diff --git a/CLAUDE.md b/CLAUDE.md
index 7119223..b7c040c 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -5,6 +5,22 @@ Project guidance for Claude Code in this repository.
 Codex and other AI agents should use `AGENTS.md` as the primary shared
 instructions file. Claude-specific behavior and slash-command usage remain here.
 
+## Role:
+We are developing open-source code for scientific AI libraries. Leverage GPU-accelerated methods when appropriate.
+
+## Priorities (Ordered)
+1) accuracy
+2) clarity/maintainability/simplicity
+3) consistency with the rest of the platform and open source standards
+4) documentation
+5) testing
+
+## Behavior Guidelines
+1) Don't assume.  Don't hide confusion. Surface tradeoffs.
+2) Minimum code that solves the problem.  Nothing speculative.
+3) Touch only what you must.  Clean up only your own mess.
+4) Define success criteria.  Loop until verified.
+
 ## Commands
 
 **Python launcher:** Use `py` on this Windows system (not `python`).
@@ -47,8 +63,6 @@ py -m pytest tests/ --create-baselines
 
 ## Architecture
 
-Pipeline: `4D CT → Segmentation → Registration → Contour Extraction → USD Export`
-
 All classes inherit from `PhysioMotion4DBase` (`physiomotion4d_base.py`), which provides
 a shared logger. Use `self.log_info()`, `self.log_debug()` — never `print()`.
 
@@ -58,12 +72,13 @@ Regenerate it after any public API change: `py utils/generate_api_map.py`
 **Key data conventions:**
 - Images: `itk.Image`, axes X, Y, Z [, T] in LPS world space (ITK's native
   frame; `itk.imread` normalizes DICOM, NIfTI, MHA, and NRRD inputs to LPS)
+  stored using itk.imwrite with compression=True
 - 4D time series: shape `(X, Y, Z, T)` — never silently squeeze or permute axes
 - Surfaces: `pv.PolyData` in LPS (inherited from the source `itk.Image` via
   `itk.vtk_image_from_image`); converted to USD right-handed Y-up only at USD
   export by `vtk_to_usd.lps_points_to_usd` (USD +X=Left, +Y=Superior, +Z=Anterior)
 - Masks: ITK images with integer labels; consistent anatomy group IDs across all segmenters
-- Transforms: ITK composite transforms stored in `.hdf` files
+- Transforms: ITK composite transforms stored in `.hdf` files with compression
 - State axis order and shape explicitly in every docstring and comment that touches arrays
 
 ## Testing
@@ -71,18 +86,24 @@ Regenerate it after any public API change: `py utils/generate_api_map.py`
 - Baselines in `tests/baselines/` via Git LFS — run `git lfs pull` after cloning
 - `tests/conftest.py`: session-scoped fixtures chaining download → convert → segment → register
 - `src/physiomotion4d/test_tools.py`: baseline comparison utilities (`TestTools`, etc.)
-- Markers: `slow`, `requires_gpu`, `requires_data`, `experiment` (skipped by default)
-- Prefer synthetic `itk.Image` / `pv.PolyData` over real data; keep volumes ≤64 voxels/side
+- Markers: `slow`, `requires_gpu`, `requires_data`, `experiment`, `tutorial`
+- Prefer images from `ROOT/data/test/slicer_heart_small` for tests
+- Prefer storing results in subdirs `./results/<test_name>`
 
 ## Working Process
 
 Before editing any code:
 1. Read the relevant source file(s) in full.
 2. Summarize current behavior in 2–4 sentences.
-3. Propose a numbered plan; confirm before implementing non-trivial changes.
-4. Implement in small, reviewable diffs.
-5. Update docstrings and tests for every changed public method.
-6. Call out breaking changes explicitly.
+3. Identify success criteria / metrics
+4. Refer to *_tools.py files for commonly used routines
+5. Refer to workspace/reference_code (when available) for third-party libraries
+6. Propose a numbered plan; confirm before implementing non-trivial changes.
+7. Follow the behavior guidelines given above.
+8. Implement in small, reviewable diffs.
+9. Update docstrings and tests for every changed public method.
+10. Call out breaking changes explicitly.
+11. Do not commit changes or make pull requests unless specifically told to do so.
 
 Breaking changes are acceptable. Backward-compatibility shims are not.
 
@@ -113,3 +134,4 @@ Document via docstrings and inline comments.
 - `Optional[X]` not `X | None` (ruff `UP007` suppressed)
 - Breaking changes are acceptable — backward compatibility is not a priority
 - Max line length: 88 characters
+- Follow behavior guidelines.
diff --git a/README.md b/README.md
index 8a165a3..7a87fff 100644
--- a/README.md
+++ b/README.md
@@ -196,7 +196,7 @@ a CUDA-capable GPU are required for practical runtime.
 python -c "from physiomotion4d import DataDownloadTools; DataDownloadTools.DownloadSlicerHeartCTData('data/test')"
 
 physiomotion4d-convert-image-to-usd data/test/TruncalValve_4DCT.seq.nrrd \
-    --registration-method ants \
+    --registration-method ANTS \
     --output-dir output/quickstart \
     --project-name slicer_heart_quickstart
 ```
@@ -286,7 +286,7 @@ processor = WorkflowConvertImageToUSD(
     contrast_enhanced=True,
     output_directory="./results",
     project_name="cardiac_model",
-    registration_method='icon'  # or 'ants'
+    registration_method='ICON'  # or 'ANTS'
 )
 
 # Run complete workflow
diff --git a/docs/API_MAP.md b/docs/API_MAP.md
index 411e2cf..0a3e8b0 100644
--- a/docs/API_MAP.md
+++ b/docs/API_MAP.md
@@ -62,10 +62,6 @@ _Re-run `py utils/generate_api_map.py` whenever public APIs change._
   - `def group_for_id(self, label_id)` (line 132): Return the group containing *label_id*; :data:`OTHER_GROUP` if absent.
   - `def fill_other_group(self, id_range=range(1, 256), name_template='other_{id}')` (line 139): Populate the ``other`` group with any ids not already claimed.
 
-## src/physiomotion4d/cli/convert_ct_to_vtk.py
-
-- `def main()` (line 26): CLI entry point for CT to VTK conversion.
-
 ## src/physiomotion4d/cli/convert_image_4d_to_3d.py
 
 - `def main()` (line 20): CLI entry point for 4D-to-3D image conversion.
@@ -74,6 +70,10 @@ _Re-run `py utils/generate_api_map.py` whenever public APIs change._
 
 - `def main()` (line 14): Command-line interface for the Image-to-USD workflow.
 
+## src/physiomotion4d/cli/convert_image_to_vtk.py
+
+- `def main()` (line 26): CLI entry point for image to VTK conversion.
+
 ## src/physiomotion4d/cli/convert_vtk_to_usd.py
 
 - `def main()` (line 22): Command-line interface for VTK to USD conversion.
@@ -202,14 +202,15 @@ _Re-run `py utils/generate_api_map.py` whenever public APIs change._
 
 ## src/physiomotion4d/register_images_icon.py
 
-- **class RegisterImagesICON** (line 25): ICON-based deformable image registration implementation.
-  - `def __init__(self, log_level=logging.INFO)` (line 61): Initialize the ICON image registration class.
-  - `def set_weights_path(self, weights_path)` (line 79): Set a custom weights file for the uniGradICON network.
-  - `def set_number_of_iterations(self, number_of_iterations)` (line 93): Set the number of iterations for ICON registration.
-  - `def set_multi_modality(self, enable)` (line 101): Enable or disable multi-modality registration.
-  - `def set_mass_preservation(self, enable)` (line 118): Enable or disable mass preservation constraint.
-  - `def preprocess(self, image, modality='ct')` (line 135): Preprocess the image for ICON registration.
-  - `def registration_method(self, moving_image, moving_mask=None, moving_labelmap=None, moving_image_pre=None, initial_forward_transform=None)` (line 155): Register moving image to fixed image using ICON registration algorithm.
+- **class RegisterImagesICON** (line 32): ICON-based deformable image registration implementation.
+  - `def __init__(self, log_level=logging.INFO)` (line 68): Initialize the ICON image registration class.
+  - `def set_weights_path(self, weights_path)` (line 86): Set a custom weights file for the uniGradICON network.
+  - `def set_number_of_iterations(self, number_of_iterations)` (line 100): Set the number of iterations for ICON registration.
+  - `def set_multi_modality(self, enable)` (line 108): Enable or disable multi-modality registration.
+  - `def set_mass_preservation(self, enable)` (line 125): Enable or disable mass preservation constraint.
