-
-
Notifications
You must be signed in to change notification settings - Fork 101
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Removed support for -initc2 flag because there is an alternative approach with sct_label_utils #2125
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
User can do sct_label_utils()
jcohenadad
added
enhancement
category: improves performance/results of an existing feature
sct_label_vertebrae
context:
labels
Jan 19, 2019
jcohenadad
added
the
compatibility
Incompatible API changes that necessitate a MAJOR version bump. Refer to https://semver.org/
label
Jan 19, 2019
jcohenadad
changed the title
sct_label_vertebrae: Removed support for initc2
Removed support for -initc2 flag
Jan 19, 2019
jcohenadad
changed the title
Removed support for -initc2 flag
Removed support for -initc2 flag because there is an alternative approach with sct_label_utils
Jan 19, 2019
alexfoias
approved these changes
Jan 19, 2019
jcohenadad
pushed a commit
that referenced
this pull request
Jan 19, 2019
* detect_c2c3: improvements -- postprocessing * keep clusters with correct margin * use normalised margin * use top of the segmentation as anatomical prior * dev/detect_c2c3/train: create qc, nb of sagittal slices avg * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7 sag slices, remove hard coded post processing * Update README.md (#2118) * Expose aggregate_slicewise() API and various improvements (#2115) * sct_extract_metric: Created API: extract_metric * sct_extract_metric: Started refactoring to use aggregate_slicewise * aggregate_slicewise: Started refactoring for accommodating extract_metric - metrics is now ndarray (instead of list) to deal with >1 dim - added mask for computing weighted average, ml, etc. * sct_extract_metric,aggregate_slicewise: Main steps of working API sct_extract_metric now working (in specific scenario) with new APIs. * aggregate_slicewise,sct_extract_metric: Further improvements - Moved Metric() class inside aggregate_slicewise - Now display Mask in output csv - Now display func with metric name (for compatibility with process_seg module) * aggregate_slicewise: Changed variable name * process_seg: Adapted code to fit recent changes in aggregate_slicewise * msct_shape,process_seg: Adapted code to fit changes in aggregate_slicewise Other modifications: - drop features: incremental_length, distance_from_C1, vertebral_level * test_process_seg: Fixed broken compatibility with recent changes * sct_extract_metric,aggregate_slicewise: Refactored to generalize for ML and WA Notably introduced label_struc Class inside sct_extract_metric for simplicity * sct_extract_metric,aggregate_slicewise: Moved extract_metric inside aggregate_slicewise Will enable unit testing * aggregate_slicewise: Generalized to n-dim was breaking compatibility with process_seg * test_aggregate_slicewise: Started to update tests with recent changes * aggregate_slicewise: Generalized to n-dim, added tests * test_aggregate_slicewise: All tests pass * test_aggregate_slicewise: Added test for csv Testing output of extract_metric() Also fixed few issues in aggregate_slicewise.py * aggregate_slicewise: Fixed ordering of column in output csv All tests pass * aggregate_slicewise: Fixed issue with STD and ML method * aggregate_slicewise: Changed the way errors are raised * sct_extract_metric: Added field for appending to csv * utils: Fixed bug in parse_num_list_inv() Number of chars to adapt based on int * aggregate_slicewise: Implemented method=bin and added test * sct_extract_metric: Dropped support for method=wath Not really used... * aggregate_slicewise: Implemented method=max And associated tests and wrapper * sct_process_segmentation: Fixed broken compatibility * msct_shape: Fixed bug when looping across slices * sct_extract_metric: Fixed undeclared variable * aggregate_slicewise: Removed weight in ML for faster estimate Also started to implement MAP * sct_extract_metric: Changed default value for perslice * aggregate_slicewise: Implemented MAP (unfinished) need to pass ml_clusters information to func_ml() * aggregate_slicewise: Refactored for compatibility with MAP * aggregate_slicewise: Fixed bug related to reshaping mask Also added MAX in csv output * aggregate_slicewise: Fixed wrong indentation for try/except * aggregate_slicewise: Fixed duplicated dict key * aggregate_slicewise: Added check for non-finite values * test_sct_extract_metric: Updated test * aggregate_slicewise: Fixed bug introduced with checking for nonfinite * aggregate_slicewise: Fixed wrong reshape of array * batch_processing: Update with recent modifs in API * aggregate_slicewise,sct_process_segmentation: Added TODO * sct_process_segmentation,aggregate_slicewise: Changed default Regarding perslice and perlevel. To be closer to previous behaviour. * template: Now checking for inf in get_slices_from_vertebral_levels * sct_extract_metric: Few improvements - Display output file - Fixed default params * aggregate_slicewise: Created merge_dict() to deal with dict of dict Useful for sct_process_seg with several output metrics, to be able to concatenate them in a single csv * sct_process_segmentation: Now output all metrics in the same csv There's still a bug to solve in merge_dict() * aggregate_slicewise: Fixed small bug in merge_dict * aggregate_slicewise: Now ordering metrics in a friendly way * test_aggregate_slicewise: Fixed bug caused by recent changes * aggregate_slicewise: Forgot to add CSA and Angle * batch_processing: Updated to match recent changes * sct_extract_metric: Fixed deprecated default method wath * test_sct_extract_metric: Updated ground truth value * batch_processing: Fixed verbose bug * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7mm instead of 7slices * scripts/sct_download_data: update download link for c2c3 models * Output volume fraction on csv (#2122) * aggregate_slicewise: Removed VertLevel in agg_metric if not exist * aggregate_slicewise: Now display Label volume fraction Fixes #2121 * aggregate_slicewise: Fixed regression on detection nan * sct_extract_metric: Fixed bug with single mask as input * sct_extract_metric: Now display file name in Label column * test_aggregate_slicewise: Fixed unit test caused by recent changes * sct_label_vertebrae: Removed support for initc2 (#2125) User can do sct_label_utils() * detect_c2c3: improvements -- postprocessing * keep clusters with correct margin * use normalised margin * use top of the segmentation as anatomical prior * dev/detect_c2c3/train: create qc, nb of sagittal slices avg * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7 sag slices, remove hard coded post processing * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7mm instead of 7slices * scripts/sct_download_data: update download link for c2c3 models
jcohenadad
added a commit
that referenced
this pull request
Dec 18, 2019
User can do sct_label_utils() Former-commit-id: fe30f1b
jcohenadad
pushed a commit
that referenced
this pull request
Dec 18, 2019
* detect_c2c3: improvements -- postprocessing * keep clusters with correct margin * use normalised margin * use top of the segmentation as anatomical prior * dev/detect_c2c3/train: create qc, nb of sagittal slices avg * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7 sag slices, remove hard coded post processing * Update README.md (#2118) * Expose aggregate_slicewise() API and various improvements (#2115) * sct_extract_metric: Created API: extract_metric * sct_extract_metric: Started refactoring to use aggregate_slicewise * aggregate_slicewise: Started refactoring for accommodating extract_metric - metrics is now ndarray (instead of list) to deal with >1 dim - added mask for computing weighted average, ml, etc. * sct_extract_metric,aggregate_slicewise: Main steps of working API sct_extract_metric now working (in specific scenario) with new APIs. * aggregate_slicewise,sct_extract_metric: Further improvements - Moved Metric() class inside aggregate_slicewise - Now display Mask in output csv - Now display func with metric name (for compatibility with process_seg module) * aggregate_slicewise: Changed variable name * process_seg: Adapted code to fit recent changes in aggregate_slicewise * msct_shape,process_seg: Adapted code to fit changes in aggregate_slicewise Other modifications: - drop features: incremental_length, distance_from_C1, vertebral_level * test_process_seg: Fixed broken compatibility with recent changes * sct_extract_metric,aggregate_slicewise: Refactored to generalize for ML and WA Notably introduced label_struc Class inside sct_extract_metric for simplicity * sct_extract_metric,aggregate_slicewise: Moved extract_metric inside aggregate_slicewise Will enable unit testing * aggregate_slicewise: Generalized to n-dim was breaking compatibility with process_seg * test_aggregate_slicewise: Started to update tests with recent changes * aggregate_slicewise: