic model HOT 4
- `sct_deepseg -task seg_spinal_rootlets_t2w` raises `unexpected keyword argument 'perform_everything_on_device'` error HOT 3
- Output softseg from MONAI inference is not in the range `[0, 1]` HOT 4
- Update contrast-agnostic model to 2.4 HOT 1
- Mask creation is no more required for cropping
- Provide better instructions when Windows username contains spaces HOT 3
- macOS runners take an inconsistent amount of time to run, sporadically triggering the `-h` profiling test
- FileNotFoundError: when using `type=im` with `algo=centermassrot` HOT 6
- Indicate deepseg model HOT 1
- Is `line_angle()` still available in QC for looking at HOG performance? HOT 2
- Improve angle estimation for slicewise registration
- Replace deepseg MS lesion seg model
- `ValueError`: `module://matplotlib_inline.backend_inline is not a valid value` when running SCT scripts in Jupyter notbooks HOT 11
- Cannot checkout a release HOT 5
- Reuse of warping field should not happen if SCT version evolved HOT 2
- Label-based transformation during template registration is wrong HOT 14
- Different results when using `sct_deepseg` models trained with nnUNet in 3D Slicer HOT 1
- `ValueError: shapes not aligned` when generating QC report for BOLD data HOT 8
- Update documentation to explain how to integrate nnUNet models into 3D Slicer HOT 8
- Deprecate `sct_deepseg_{sc,lesion,gm}` and move the models to `sct_deepseg`
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from spinalcordtoolbox.