+  - `def preprocess(self, image, modality='ct')` (line 142): Preprocess the image for ICON registration.
+  - `def registration_method(self, moving_image, moving_mask=None, moving_labelmap=None, moving_image_pre=None, initial_forward_transform=None)` (line 162): Register moving image to fixed image using ICON registration algorithm.
+  - `def finetune(self, image_pairs, output_model_filename, mask_pairs=None, epochs=1, learning_rate=DEFAULT_FINETUNE_LEARNING_RATE)` (line 386): Fine-tune the ICON network on a cohort of image pairs.
 
 ## src/physiomotion4d/register_models_distance_maps.py
 
@@ -285,11 +286,11 @@ _Re-run `py utils/generate_api_map.py` whenever public APIs change._
 
 - **class SegmentHeartSimpleware** (line 23): Heart CT segmentation using Simpleware Medical's ASCardio module.
   - `def __init__(self, log_level=logging.INFO)` (line 58): Initialize the Simpleware Medical based heart segmentation.
-  - `def set_trim_mask_to_essentials(self, trim_mask)` (line 118): Set whether to trim mask to common and critical structures.
-  - `def set_simpleware_executable_path(self, path)` (line 126): Set the path to the Simpleware Medical console executable.
-  - `def segmentation_method(self, preprocessed_image)` (line 139): Run Simpleware Medical ASCardio segmentation on the preprocessed image.
-  - `def get_landmarks(self)` (line 339): Get the landmarks.
-  - `def trim_mask_to_essentials(self, labelmap_image)` (line 343): Trim mask to essentials.
+  - `def set_trim_branches(self, trim_branches)` (line 118): Enable trimming of pulmonary and great-vessel branches.
+  - `def set_simpleware_executable_path(self, path)` (line 133): Set the path to the Simpleware Medical console executable.
+  - `def segmentation_method(self, preprocessed_image)` (line 146): Run Simpleware Medical ASCardio segmentation on the preprocessed image.
+  - `def get_landmarks(self)` (line 346): Get the landmarks.
+  - `def trim_branches(self, labelmap_image)` (line 350): Trim pulmonary and great-vessel branches back to the cardiac region.
 
 ## src/physiomotion4d/test_tools.py
 
@@ -425,22 +426,22 @@ _Re-run `py utils/generate_api_map.py` whenever public APIs change._
 - `def read_vtk_file(filename, extract_surface=True)` (line 581): Auto-detect VTK file format and read appropriately.
 - `def validate_time_series_topology(mesh_data_sequence, filenames=None)` (line 609): Validate topology consistency across a time series of meshes.
 
-## src/physiomotion4d/workflow_convert_ct_to_vtk.py
+## src/physiomotion4d/workflow_convert_image_to_usd.py
+
+- **class WorkflowConvertImageToUSD** (line 41): Complete workflow for converting 4D CT images to dynamic USD models.
+  - `def __init__(self, input_filenames, contrast_enhanced, output_directory, project_name, reference_image_filename=None, number_of_registration_iterations=1, segmentation_method='ChestTotalSegmentator', registration_method='ICON', log_level=logging.INFO, save_registered_images=True, save_registration_transforms=True, save_labelmaps=True)` (line 49): Initialize the image-to-USD workflow.
+  - `def process(self)` (line 214): Execute the complete workflow from 4D CT to dynamic USD models.
+
+## src/physiomotion4d/workflow_convert_image_to_vtk.py
 
-- **class WorkflowConvertCTToVTK** (line 58): Segment a CT image and produce per-anatomy-group VTK surfaces and meshes.
-  - `def __init__(self, segmentation_method='total_segmentator', log_level=logging.INFO)` (line 98): Initialize the workflow.
+- **class WorkflowConvertImageToVTK** (line 58): Segment a CT image and produce per-anatomy-group VTK surfaces and meshes.
+  - `def __init__(self, segmentation_method='ChestTotalSegmentator', log_level=logging.INFO)` (line 98): Initialize the workflow.
   - `def run_workflow(self, input_image, contrast_enhanced_study=False, anatomy_groups=None)` (line 241): Segment the CT image and extract per-anatomy-group VTK objects.
   - `def save_surfaces(surfaces, output_dir, prefix='')` (line 344): Save each group surface to its own VTP file.
   - `def save_meshes(meshes, output_dir, prefix='')` (line 371): Save each group voxel mesh to its own VTU file.
   - `def save_combined_surface(surfaces, output_dir, prefix='')` (line 397): Merge all group surfaces into a single VTP file.
   - `def save_combined_mesh(meshes, output_dir, prefix='')` (line 432): Merge all group meshes into a single VTU file.
 
-## src/physiomotion4d/workflow_convert_image_to_usd.py
-
-- **class WorkflowConvertImageToUSD** (line 30): Complete workflow for converting 4D CT images to dynamic USD models.
-  - `def __init__(self, input_filenames, contrast_enhanced, output_directory, project_name, reference_image_filename=None, number_of_registration_iterations=1, registration_method='icon', log_level=logging.INFO, save_registered_images=True, save_registration_transforms=True, save_labelmaps=True)` (line 38): Initialize the image-to-USD workflow.
-  - `def process(self)` (line 184): Execute the complete workflow from 4D CT to dynamic USD models.
-
 ## src/physiomotion4d/workflow_convert_vtk_to_usd.py
 
 - **class WorkflowConvertVTKToUSD** (line 23): Workflow to convert one or more VTK files to USD with configurable
@@ -458,18 +459,18 @@ _Re-run `py utils/generate_api_map.py` whenever public APIs change._
 ## src/physiomotion4d/workflow_fit_statistical_model_to_patient.py
 
 - **class WorkflowFitStatisticalModelToPatient** (line 56): Register anatomical models using multi-stage ICP, mask-based, and image-based
-  - `def __init__(self, template_model, patient_models=None, patient_image=None, segmentation_method='simpleware_heart', log_level=logging.INFO)` (line 135): Initialize the model-to-image-and-model registration pipeline.
-  - `def set_mask_dilation_mm(self, mask_dilation_mm)` (line 356): Set mask dilation amount for auto-generated masks.
-  - `def set_roi_dilation_mm(self, roi_dilation_mm)` (line 365): Set ROI mask dilation amount.
-  - `def set_use_pca_registration(self, use_pca_registration, pca_model=None, pca_number_of_modes=0, pca_uses_surface=True)` (line 374): Set whether to use PCA-based registration and provide the PCA model.
-  - `def set_use_mask_to_mask_registration(self, use_mask_to_mask_registration)` (line 409): Set whether to use mask-to-mask registration.
-  - `def set_use_mask_to_image_registration(self, use_mask_to_image_registration, template_labelmap=None, template_labelmap_organ_mesh_ids=None, template_labelmap_organ_extra_ids=None, template_labelmap_background_ids=None)` (line 420): Set whether to use mask-to-image registration.
-  - `def register_model_to_model_icp(self)` (line 494): Perform ICP alignment of template model to patient model.
-  - `def register_model_to_model_pca(self)` (line 552): Perform PCA-based registration after ICP alignment.
-  - `def register_mask_to_mask(self, use_icon_refinement=False)` (line 678): Perform mask-based deformable registration of model to patient model.
-  - `def register_labelmap_to_image(self, use_icon_refinement=False)` (line 746): Perform labelmap-to-image refinement.
-  - `def transform_model(self, base_model=None)` (line 866): Apply registration transforms to the model.
-  - `def run_workflow(self, use_icon_registration_refinement=False)` (line 931): Execute the complete multi-stage registration workflow.
+  - `def __init__(self, template_model, patient_models=None, patient_image=None, segmentation_method='HeartSimpleware', log_level=logging.INFO)` (line 135): Initialize the model-to-image-and-model registration pipeline.
+  - `def set_mask_dilation_mm(self, mask_dilation_mm)` (line 361): Set mask dilation amount for auto-generated masks.
+  - `def set_roi_dilation_mm(self, roi_dilation_mm)` (line 370): Set ROI mask dilation amount.
+  - `def set_use_pca_registration(self, use_pca_registration, pca_model=None, pca_number_of_modes=0, pca_uses_surface=True)` (line 379): Set whether to use PCA-based registration and provide the PCA model.
+  - `def set_use_mask_to_mask_registration(self, use_mask_to_mask_registration)` (line 414): Set whether to use mask-to-mask registration.
+  - `def set_use_mask_to_image_registration(self, use_mask_to_image_registration, template_labelmap=None, template_labelmap_organ_mesh_ids=None, template_labelmap_organ_extra_ids=None, template_labelmap_background_ids=None)` (line 425): Set whether to use mask-to-image registration.
