ENH: Update fit-to-patient for non-contrast heart models#87
Merged
Conversation
Non-contrast heart models from TotalSegmentator are incomplete, but this update makes registration to a statistical model possible.
WalkthroughThe changes migrate workflow execution to ChangesWorkflow API and callers
Segmentation and utility behavior
DirLab-4DCT data flow
Estimated code review effort: 4 (Complex) | ~45 minutes ✨ Finishing Touches🧪 Generate unit tests (beta)
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (3)
src/physiotwin4d/workflow_convert_image_to_usd.py (1)
83-84: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick winUpdate the docstring to reflect the new default value.
The default value for
frames_per_secondwas changed to1.0(at line 57), but the docstring still states it defaults to24.0. As per coding guidelines, docstrings must be updated and kept factual for changed public methods.📝 Proposed fix
- frames_per_second: Frames per second for animated USD time series. - Defaults to 24.0, matching the underlying VTK-to-USD converter. + frames_per_second: Frames per second for animated USD time series. + Defaults to 1.0.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/physiotwin4d/workflow_convert_image_to_usd.py` around lines 83 - 84, Update the frames_per_second parameter documentation in the workflow conversion function’s docstring to state that the default is 1.0 instead of 24.0, matching the value defined in the function signature.Source: Coding guidelines
docs/developer/segmentation.rst (1)
40-44: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick winDoc references stale
contrastid 135.
segment_chest_total_segmentator_with_contrast.pynow registers"contrast"at id 155 (moved from 135 to avoid colliding with the newbody_extremities=135 label), but this line still documents "contrast at id 135".🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/developer/segmentation.rst` around lines 40 - 44, Update the taxonomy documentation for the default “contrast” placeholder to use id 155 instead of 135, while retaining the “soft_tissue” id 133 reference and the surrounding description.src/physiotwin4d/segment_chest_total_segmentator.py (1)
46-47: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winRestore
target_spacingto1.5or update the contract around resampling.self.target_spacing = 0.0disablesSegmentAnatomyBase.preprocess_input(), contradicts the class docstring, and breaks the current initialization test that expects1.5. If the new behavior is intentional, update the docstring and test to match.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/physiotwin4d/segment_chest_total_segmentator.py` around lines 46 - 47, Restore self.target_spacing to 1.5 in the TotalSegmentator class so it matches the documented contract and existing initialization test, preserving the expected resampling behavior through SegmentAnatomyBase.preprocess_input().
🧹 Nitpick comments (3)
src/physiotwin4d/contour_tools.py (1)
34-35: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winUpdate docstrings for the changed public methods.
The static-method conversion is compatible with the supplied callers, but the public documentation is incomplete:
transform_contoursomits several parameters,create_reference_imagelacks argument and return documentation, andcreate_mask_from_meshhas no docstring. Please update all five changed methods with complete, factual docstrings.As per coding guidelines, update docstrings for every changed public method.
Also applies to: 74-75, 138-139, 167-168, 363-364
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/physiotwin4d/contour_tools.py` around lines 34 - 35, Update the docstrings for all five changed public methods, including extract_contours, transform_contours, create_reference_image, create_mask_from_mesh, and the method at the additional referenced location. Document every parameter and the return value with accurate descriptions, ensuring transform_contours includes its omitted parameters and create_reference_image and create_mask_from_mesh have complete argument and return documentation.Source: Coding guidelines
src/physiotwin4d/segment_anatomy_base.py (1)
456-463: 🎯 Functional Correctness | 🔵 Trivial | ⚡ Quick winGroup labelmaps aren't cast to uint8 like the main
"labelmap"key.
labelmap_imageis explicitly re-cast touint8before being returned, but thelabelmapsdict (heart/lung/etc.) is built from the pre-cast image and returned as-is. All current segmenters happen to already produce uint8 labelmaps, so this is not currently observable, but the returned dict has no guaranteed-consistent pixel type across its values, which downstream consumers (writers, comparisons) may implicitly assume.♻️ Suggested fix
labelmaps = self.create_anatomy_group_labelmaps(labelmap_image) labelmap_image = itk.GetImageFromArray( itk.GetArrayFromImage(labelmap_image).astype(np.uint8) ) labelmap_image.CopyInformation(input_image) - return {"labelmap": labelmap_image, **labelmaps} + labelmaps = { + group: itk.GetImageFromArray( + itk.GetArrayFromImage(group_labelmap).astype(np.uint8) + ) + for group, group_labelmap in labelmaps.items() + } + for group_labelmap, source in zip(labelmaps.values(), labelmaps.values()): + group_labelmap.CopyInformation(input_image) + + return {"labelmap": labelmap_image, **labelmaps}🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/physiotwin4d/segment_anatomy_base.py` around lines 456 - 463, Update the labelmap construction flow around create_anatomy_group_labelmaps so every group labelmap in labelmaps is converted to uint8 before returning. Apply the same pixel-type normalization used for the main "labelmap" while preserving each group's existing image metadata and the return structure.tutorials/tutorial_04_fit_statistical_model_to_patient.py (1)
101-110: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winPersisted ITK images/transforms omit
compression=Truein two tutorials. Bothitk.imwriteanditk.transformwritedefault theircompressionparameter toFalse; the coding guidelines require compressed storage for both ITK images and.hdftransforms.