Generalized to n-dim, added tests * test_aggregate_slicewise: All tests pass * test_aggregate_slicewise: Added test for csv Testing output of extract_metric() Also fixed few issues in aggregate_slicewise.py * aggregate_slicewise: Fixed ordering of column in output csv All tests pass * aggregate_slicewise: Fixed issue with STD and ML method * aggregate_slicewise: Changed the way errors are raised * sct_extract_metric: Added field for appending to csv * utils: Fixed bug in parse_num_list_inv() Number of chars to adapt based on int * aggregate_slicewise: Implemented method=bin and added test * sct_extract_metric: Dropped support for method=wath Not really used... * aggregate_slicewise: Implemented method=max And associated tests and wrapper * sct_process_segmentation: Fixed broken compatibility * msct_shape: Fixed bug when looping across slices * sct_extract_metric: Fixed undeclared variable * aggregate_slicewise: Removed weight in ML for faster estimate Also started to implement MAP * sct_extract_metric: Changed default value for perslice * aggregate_slicewise: Implemented MAP (unfinished) need to pass ml_clusters information to func_ml() * aggregate_slicewise: Refactored for compatibility with MAP * aggregate_slicewise: Fixed bug related to reshaping mask Also added MAX in csv output * aggregate_slicewise: Fixed wrong indentation for try/except * aggregate_slicewise: Fixed duplicated dict key * aggregate_slicewise: Added check for non-finite values * test_sct_extract_metric: Updated test * aggregate_slicewise: Fixed bug introduced with checking for nonfinite * aggregate_slicewise: Fixed wrong reshape of array * batch_processing: Update with recent modifs in API * aggregate_slicewise,sct_process_segmentation: Added TODO * sct_process_segmentation,aggregate_slicewise: Changed default Regarding perslice and perlevel. To be closer to previous behaviour. * template: Now checking for inf in get_slices_from_vertebral_levels * sct_extract_metric: Few improvements - Display output file - Fixed default params * aggregate_slicewise: Created merge_dict() to deal with dict of dict Useful for sct_process_seg with several output metrics, to be able to concatenate them in a single csv * sct_process_segmentation: Now output all metrics in the same csv There's still a bug to solve in merge_dict() * aggregate_slicewise: Fixed small bug in merge_dict * aggregate_slicewise: Now ordering metrics in a friendly way * test_aggregate_slicewise: Fixed bug caused by recent changes * aggregate_slicewise: Forgot to add CSA and Angle * batch_processing: Updated to match recent changes * sct_extract_metric: Fixed deprecated default method wath * test_sct_extract_metric: Updated ground truth value * batch_processing: Fixed verbose bug * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7mm instead of 7slices * scripts/sct_download_data: update download link for c2c3 models * Output volume fraction on csv (#2122) * aggregate_slicewise: Removed VertLevel in agg_metric if not exist * aggregate_slicewise: Now display Label volume fraction Fixes #2121 * aggregate_slicewise: Fixed regression on detection nan * sct_extract_metric: Fixed bug with single mask as input * sct_extract_metric: Now display file name in Label column * test_aggregate_slicewise: Fixed unit test caused by recent changes * sct_label_vertebrae: Removed support for initc2 (#2125) User can do sct_label_utils() * detect_c2c3: improvements -- postprocessing * keep clusters with correct margin * use normalised margin * use top of the segmentation as anatomical prior * dev/detect_c2c3/train: create qc, nb of sagittal slices avg * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7 sag slices, remove hard coded post processing * spinalcordtoolbox/vertebrae/detect_c2c3: avg 7mm instead of 7slices * scripts/sct_download_data: update download link for c2c3 models Former-commit-id: 9217ece
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
compatibility
Incompatible API changes that necessitate a MAJOR version bump. Refer to https://semver.org/
enhancement
category: improves performance/results of an existing feature
sct_label_vertebrae
context:
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Instead, user can create a label with
sct_label_utils
and then runsct_label_vertebrae
with flag-initlabel
. This decision enables to lighter the code and minimize the number of choices for the user (could be overwhelming).Example:
Fixes #2120