+  - `def register_model_to_model_icp(self)` (line 499): Perform ICP alignment of template model to patient model.
+  - `def register_model_to_model_pca(self)` (line 557): Perform PCA-based registration after ICP alignment.
+  - `def register_mask_to_mask(self, use_icon_refinement=False)` (line 683): Perform mask-based deformable registration of model to patient model.
+  - `def register_labelmap_to_image(self, use_icon_refinement=False)` (line 751): Perform labelmap-to-image refinement.
+  - `def transform_model(self, base_model=None)` (line 871): Apply registration transforms to the model.
+  - `def run_workflow(self, use_icon_registration_refinement=False)` (line 936): Execute the complete multi-stage registration workflow.
 
 ## src/physiomotion4d/workflow_reconstruct_highres_4d_ct.py
 
diff --git a/docs/api/cli/convert_ct_to_vtk.rst b/docs/api/cli/convert_ct_to_vtk.rst
deleted file mode 100644
index e910d8d..0000000
--- a/docs/api/cli/convert_ct_to_vtk.rst
+++ /dev/null
@@ -1,10 +0,0 @@
-=======================
-convert_ct_to_vtk (CLI)
-=======================
-
-.. automodule:: physiomotion4d.cli.convert_ct_to_vtk
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-See :doc:`../../cli_scripts/overview` for usage.
diff --git a/docs/api/cli/convert_image_to_vtk.rst b/docs/api/cli/convert_image_to_vtk.rst
new file mode 100644
index 0000000..c132590
--- /dev/null
+++ b/docs/api/cli/convert_image_to_vtk.rst
@@ -0,0 +1,10 @@
+==========================
+convert_image_to_vtk (CLI)
+==========================
+
+.. automodule:: physiomotion4d.cli.convert_image_to_vtk
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+See :doc:`../../cli_scripts/overview` for usage.
diff --git a/docs/api/cli/index.rst b/docs/api/cli/index.rst
index aa885c3..1e57083 100644
--- a/docs/api/cli/index.rst
+++ b/docs/api/cli/index.rst
@@ -19,7 +19,7 @@ Module Index.
    :maxdepth: 1
 
    convert_image_to_usd
-   convert_ct_to_vtk
+   convert_image_to_vtk
    convert_vtk_to_usd
    create_statistical_model
    fit_statistical_model_to_patient
diff --git a/docs/api/segmentation/totalsegmentator.rst b/docs/api/segmentation/totalsegmentator.rst
index 2b11776..4f38e21 100644
--- a/docs/api/segmentation/totalsegmentator.rst
+++ b/docs/api/segmentation/totalsegmentator.rst
@@ -67,7 +67,7 @@ Operational Notes
 
 TotalSegmentator model inference may download model assets and can be slow on a
 CPU-only environment. For repeatable workflows, prefer the tutorial scripts or
-the ``physiomotion4d-convert-ct-to-vtk`` CLI.
+the ``physiomotion4d-convert-image-to-vtk`` CLI.
 
 See Also
 ========
diff --git a/docs/api/workflows.rst b/docs/api/workflows.rst
index 0fe4a36..6b20255 100644
--- a/docs/api/workflows.rst
+++ b/docs/api/workflows.rst
@@ -3,7 +3,7 @@ Workflow Classes
 ================
 
 .. module:: physiomotion4d.workflow_convert_image_to_usd
-.. module:: physiomotion4d.workflow_convert_ct_to_vtk
+.. module:: physiomotion4d.workflow_convert_image_to_vtk
 .. module:: physiomotion4d.workflow_convert_vtk_to_usd
 .. module:: physiomotion4d.workflow_create_statistical_model
 .. module:: physiomotion4d.workflow_fit_statistical_model_to_patient
@@ -26,7 +26,7 @@ Available Workflows
      - Typical use
    * - :class:`WorkflowConvertImageToUSD`
      - Convert a 4D cardiac CT sequence into animated USD anatomy.
-   * - :class:`WorkflowConvertCTToVTK`
+   * - :class:`WorkflowConvertImageToVTK`
      - Segment one CT image and export anatomy-group VTK surfaces and meshes.
    * - :class:`WorkflowConvertVTKToUSD`
      - Convert VTK/VTP/VTU meshes or time series into USD.
@@ -55,15 +55,16 @@ Convert Image to USD
        contrast_enhanced=True,
        output_directory="./results",
        project_name="patient_001",
-       registration_method="ants",
+       segmentation_method="ChestTotalSegmentator",
+       registration_method="ANTS",
    )
 
    final_usd = workflow.process()
 
-CT to VTK
-=========
+Image to VTK
+============
 
-.. autoclass:: WorkflowConvertCTToVTK
+.. autoclass:: WorkflowConvertImageToVTK
    :members:
    :undoc-members:
    :show-inheritance:
@@ -72,17 +73,17 @@ CT to VTK
 
    import itk
 
-   from physiomotion4d import WorkflowConvertCTToVTK
+   from physiomotion4d import WorkflowConvertImageToVTK
 
    image = itk.imread("chest_ct.nii.gz")
-   workflow = WorkflowConvertCTToVTK(segmentation_method="total_segmentator")
+   workflow = WorkflowConvertImageToVTK(segmentation_method="ChestTotalSegmentator")
    result = workflow.run_workflow(
        input_image=image,
        contrast_enhanced_study=True,
        anatomy_groups=["heart", "major_vessels"],
    )
 
-   WorkflowConvertCTToVTK.save_combined_surface(
+   WorkflowConvertImageToVTK.save_combined_surface(
        result["surfaces"],
        "./output",
        prefix="patient01",
diff --git a/docs/architecture.rst b/docs/architecture.rst
index 93f4a40..7524cd8 100644
--- a/docs/architecture.rst
+++ b/docs/architecture.rst
@@ -33,7 +33,7 @@ Data Flow
    ContourTools + TransformTools
           |
           v
-   WorkflowConvertCTToVTK / ConvertVTKToUSD / WorkflowConvertVTKToUSD
+   WorkflowConvertImageToVTK / ConvertVTKToUSD / WorkflowConvertVTKToUSD
           |
           v
    OpenUSD assets for NVIDIA Omniverse
@@ -45,7 +45,7 @@ Primary Workflows
    Converts a 4D cardiac CT file or 3D CT time series into registered anatomy
    contours and painted animated USD files.
 
-``WorkflowConvertCTToVTK``
+``WorkflowConvertImageToVTK``
    Segments a 3D CT image and exports anatomy groups as VTK surfaces and voxel
    meshes.
 
@@ -89,7 +89,7 @@ The installed CLI commands in ``pyproject.toml`` are thin wrappers around the
 workflow classes. They are the preferred examples for executable API usage:
 
 * ``physiomotion4d-convert-image-to-usd``
-* ``physiomotion4d-convert-ct-to-vtk``
+* ``physiomotion4d-convert-image-to-vtk``
 * ``physiomotion4d-create-statistical-model``
 * ``physiomotion4d-fit-statistical-model-to-patient``
 * ``physiomotion4d-convert-vtk-to-usd``
diff --git a/docs/cli_scripts/best_practices.rst b/docs/cli_scripts/best_practices.rst
index fd01ed6..532839e 100644
--- a/docs/cli_scripts/best_practices.rst
+++ b/docs/cli_scripts/best_practices.rst
@@ -171,7 +171,7 @@ Registration Failure
 **Solutions**:
    * Select better reference image (less motion, better quality)
    * Increase ``--registration-iterations``
-   * Try alternative registration method (``--registration-method ants``)
+   * Try alternative registration method (``--registration-method ANTS``)
    * Verify phases are temporally ordered correctly
 
 Memory Errors
diff --git a/docs/cli_scripts/byod_tutorials.rst b/docs/cli_scripts/byod_tutorials.rst
new file mode 100644
index 0000000..22881f2
--- /dev/null
+++ b/docs/cli_scripts/byod_tutorials.rst
@@ -0,0 +1,240 @@
+.. _byod_tutorials:
+
+Bring Your Own Data — DICOM & VTK to USD
+=========================================
+
+PhysioMotion4D lets you convert your own medical imaging data — whether
+DICOM-derived NIfTI volumes or VTK surface meshes — into OpenUSD for
+interactive visualization in NVIDIA Omniverse.  Both 3D (single
+volume/mesh) and 4D (time-series) inputs are supported.  The CLI and
+Python API are **identical** for 3D and 4D inputs; the only difference
+is how many files you pass in.