tutorials/tutorial_04_fit_statistical_model_to_patient.py#L101-L110: addcompression=Trueto the threeitk.imwrite(...)calls (patient image, patient labelmap, heart labelmap).tutorials/tutorial_06_reconstruct_highres_4d_ct.py#L107-L111: addcompression=Trueto the twoitk.transformwrite(...)calls (forward and inverse transform).🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tutorials/tutorial_04_fit_statistical_model_to_patient.py` around lines 101 - 110, Enable compression on all persisted ITK outputs: update the three itk.imwrite calls in tutorials/tutorial_04_fit_statistical_model_to_patient.py for patient_image, patient_labelmap, and heart_labelmap, and the two itk.transformwrite calls in tutorials/tutorial_06_reconstruct_highres_4d_ct.py for the forward and inverse transforms, by passing compression=True.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@experiments/Heart-Create_Statistical_Model/README.md`:
- Line 164: Update the workflow result assignment around
WorkflowFitStatisticalModelToPatient.process() so it selects
registered_template_model_surface from the returned dictionary instead of
assigning the entire dictionary to registered_mesh.
In `@src/physiotwin4d/segment_chest_total_segmentator.py`:
- Line 286: Remove the three unconditional debug itk.imwrite calls for
preprocessed_image, labelmap_arr_heart, and labelmap_arr_body from the
segmentation flow. Do not replace them with other production writes; preserve
the segmentation behavior while eliminating the working-directory artifacts and
associated debug image creation if it is used only by those writes.
- Around line 369-393: Binarize the heart interior mask before constructing
interior_image in the high-resolution heart expansion block: make interior_arr
contain 1 for labels 141–144 and 0 elsewhere, while preserving the existing
dilation and erosion calls using foreground value 1. Keep the subsequent
exterior mask application and labelmap replacement behavior unchanged.
In `@src/physiotwin4d/workflow_convert_image_to_usd.py`:
- Line 228: Wrap the assignment to self.reference_segmentation_results in the
workflow conversion code so each resulting line is no longer than 88 characters,
preserving the existing segmenter.segment(self.reference_image) behavior.
In `@tests/conftest.py`:
- Around line 517-529: Remove the unconditional "contrast" lookup from the
fixture result assembled with segmenter_total_segmentator, since
create_anatomy_group_labelmaps only returns registered groups. Keep the existing
groups unchanged; if contrast output is required, use the
segmenter_total_segmentator_with_contrast fixture instead.
In `@tutorials/tutorial_04_fit_statistical_model_to_patient.py`:
- Around line 128-143: Guard PCA registration in the workflow setup using the
loaded pca_model: call set_use_pca_registration only when pca_model is not None,
while preserving the existing enabled configuration when it is available. Update
the result-saving flow around workflow.pca_coefficients so it does not call
tolist() when PCA was skipped, and save registered coefficients only when they
exist.
---
Outside diff comments:
In `@docs/developer/segmentation.rst`:
- Around line 40-44: Update the taxonomy documentation for the default
“contrast” placeholder to use id 155 instead of 135, while retaining the
“soft_tissue” id 133 reference and the surrounding description.
In `@src/physiotwin4d/segment_chest_total_segmentator.py`:
- Around line 46-47: Restore self.target_spacing to 1.5 in the TotalSegmentator
class so it matches the documented contract and existing initialization test,
preserving the expected resampling behavior through
SegmentAnatomyBase.preprocess_input().
In `@src/physiotwin4d/workflow_convert_image_to_usd.py`:
- Around line 83-84: Update the frames_per_second parameter documentation in the
workflow conversion function’s docstring to state that the default is 1.0
instead of 24.0, matching the value defined in the function signature.
---
Nitpick comments:
In `@src/physiotwin4d/contour_tools.py`:
- Around line 34-35: Update the docstrings for all five changed public methods,
including extract_contours, transform_contours, create_reference_image,
create_mask_from_mesh, and the method at the additional referenced location.
Document every parameter and the return value with accurate descriptions,
ensuring transform_contours includes its omitted parameters and
create_reference_image and create_mask_from_mesh have complete argument and
return documentation.
In `@src/physiotwin4d/segment_anatomy_base.py`:
- Around line 456-463: Update the labelmap construction flow around
create_anatomy_group_labelmaps so every group labelmap in labelmaps is converted
to uint8 before returning. Apply the same pixel-type normalization used for the
main "labelmap" while preserving each group's existing image metadata and the
return structure.