+
+.. note::
+
+   PhysioMotion4D is a research tool and has **not** been validated for
+   clinical use.  Outputs must not be used for diagnostic or therapeutic
+   decisions without independent validation.
+
+Installation
+------------
+
+Install the package with CUDA support (recommended for GPU acceleration)
+or the CPU-only variant:
+
+.. code-block:: bash
+
+   # Recommended — CUDA-enabled
+   pip install physiomotion4d[cuda13]
+
+   # CPU-only
+   pip install physiomotion4d
+
+Verify that both relevant CLI entry-points are available after installation:
+
+.. code-block:: bash
+
+   physiomotion4d-convert-image-to-usd --help
+   physiomotion4d-convert-vtk-to-usd --help
+
+See :doc:`/installation` for prerequisites, CUDA version requirements, and
+source-based installation.
+
+DICOM to USD
+------------
+
+Raw DICOM images must first be converted to NIfTI with a tool such as
+`dcm2niix <https://github.com/rordenlab/dcm2niix>`_ before being passed
+to PhysioMotion4D.
+
+3D — Single Volume
+~~~~~~~~~~~~~~~~~~
+
+Pass a single ``.nii.gz`` file to produce a static USD scene.
+
+**CLI:**
+
+.. code-block:: bash
+
+   physiomotion4d-convert-image-to-usd \
+       patient_ct.nii.gz \
+       --output patient_heart.usd
+
+**Python API:**
+
+.. code-block:: python
+
+   import physiomotion4d as pm4d
+
+   wf = pm4d.WorkflowConvertImageToUSD()
+   wf.input_image = "patient_ct.nii.gz"
+   wf.output_file = "patient_heart.usd"
+   wf.run_workflow()
+
+.. note::
+
+   If your source data is raw DICOM, run ``dcm2niix -z y -o output_dir
+   dicom_dir/`` first to produce the ``.nii.gz`` input file expected by
+   this command.
+
+4D — Gated CT Time Series
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Pass multiple per-phase volumes (glob or explicit list) to produce an
+animated USD scene.  Use ``--fps`` to control playback rate and
+``--reference-frame`` to choose the registration anchor phase (0-indexed).
+
+**CLI:**
+
+.. code-block:: bash
+
+   physiomotion4d-convert-image-to-usd \
+       phase_*.nii.gz \
+       --output heart_animated.usd \
+       --fps 25 \
+       --reference-frame 0
+
+**Python API:**
+
+.. code-block:: python
+
+   import glob
+   import physiomotion4d as pm4d
+
+   wf = pm4d.WorkflowConvertImageToUSD()
+   wf.input_images = sorted(glob.glob("phase_*.nii.gz"))
+   wf.output_file  = "heart_animated.usd"
+   wf.fps            = 25
+   wf.reference_frame = 0
+   wf.run_workflow()
+
+The resulting USD file contains a time-sampled mesh sequence that plays
+back when you press **Play** in Omniverse USD Composer.
+
+VTK to USD
+----------
+
+3D — Single Mesh
+~~~~~~~~~~~~~~~~
+
+Pass a single ``.vtp`` file.  Use ``--appearance`` to control material
+style and ``--no-split`` to skip the default connected-component split.
+
+**CLI:**
+
+.. code-block:: bash
+
+   # Default — split by connected component, anatomy material
+   physiomotion4d-convert-vtk-to-usd heart.vtp \
+       --output heart.usd \
+       --appearance anatomy \
+       --anatomy-type heart
+
+   # Solid colour, no splitting
+   physiomotion4d-convert-vtk-to-usd mesh.vtp \
+       --output mesh_red.usd \
+       --appearance solid \
+       --color 0.8 0.1 0.1 \
+       --no-split
+
+**Python API:**
+
+.. code-block:: python
+
+   import physiomotion4d as pm4d
+
+   wf = pm4d.WorkflowConvertVTKToUSD()
+   wf.input_files  = ["heart.vtp"]
+   wf.output_file  = "heart.usd"
+   wf.appearance   = "anatomy"
+   wf.anatomy_type = "heart"
+   wf.run()
+
+4D — Mesh Time Series
+~~~~~~~~~~~~~~~~~~~~~
+
+Pass a glob of per-frame files.  The ``--fps`` flag controls playback
+rate.  For scalar colormaps, combine ``--primvar``, ``--cmap``, and
+``--intensity-range``.
+
+**CLI:**
+
+.. code-block:: bash
+
+   # Animated mesh sequence
+   physiomotion4d-convert-vtk-to-usd frame_*.vtp \
+       --output heart_animation.usd \
+       --fps 30
+
+   # Animated with scalar colormap (e.g. wall stress)
+   physiomotion4d-convert-vtk-to-usd frame_*.vtk \
+       --output stress_animation.usd \
+       --fps 30 \
+       --appearance colormap \
+       --primvar vtk_point_stress_c0 \
+       --cmap viridis \
+       --intensity-range 0 500
+
+**Python API:**
+
+.. code-block:: python
+
+   import glob
+   import physiomotion4d as pm4d
+
+   wf = pm4d.WorkflowConvertVTKToUSD()
+   wf.input_files      = sorted(glob.glob("frame_*.vtk"))
+   wf.output_file      = "stress_animation.usd"
+   wf.fps              = 30
+   wf.appearance       = "colormap"
+   wf.primvar          = "vtk_point_stress_c0"
+   wf.cmap             = "viridis"
+   wf.intensity_range  = (0, 500)
+   wf.run()
+
+**Lower-level in-memory conversion with** ``ConvertVTKToUSD``**:**
+
+For programmatic pipelines where meshes are already in memory, use the
+lower-level :class:`physiomotion4d.ConvertVTKToUSD` class directly:
+
+.. code-block:: python
+
+   import pyvista as pv
+   import physiomotion4d as pm4d
+
+   # Load or construct meshes in memory
+   meshes = [pv.read(f"frame_{i:04d}.vtp") for i in range(10)]
+
+   converter = pm4d.ConvertVTKToUSD(output_file="output.usd", fps=30)
+   for i, mesh in enumerate(meshes):
+       converter.add_frame(mesh, frame_index=i)
+   converter.write()
+
+Viewing Results
+---------------
+
+**Quick preview with PyVista (no Omniverse required):**
+
+.. code-block:: python
+
+   import pyvista as pv
+
+   mesh = pv.read("output.usd")
+   mesh.plot()
+
+**In NVIDIA Omniverse:**
+
+Open **Omniverse USD Composer**, drag your ``.usd`` file onto the
+viewport, then press **Play** (spacebar) to watch the animation.  For
+4D cardiac data, use the **Timeline** panel to scrub through phases.
+
+See Also
+--------
+
+- :doc:`/installation`
+- :doc:`/quickstart`
+- :doc:`/cli_scripts/heart_gated_ct`
+- :doc:`/cli_scripts/vtk_to_usd`
+- :doc:`/api/workflows`
+- :doc:`/examples`
+- :doc:`/troubleshooting`
diff --git a/docs/cli_scripts/heart_gated_ct.rst b/docs/cli_scripts/heart_gated_ct.rst
index 059c2d8..d42a975 100644
--- a/docs/cli_scripts/heart_gated_ct.rst
+++ b/docs/cli_scripts/heart_gated_ct.rst
@@ -111,8 +111,8 @@ Optional Arguments
      - 1
      - Number of registration refinement iterations
    * - ``--registration-method``
-     - ``icon``
-     - Registration method: ``icon`` or ``ants``
+     - ``ICON``
+     - Registration method: ``ICON`` or ``ANTS``
 
 Processing Pipeline
 ===================
@@ -222,7 +222,7 @@ With ANTs Registration
 
    physiomotion4d-convert-image-to-usd cardiac.nrrd \
        --contrast \
-       --registration-method ants \
+       --registration-method ANTS \
        --registration-iterations 50
 
 Best Practices
@@ -289,7 +289,7 @@ Registration Failures
 **Registration not converging**
    * Try different reference image (better quality phase)
    * Increase ``--registration-iterations``
-   * Switch registration method (``--registration-method ants``)
+   * Switch registration method (``--registration-method ANTS``)
 
 **Excessive deformation**
    * Verify sufficient temporal overlap between phases
diff --git a/docs/cli_scripts/overview.rst b/docs/cli_scripts/overview.rst
index 60058b4..2ed59a4 100644
--- a/docs/cli_scripts/overview.rst
+++ b/docs/cli_scripts/overview.rst
@@ -51,8 +51,8 @@ Current Scripts
      - Description
    * - :doc:`heart_gated_ct`
      - Process cardiac gated CT to animated heart models with physiological motion
-   * - ``physiomotion4d-convert-ct-to-vtk``
-     - Segment one CT image and export anatomy-group VTK surfaces and meshes
+   * - ``physiomotion4d-convert-image-to-vtk``
+     - Segment one 3D image and export anatomy-group VTK surfaces and meshes
    * - ``physiomotion4d-convert-image-4d-to-3d``
      - Split a 4D medical image into a 3D time series using ITK readers
    * - :doc:`create_statistical_model`
diff --git a/docs/developer/architecture.rst b/docs/developer/architecture.rst
index ccbf06b..a8b2f55 100644
--- a/docs/developer/architecture.rst
+++ b/docs/developer/architecture.rst
@@ -38,8 +38,8 @@ Workflow Classes
    Orchestrates 4D CT loading, segmentation, image registration, contour
    transformation, and animated USD generation.