In `@tutorials/tutorial_04_fit_statistical_model_to_patient.py`:
- Around line 101-110: Enable compression on all persisted ITK outputs: update
the three itk.imwrite calls in
tutorials/tutorial_04_fit_statistical_model_to_patient.py for patient_image,
patient_labelmap, and heart_labelmap, and the two itk.transformwrite calls in
tutorials/tutorial_06_reconstruct_highres_4d_ct.py for the forward and inverse
transforms, by passing compression=True.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: abdc6a98-e2d4-4726-9063-94a05139b70e
📒 Files selected for processing (23)
docs/api/model_registration/index.rstdocs/api/workflows.rstdocs/developer/registration_models.rstdocs/developer/segmentation.rstdocs/tutorials.rstexperiments/Heart-Create_Statistical_Model/README.mdexperiments/Heart-GatedCT_To_USD/2-generate_segmentation.pyexperiments/Heart-Statistical_Model_To_Patient/heart_model_to_patient-CHOPValve.pysrc/physiotwin4d/cli/fit_statistical_model_to_patient.pysrc/physiotwin4d/cli/reconstruct_highres_4d_ct.pysrc/physiotwin4d/contour_tools.pysrc/physiotwin4d/segment_anatomy_base.pysrc/physiotwin4d/segment_chest_total_segmentator.pysrc/physiotwin4d/segment_chest_total_segmentator_with_contrast.pysrc/physiotwin4d/segment_heart_simpleware.pysrc/physiotwin4d/workflow_convert_image_to_usd.pysrc/physiotwin4d/workflow_fit_statistical_model_to_patient.pysrc/physiotwin4d/workflow_reconstruct_highres_4d_ct.pytests/conftest.pytests/test_segment_chest_total_segmentator.pytutorials/tutorial_04_fit_statistical_model_to_patient.pytutorials/tutorial_06_reconstruct_highres_4d_ct.pytutorials/tutorial_08_cardiac_fit_model.py
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
tutorials/tutorial_01b_lung_gated_ct_to_usd.py (1)
141-150: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueChange
usd_project_nameto reflect lung anatomy.Since this tutorial processes lung data from DirLab, consider renaming the USD project name from
"cardiac_model"to"lung_model"(or similar) to avoid confusion in the output artifacts.♻️ Proposed fix
workflow = WorkflowConvertImageToUSD( time_series_images=time_series_images, reference_image=reference_image, output_directory=str(output_dir), - usd_project_name="cardiac_model", + usd_project_name="lung_model", registration_method=registration_method, log_level=log_level, save_assets=True, )🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tutorials/tutorial_01b_lung_gated_ct_to_usd.py` around lines 141 - 150, Update the usd_project_name argument in the WorkflowConvertImageToUSD initialization to use a lung-specific name such as "lung_model" instead of "cardiac_model", keeping the remaining workflow configuration unchanged.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@tutorials/tutorial_01b_lung_gated_ct_to_usd.py`:
- Around line 1-68: Update the module-level docstring to describe the
DirLab-4DCT lung workflow rather than cardiac processing. Replace heart-specific
title, anatomy, dataset, input path, terminology, class descriptions, and output
filenames with accurate lung tutorial details, while preserving the documented
workflow purpose, requirements, and limitations where applicable.
---
Nitpick comments:
In `@tutorials/tutorial_01b_lung_gated_ct_to_usd.py`:
- Around line 141-150: Update the usd_project_name argument in the
WorkflowConvertImageToUSD initialization to use a lung-specific name such as
"lung_model" instead of "cardiac_model", keeping the remaining workflow
configuration unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 4025c926-9f8f-42b0-8e87-1afd927394ca
📒 Files selected for processing (113)
data/DirLab-4DCT/README.mddata/DirLab-4DCT/downloaded_data/Case10Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case10Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case1Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case2Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case3Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case4Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case5Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case6Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case7Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T00.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T10.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T20.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T30.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T40.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T50.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T60.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T70.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T80.mhddata/DirLab-4DCT/downloaded_data/Case8Deploy_T90.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T00.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T10.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T20.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T30.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T40.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T50.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T60.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T70.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T80.mhddata/DirLab-4DCT/downloaded_data/Case9Pack_T90.mhddata/DirLab-4DCT/downloaded_data/Convert4DCTToMHD.pydata/DirLab-4DCT/fix_downloaded_data.pyexperiments/Heart-Create_Statistical_Model/README.mdexperiments/Lung-GatedCT_To_USD/0-register_dirlab_4dct.pyexperiments/Lung-GatedCT_To_USD/Experiment_SegReg.pyexperiments/Lung-GatedCT_To_USD/data_dirlab_4d_ct.pysrc/physiotwin4d/data_download_tools.pysrc/physiotwin4d/segment_chest_total_segmentator.pytests/conftest.pytutorials/tutorial_01b_lung_gated_ct_to_usd.pytutorials/tutorial_04_fit_statistical_model_to_patient.pytutorials/tutorial_06_reconstruct_highres_4d_ct.py
💤 Files with no reviewable changes (1)
- tests/conftest.py
🚧 Files skipped from review as they are similar to previous changes (2)
- tutorials/tutorial_04_fit_statistical_model_to_patient.py
- src/physiotwin4d/segment_chest_total_segmentator.py
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Non-contrast heart models from TotalSegmentator are incomplete, but this update makes registration to a statistical model possible.
Summary by CodeRabbit
process()entry point (and refreshed related examples/terminology).