 
-``WorkflowConvertCTToVTK``
-   Converts one CT image into labeled VTK surface and voxel-mesh outputs.
+``WorkflowConvertImageToVTK``
+   Converts one 3D image into labeled VTK surface and voxel-mesh outputs.
 
 ``WorkflowCreateStatisticalModel``
    Builds a PCA statistical shape model from aligned population meshes.
diff --git a/docs/developer/workflows.rst b/docs/developer/workflows.rst
index a8869d5..5c0f8e8 100644
--- a/docs/developer/workflows.rst
+++ b/docs/developer/workflows.rst
@@ -16,8 +16,8 @@ Current Workflow Mapping
      - Workflow class
    * - ``physiomotion4d-convert-image-to-usd``
      - :class:`physiomotion4d.WorkflowConvertImageToUSD`
-   * - ``physiomotion4d-convert-ct-to-vtk``
-     - :class:`physiomotion4d.WorkflowConvertCTToVTK`
+   * - ``physiomotion4d-convert-image-to-vtk``
+     - :class:`physiomotion4d.WorkflowConvertImageToVTK`
    * - ``physiomotion4d-convert-vtk-to-usd``
      - :class:`physiomotion4d.WorkflowConvertVTKToUSD`
    * - ``physiomotion4d-create-statistical-model``
@@ -39,7 +39,7 @@ Workflow Example
        contrast_enhanced=True,
        output_directory="./results",
        project_name="patient_001",
-       registration_method="ants",
+       registration_method="ANTS",
    )
 
    final_usd = workflow.process()
diff --git a/docs/examples.rst b/docs/examples.rst
index 3ca3d99..283e018 100644
--- a/docs/examples.rst
+++ b/docs/examples.rst
@@ -35,7 +35,7 @@ Complete end-to-end cardiac CT processing:
        contrast_enhanced=True,
        output_directory="./results",
        project_name="patient_001",
-       registration_method="ants",
+       registration_method="ANTS",
    )
 
    # Run complete workflow
@@ -411,7 +411,7 @@ Batch process multiple datasets:
            contrast_enhanced=True,
            output_directory=f"results/{patient_id}",
            project_name=patient_id,
-           registration_method="ants",
+           registration_method="ANTS",
        )
 
        try:
@@ -481,7 +481,7 @@ Run the supported end-to-end workflow API:
        contrast_enhanced=True,
        output_directory="./results",
        project_name="cardiac_model",
-       registration_method="ants",
+       registration_method="ANTS",
    )
 
    final_usd = workflow.process()
diff --git a/docs/quickstart.rst b/docs/quickstart.rst
index 68fed1c..d719f87 100644
--- a/docs/quickstart.rst
+++ b/docs/quickstart.rst
@@ -71,7 +71,7 @@ CUDA-capable GPU are required for practical runtime.
    python -c "from physiomotion4d import DataDownloadTools; DataDownloadTools.DownloadSlicerHeartCTData('data/test')"
 
    physiomotion4d-convert-image-to-usd data/test/TruncalValve_4DCT.seq.nrrd \
-       --registration-method ants \
+       --registration-method ANTS \
        --output-dir output/quickstart \
        --project-name slicer_heart_quickstart
 
@@ -115,7 +115,7 @@ For more control, use the Python API:
        contrast_enhanced=True,
        output_directory="./results",
        project_name="cardiac_model",
-       registration_method="ants",
+       registration_method="ANTS",
    )
 
 **Step 3: Run the workflow**
@@ -150,7 +150,7 @@ For more control over individual steps:
        contrast_enhanced=True,
        output_directory="./results",
        project_name="cardiac_model",
-       registration_method="ants",
+       registration_method="ANTS",
    )
 
    final_usd = workflow.process()
@@ -312,7 +312,7 @@ Common Issues
 
 * Resample or crop the input image before running the workflow
 * Process fewer frames at once
-* Use ANTs registration with ``--registration-method ants`` when CUDA is unavailable
+* Use ANTs registration with ``--registration-method ANTS`` when CUDA is unavailable
 
 **Segmentation quality issues**
 
diff --git a/docs/troubleshooting.rst b/docs/troubleshooting.rst
index 659d733..546b954 100644
--- a/docs/troubleshooting.rst
+++ b/docs/troubleshooting.rst
@@ -15,7 +15,7 @@ CUDA Out of Memory
 **Solutions**:
 
 1. Resample or crop the input image before running the workflow.
-2. Use ``--registration-method ants`` when CUDA is unavailable.
+2. Use ``--registration-method ANTS`` when CUDA is unavailable.
 3. Process fewer frames per run.
 
 CUDA Version Mismatch
@@ -93,7 +93,7 @@ Registration Not Converging
 
    .. code-block:: bash
 
-      physiomotion4d-convert-image-to-usd cardiac_4d.nrrd --registration-method ants
+      physiomotion4d-convert-image-to-usd cardiac_4d.nrrd --registration-method ANTS
 
 3. Check image orientation and spacing
 
diff --git a/docs/tutorials.rst b/docs/tutorials.rst
index 781884e..0634ee8 100644
--- a/docs/tutorials.rst
+++ b/docs/tutorials.rst
@@ -121,7 +121,7 @@ Script
    ``tutorials/tutorial_02_ct_to_vtk.py``
 
 Workflow
-   ``WorkflowConvertCTToVTK``
+   ``WorkflowConvertImageToVTK``
 
 Dataset
    Slicer-Heart-CT, prepared before running the tutorial.
@@ -222,7 +222,7 @@ Script
    ``tutorials/tutorial_07_dirlab_pca_model.py``
 
 Workflow
-   ``WorkflowConvertCTToVTK``, ``WorkflowCreateStatisticalModel``, and
+   ``WorkflowConvertImageToVTK``, ``WorkflowCreateStatisticalModel``, and
    ``WorkflowFitStatisticalModelToPatient``
 
 Dataset
diff --git a/experiments/Heart-Simpleware_Segmentation/simpleware_heart_segmentation.py b/experiments/Heart-Simpleware_Segmentation/simpleware_heart_segmentation.py
index 4f40d74..0def33e 100644
--- a/experiments/Heart-Simpleware_Segmentation/simpleware_heart_segmentation.py
+++ b/experiments/Heart-Simpleware_Segmentation/simpleware_heart_segmentation.py
@@ -274,7 +274,7 @@
     heart_array = itk.array_from_image(result["heart"])
     vessels_array = itk.array_from_image(result["major_vessels"])
 
-    labelmap_essentials = segmenter.trim_mask_to_essentials(result["labelmap"])
+    labelmap_essentials = segmenter.trim_branches(result["labelmap"])
     labelmap_essentials_array = itk.array_from_image(labelmap_essentials)
 
     # Select middle slice
diff --git a/experiments/Heart-Statistical_Model_To_Patient/heart_model_to_patient-CHOPValve.py b/experiments/Heart-Statistical_Model_To_Patient/heart_model_to_patient-CHOPValve.py
index 0c00e15..3a2c53b 100644
--- a/experiments/Heart-Statistical_Model_To_Patient/heart_model_to_patient-CHOPValve.py
+++ b/experiments/Heart-Statistical_Model_To_Patient/heart_model_to_patient-CHOPValve.py
@@ -51,7 +51,7 @@
 registrar = WorkflowFitStatisticalModelToPatient(
     template_model=template_model,
     patient_image=patient_image,
-    segmentation_method="simpleware_heart",
+    segmentation_method="HeartSimpleware",
 )
 
 registrar.set_use_pca_registration(
diff --git a/pyproject.toml b/pyproject.toml
index 379c8f0..11c2f61 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -160,7 +160,7 @@ Repository = "https://github.com/Project-MONAI/physiomotion4d.git"
 [project.scripts]
 # CLI commands installed via pip
 # Entry points reference the main() functions in the cli submodule
-physiomotion4d-convert-ct-to-vtk = "physiomotion4d.cli.convert_ct_to_vtk:main"
+physiomotion4d-convert-image-to-vtk = "physiomotion4d.cli.convert_image_to_vtk:main"
 physiomotion4d-convert-image-4d-to-3d = "physiomotion4d.cli.convert_image_4d_to_3d:main"
 physiomotion4d-convert-image-to-usd = "physiomotion4d.cli.convert_image_to_usd:main"
 physiomotion4d-convert-vtk-to-usd = "physiomotion4d.cli.convert_vtk_to_usd:main"
@@ -236,6 +236,8 @@ module = [
     "SimpleITK",
     "SimpleITK.*",
     "sklearn.*",
+    "torch",
+    "torch.*",
     "totalsegmentator.*",
     "trimesh",
     "trimesh.*",
diff --git a/src/physiomotion4d/__init__.py b/src/physiomotion4d/__init__.py
index c1f5071..9fb2c24 100644
--- a/src/physiomotion4d/__init__.py
+++ b/src/physiomotion4d/__init__.py
@@ -68,7 +68,7 @@
 from .usd_tools import USDTools
 
 # Core workflow processor
-from .workflow_convert_ct_to_vtk import WorkflowConvertCTToVTK
+from .workflow_convert_image_to_vtk import WorkflowConvertImageToVTK
 from .workflow_convert_image_to_usd import WorkflowConvertImageToUSD
 from .workflow_convert_vtk_to_usd import WorkflowConvertVTKToUSD
 from .workflow_reconstruct_highres_4d_ct import WorkflowReconstructHighres4DCT
@@ -79,7 +79,7 @@
 
 __all__ = [
     # Workflow classes
-    "WorkflowConvertCTToVTK",
+    "WorkflowConvertImageToVTK",
     "WorkflowConvertImageToUSD",
     "WorkflowConvertVTKToUSD",
     "WorkflowCreateStatisticalModel",
diff --git a/src/physiomotion4d/cli/convert_image_to_usd.py b/src/physiomotion4d/cli/convert_image_to_usd.py
index 317b130..58c5f0c 100644
--- a/src/physiomotion4d/cli/convert_image_to_usd.py
+++ b/src/physiomotion4d/cli/convert_image_to_usd.py
@@ -28,7 +28,10 @@ def main() -> int:
   %(prog)s input.nrrd --reference-image ref.mha --registration-iterations 50
 
   # Use ANTs registration instead of ICON
-  %(prog)s input.nrrd --contrast --registration-method ants
+  %(prog)s input.nrrd --contrast --registration-method ANTS
+
+  # Use the cardiac-only Simpleware segmentation backend
+  %(prog)s input.nrrd --segmentation-method HeartSimpleware
         """,
     )
 
@@ -64,11 +67,20 @@ def main() -> int:
         default=1,
         help="Number of registration iterations (default: 1)",
     )
+    parser.add_argument(
+        "--segmentation-method",
+        choices=["ChestTotalSegmentator", "HeartSimpleware"],
+        default="ChestTotalSegmentator",
+        help=(
+            "Segmentation backend to use: ChestTotalSegmentator (default) "
+            "or HeartSimpleware."
+        ),
+    )
     parser.add_argument(
         "--registration-method",
-        choices=["ants", "icon"],
-        default="icon",
-        help="Registration method to use: ants or icon (default: icon)",
+        choices=["ANTS", "ICON"],
+        default="ICON",
+        help="Registration method to use: ANTS or ICON (default: ICON)",
     )
 
     args = parser.parse_args()
@@ -91,6 +103,7 @@ def main() -> int:
             project_name=args.project_name,
             reference_image_filename=args.reference_image,
             number_of_registration_iterations=args.registration_iterations,
+            segmentation_method=args.segmentation_method,
             registration_method=args.registration_method,
         )
     except Exception as e:
diff --git a/src/physiomotion4d/cli/convert_ct_to_vtk.py b/src/physiomotion4d/cli/convert_image_to_vtk.py
similarity index 88%
rename from src/physiomotion4d/cli/convert_ct_to_vtk.py
rename to src/physiomotion4d/cli/convert_image_to_vtk.py
index b4d91b3..ff29872 100644
--- a/src/physiomotion4d/cli/convert_ct_to_vtk.py
+++ b/src/physiomotion4d/cli/convert_image_to_vtk.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python
-"""Command-line interface for the CT-to-VTK segmentation workflow.
+"""Command-line interface for the image-to-VTK segmentation workflow.
 
-Segments a 3D CT image using a chosen backend and writes per-anatomy-group VTP
+Segments a 3D image using a chosen backend and writes per-anatomy-group VTP
 surfaces and VTU voxel meshes annotated with anatomy labels and colors.
 """
 
@@ -20,13 +20,13 @@
     "contrast",
 )
 
-SEGMENTATION_METHODS = ("total_segmentator", "simpleware_heart")
+SEGMENTATION_METHODS = ("ChestTotalSegmentator", "HeartSimpleware")
 
 
 def main() -> int:
-    """CLI entry point for CT to VTK conversion."""
+    """CLI entry point for image to VTK conversion."""
     parser = argparse.ArgumentParser(
-        description="Segment a CT image and export anatomy groups as VTK surfaces and meshes.",
+        description="Segment a 3D image and export anatomy groups as VTK surfaces and meshes.",
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="""
 Anatomy groups
@@ -54,7 +54,7 @@ def main() -> int:
   # Simpleware heart-only, cardiac anatomy groups, combined output
   %(prog)s \\
     --input-image chest_ct.nii.gz \\
-    --segmentation-method simpleware_heart \\
+    --segmentation-method HeartSimpleware \\
     --anatomy-groups heart major_vessels \\
     --output-dir ./results \\
     --output-prefix patient01
@@ -71,7 +71,7 @@ def main() -> int:
     parser.add_argument(
         "--input-image",
         required=True,
-        help="Path to the input CT image (.nii.gz, .nrrd, .mha, …).",
+        help="Path to the input 3D image (.nii.gz, .nrrd, .mha, …).",
     )
     parser.add_argument(
         "--output-dir",
@@ -82,9 +82,11 @@ def main() -> int:
     # ── Segmentation ──────────────────────────────────────────────────────
     parser.add_argument(
         "--segmentation-method",
-        default="total_segmentator",
+        default="ChestTotalSegmentator",
         choices=list(SEGMENTATION_METHODS),
-        help=("Segmentation backend.  total_segmentator (default) | simpleware_heart"),
+        help=(
+            "Segmentation backend.  ChestTotalSegmentator (default) | HeartSimpleware"
+        ),
     )
     parser.add_argument(
         "--contrast",
@@ -151,9 +153,9 @@ def main() -> int:
     print("=" * 70)
 
     try:
-        from physiomotion4d import WorkflowConvertCTToVTK
+        from physiomotion4d import WorkflowConvertImageToVTK
 
-        workflow = WorkflowConvertCTToVTK(
+        workflow = WorkflowConvertImageToVTK(
             segmentation_method=args.segmentation_method,
         )
         result = workflow.run_workflow(
@@ -183,13 +185,13 @@ def main() -> int:
         if args.split_files:
             # One file per anatomy group
             if surfaces:
-                saved_surfaces = WorkflowConvertCTToVTK.save_surfaces(
+                saved_surfaces = WorkflowConvertImageToVTK.save_surfaces(
                     surfaces, args.output_dir, prefix=prefix
                 )
                 for group, path in saved_surfaces.items():
                     print(f"  Surface  [{group:15s}] → {path}")
             if meshes:
-                saved_meshes = WorkflowConvertCTToVTK.save_meshes(
+                saved_meshes = WorkflowConvertImageToVTK.save_meshes(
                     meshes, args.output_dir, prefix=prefix
                 )
                 for group, path in saved_meshes.items():
@@ -197,12 +199,12 @@ def main() -> int:
         else:
             # Combined single-file output
             if surfaces:
-                surface_file = WorkflowConvertCTToVTK.save_combined_surface(
+                surface_file = WorkflowConvertImageToVTK.save_combined_surface(
                     surfaces, args.output_dir, prefix=prefix
                 )
                 print(f"  Combined surface → {surface_file}")
             if meshes:
-                mesh_file = WorkflowConvertCTToVTK.save_combined_mesh(
+                mesh_file = WorkflowConvertImageToVTK.save_combined_mesh(
                     meshes, args.output_dir, prefix=prefix
                 )
                 print(f"  Combined mesh    → {mesh_file}")
diff --git a/src/physiomotion4d/register_images_icon.py b/src/physiomotion4d/register_images_icon.py
index 9cc93a7..8f60a2a 100644
--- a/src/physiomotion4d/register_images_icon.py
+++ b/src/physiomotion4d/register_images_icon.py
@@ -10,17 +10,24 @@
 """
 
 import logging
-from typing import Optional, Union
+from collections.abc import Sequence
+from pathlib import Path
+from typing import Any, Optional, Union
 
 import icon_registration as icon
 import icon_registration.itk_wrapper
 import itk
+import numpy as np
+import torch
+import torch.nn.functional as F
 from unigradicon import get_multigradicon, get_unigradicon
 from unigradicon import preprocess as unigradicon_preprocess
 
 from physiomotion4d.register_images_base import RegisterImagesBase
 from physiomotion4d.transform_tools import TransformTools
 
+DEFAULT_FINETUNE_LEARNING_RATE = 2e-5
+
 
 class RegisterImagesICON(RegisterImagesBase):
     """ICON-based deformable image registration implementation.
@@ -226,20 +233,7 @@ def registration_method(
         moving_effective_mask = moving_labelmap if use_labelmaps else moving_mask
         fixed_effective_mask = self.fixed_labelmap if use_labelmaps else self.fixed_mask
 
-        if self.net is None:
-            if self.use_multi_modality:
-                self.net = get_multigradicon(
-                    loss_fn=icon.LNCC(sigma=5),
-                    # loss_fn=icon.losses.MINDSSC(radius=2, dilation=2),
-                    apply_intensity_conservation_loss=self.use_mass_preservation,
-                    weights_location=self.weights_path,
-                )
-            else:
-                self.net = get_unigradicon(
-                    loss_fn=icon.LNCC(sigma=5),
-                    apply_intensity_conservation_loss=self.use_mass_preservation,
-                    weights_location=self.weights_path,
-                )
+        self._ensure_net()
 
         inverse_transform = None
         forward_transform = None
@@ -290,3 +284,209 @@ def registration_method(
             "inverse_transform": inverse_transform,
             "loss": loss,
         }
+
+    def _ensure_net(self) -> None:
+        """Lazily instantiate the ICON network using current configuration.
+
+        Honors set_weights_path() if a custom checkpoint has been requested,
+        otherwise loads the default UniGradICON / MultiGradICON pretrained
+        weights.
+        """
+        if self.net is not None:
+            return
+        if self.use_multi_modality:
+            self.net = get_multigradicon(
+                loss_fn=icon.LNCC(sigma=5),
+                apply_intensity_conservation_loss=self.use_mass_preservation,
+                weights_location=self.weights_path,
+            )
+        else:
+            self.net = get_unigradicon(
+                loss_fn=icon.LNCC(sigma=5),
+                apply_intensity_conservation_loss=self.use_mass_preservation,
+                weights_location=self.weights_path,
+            )
+
+    def _image_to_resized_tensor(
+        self, image: itk.Image, shape: torch.Size
+    ) -> torch.Tensor:
+        """Convert an itk image to a torch tensor resized to the net's input grid.
+
+        Mirrors the trilinear preprocessing path used by
+        ``icon_registration.itk_wrapper.register_pair`` exactly.
+
+        Axis ordering:
+            - Input ``image`` is a scalar (single-channel) 3D ``itk.Image`` with
+              ITK world-axis order (X, Y, Z). ``np.array(image)`` returns a
+              C-contiguous array with axes **reversed** to (Z, Y, X) — ITK's
+              standard numpy view.
+            - ``torch.Tensor(arr)`` casts to ``float32`` (PyTorch's
+              ``FloatTensor`` constructor) regardless of the source dtype.
+            - Indexing with ``[None, None]`` prepends batch and channel
+              singleton axes, producing shape ``(1, 1, Z, Y, X)``. This is
+              PyTorch's NCDHW layout where ``D=Z``, ``H=Y``, ``W=X``.
+            - ``shape`` is ``self.net.identity_map.shape`` (5D, NCDHW); the
+              target spatial size is ``shape[2:] = (D_out, H_out, W_out)``.
+            - Return shape: ``(1, 1, D_out, H_out, W_out)``, float32,
+              C-contiguous on ``icon.config.device``.
+
+        Notes:
+            - Single-channel scalar inputs only. Vector/multi-channel
+              ``itk.Image`` would yield ``(Z, Y, X, C)`` from ``np.array`` and
+              break the assumed NCDHW layout — not supported here, matching
+              ICON's own preprocessing.
+            - No explicit time axis: 4D series must be split into 3D
+              timepoints by the caller; pairs are processed one volume at a
+              time.
+            - No transpose is performed; the (Z, Y, X) numpy ordering is
+              consumed directly as (D, H, W). Voxel values, not world
+              coordinates, drive the trilinear resample.
+        """
+        arr = np.array(image)
+        tensor = torch.Tensor(arr).to(icon.config.device)[None, None]
+        return F.interpolate(
+            tensor, size=shape[2:], mode="trilinear", align_corners=False
+        )
+
+    def _mask_to_resized_tensor(
+        self, mask: itk.Image, shape: torch.Size
+    ) -> torch.Tensor:
+        """Convert an itk mask image to a torch tensor resized via nearest-neighbor.
+
+        Mirrors the mask preprocessing used by
+        ``icon_registration.itk_wrapper.register_pair_with_mask`` exactly.
+
+        Axis ordering:
+            - Input ``mask`` is a scalar (single-channel) 3D ``itk.Image``
+              (typically ``uint8``/short labels) with ITK world-axis order
+              (X, Y, Z). ``np.array(mask)`` returns a C-contiguous array with
+              axes **reversed** to (Z, Y, X).
+            - ``torch.Tensor(arr)`` casts to ``float32`` (label values become
+              integral-valued floats; nearest-neighbor resampling preserves
+              them).
+            - ``[None, None]`` prepends batch and channel singletons →
+              ``(1, 1, Z, Y, X)`` in NCDHW (``D=Z``, ``H=Y``, ``W=X``).
+            - Target spatial size is ``shape[2:] = (D_out, H_out, W_out)``
+              from ``self.net.identity_map.shape``.
+            - Return shape: ``(1, 1, D_out, H_out, W_out)``, float32,
+              C-contiguous on ``icon.config.device``.
+
+        Notes:
+            - Single-channel mask inputs only; multi-label masks are encoded
+              as scalar integer values, not channels. Vector ``itk.Image``
+              inputs are not supported.
+            - No time axis: per-volume 3D processing.
+            - Resampling uses ``mode='nearest'`` (no ``align_corners``) so
+              label identities are preserved.
+        """
+        arr = np.array(mask)
+        tensor = torch.Tensor(arr).to(icon.config.device)[None, None]
+        return F.interpolate(tensor, size=shape[2:], mode="nearest")
+
+    def finetune(
+        self,
+        image_pairs: Sequence[tuple[itk.Image, itk.Image]],
+        output_model_filename: str,
+        mask_pairs: Optional[Sequence[tuple[itk.Image, itk.Image]]] = None,
+        epochs: int = 1,
+        learning_rate: float = DEFAULT_FINETUNE_LEARNING_RATE,
+    ) -> dict[str, Any]:
+        """Fine-tune the ICON network on a cohort of image pairs.
+
+        Unlike ``register()``, this method *persistently* updates the in-memory
+        network weights and saves the resulting inner-network state_dict to
+        disk. The starting weights are whatever ``set_weights_path()`` was
+        configured to (default UniGradICON pretrained weights if never set).
+
+        This method intentionally does not call ``register()`` / the ICON
+        ``register_pair`` helpers, because those wrap their optimization in a
+        ``state_dict`` save/restore that discards any persistent weight
+        changes. Here the optimizer steps act directly on ``self.net`` and
+        are not undone.
+
+        Args:
+            image_pairs: Sequence of (fixed_image, moving_image) itk image
+                pairs to fine-tune on. Caller can build this from a list of
+                images with ``itertools.combinations(images, 2)``.
+            output_model_filename: Path where the fine-tuned inner-network
+                state_dict will be saved. Suitable for reloading via
+                ``set_weights_path()`` on a new RegisterImagesICON instance.
+            mask_pairs: Optional sequence of (fixed_mask, moving_mask) itk
+                image pairs, same length as ``image_pairs``. When provided,
+                ICON's masked-loss path is used for every pair.
+            epochs: Number of full passes over ``image_pairs``. Default 1.
+            learning_rate: Adam learning rate. Default matches
+                ``icon_registration``'s per-pair fine-tune rate.
+
+        Returns:
+            Dict with keys:
+                - ``output_model_filename``: str path of saved checkpoint
+                - ``losses``: list[float], one entry per (epoch, pair)
+                - ``epochs``: int
+                - ``number_of_pairs``: int
+
+        Raises:
+            ValueError: If ``image_pairs`` is empty or ``mask_pairs`` length
+                does not match ``image_pairs``.
+        """
+        if len(image_pairs) == 0:
+            raise ValueError("At least one image pair is required for finetune.")
+        if mask_pairs is not None and len(mask_pairs) != len(image_pairs):
+            raise ValueError("mask_pairs must match image_pairs length.")
+        if epochs < 1:
+            raise ValueError("epochs must be >= 1.")
+
+        self._ensure_net()
+        assert self.net is not None
+        self.net.to(icon.config.device)
+        self.net.train()
+
+        optimizer = torch.optim.Adam(self.net.parameters(), lr=learning_rate)
+        shape = self.net.identity_map.shape
+        losses: list[float] = []
+
+        for epoch_index in range(epochs):
+            for pair_index, (fixed_image, moving_image) in enumerate(image_pairs):
+                fixed_pre = self.preprocess(fixed_image, modality=self.modality)
+                moving_pre = self.preprocess(moving_image, modality=self.modality)
+
+                fixed_resized = self._image_to_resized_tensor(fixed_pre, shape)
+                moving_resized = self._image_to_resized_tensor(moving_pre, shape)
+
+                forward_kwargs: dict[str, torch.Tensor] = {}
+                if mask_pairs is not None:
+                    fixed_mask, moving_mask = mask_pairs[pair_index]
+                    forward_kwargs["mask_A"] = self._mask_to_resized_tensor(
+                        fixed_mask, shape
+                    )
+                    forward_kwargs["mask_B"] = self._mask_to_resized_tensor(
+                        moving_mask, shape
+                    )
+
+                optimizer.zero_grad()
+                loss_tuple = self.net(fixed_resized, moving_resized, **forward_kwargs)
+                loss = loss_tuple[0]
+                loss.backward()
+                optimizer.step()
+
+                loss_value = float(loss.detach().cpu().item())
+                losses.append(loss_value)
+                self.log_info(
+                    "finetune epoch %d pair %d/%d loss=%.6f",
+                    epoch_index,
+                    pair_index + 1,
+                    len(image_pairs),
+                    loss_value,
+                )
+
+        output_path = Path(output_model_filename)
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        torch.save(self.net.regis_net.state_dict(), output_path)
+        self.weights_path = str(output_path)
+
+        return {
+            "output_model_filename": str(output_path),
+            "losses": losses,
+            "epochs": epochs,
+            "number_of_pairs": len(image_pairs),
+        }
diff --git a/src/physiomotion4d/segment_heart_simpleware.py b/src/physiomotion4d/segment_heart_simpleware.py
index 2b39a18..c9eec86 100644
--- a/src/physiomotion4d/segment_heart_simpleware.py
+++ b/src/physiomotion4d/segment_heart_simpleware.py
@@ -115,13 +115,20 @@ def __init__(self, log_level: int | str = logging.INFO):
             "SimplewareScript_heart_segmentation.py",
         )
 
-    def set_trim_mask_to_essentials(self, trim_mask: bool) -> None:
-        """Set whether to trim mask to common and critical structures.
+    def set_trim_branches(self, trim_branches: bool) -> None:
+        """Enable trimming of pulmonary and great-vessel branches.
+
+        When enabled, :meth:`trim_branches` is applied to the labelmap after
+        Simpleware segmentation, clipping the pulmonary veins and major great
+        vessels back to the cardiac region.  Trimming reduces inter-subject
+        variability in vessel extent, which simplifies AI-Ready and Sim-Ready
+        model fitting.  It is consistent with how vessels were trimmed in the
+        example KCL Heart dataset.
 
         Args:
-            trim_mask (bool): Whether to reduce to essential.
+            trim_branches (bool): Whether to trim branches to the cardiac region.
         """
-        self._trim_mask = trim_mask
+        self._trim_mask = trim_branches
 
     def set_simpleware_executable_path(self, path: str) -> None:
         """Set the path to the Simpleware Medical console executable.
@@ -332,7 +339,7 @@ def segmentation_method(self, preprocessed_image: itk.image) -> itk.image:
             labelmap_image.CopyInformation(preprocessed_image)
 
             if self._trim_mask:
-                labelmap_image = self.trim_mask_to_essentials(labelmap_image)
+                labelmap_image = self.trim_branches(labelmap_image)
 
         return labelmap_image
 
@@ -340,8 +347,16 @@ def get_landmarks(self) -> dict[str, tuple[float, float, float]]:
         """Get the landmarks."""
         return self.landmarks
 
-    def trim_mask_to_essentials(self, labelmap_image: itk.image) -> itk.image:
-        """Trim mask to essentials."""
+    def trim_branches(self, labelmap_image: itk.image) -> itk.image:
+        """Trim pulmonary and great-vessel branches back to the cardiac region.
+
+        Clips pulmonary veins and the great vessels (aorta, pulmonary artery)
+        to the portions adjacent to the heart and keeps only the largest
+        connected component of the left and right atria.  Reduces inter-subject
+        variability in vessel extent, simplifying AI-Ready and Sim-Ready model
+        fitting.  Consistent with how vessels were trimmed in the example KCL
+        Heart dataset.
+        """
 
         # Reference code for cropping aorta and pulmonary artery to
         #    portions adjacent to the heart.
diff --git a/src/physiomotion4d/workflow_convert_image_to_usd.py b/src/physiomotion4d/workflow_convert_image_to_usd.py
index eb3f853..aa0e77b 100644
--- a/src/physiomotion4d/workflow_convert_image_to_usd.py
+++ b/src/physiomotion4d/workflow_convert_image_to_usd.py
@@ -22,10 +22,21 @@
 from physiomotion4d.register_images_ants import RegisterImagesANTs
 from physiomotion4d.register_images_base import RegisterImagesBase
 from physiomotion4d.register_images_icon import RegisterImagesICON
+from physiomotion4d.segment_anatomy_base import SegmentAnatomyBase
 from physiomotion4d.segment_chest_total_segmentator import SegmentChestTotalSegmentator
+from physiomotion4d.segment_heart_simpleware import SegmentHeartSimpleware
 from physiomotion4d.transform_tools import TransformTools
 from physiomotion4d.usd_anatomy_tools import USDAnatomyTools
 
+#: Supported segmentation backend identifiers.
+SEGMENTATION_METHODS: tuple[str, ...] = (
+    "ChestTotalSegmentator",
+    "HeartSimpleware",
+)
+
+#: Supported registration backend identifiers.
+REGISTRATION_METHODS: tuple[str, ...] = ("ANTS", "ICON")
+
 
 class WorkflowConvertImageToUSD(PhysioMotion4DBase):
     """
@@ -43,7 +54,8 @@ def __init__(
         project_name: str,
         reference_image_filename: Optional[str] = None,
         number_of_registration_iterations: Optional[int] = 1,
-        registration_method: str = "icon",
+        segmentation_method: str = "ChestTotalSegmentator",
+        registration_method: str = "ICON",
         log_level: int | str = logging.INFO,
         save_registered_images: bool = True,
         save_registration_transforms: bool = True,
@@ -65,7 +77,10 @@ def __init__(
             project_name (str): Project name for USD file organization
             reference_image_filename (Optional[str]): Path to reference image file
             number_of_registration_iterations (Optional[int]): Number of registration iterations
-            registration_method (str): Registration method to use: 'ants' or 'icon' (default: 'icon')
+            segmentation_method (str): Segmentation backend to use:
+                ``'ChestTotalSegmentator'`` (default) or ``'HeartSimpleware'``.
+            registration_method (str): Registration method to use:
+                ``'ANTS'`` or ``'ICON'`` (default: ``'ICON'``).
             log_level: Logging level (default: logging.INFO)
             save_registered_images: Write registered image intermediates to
                 output_directory when True
@@ -86,11 +101,19 @@ def __init__(
         self.save_registration_transforms = save_registration_transforms
         self.save_labelmaps = save_labelmaps
 
+        # Validate segmentation method
+        if segmentation_method not in SEGMENTATION_METHODS:
+            raise ValueError(
+                f"Invalid segmentation_method '{segmentation_method}'. "
+                f"Must be one of: {', '.join(SEGMENTATION_METHODS)}."
+            )
+        self.segmentation_method = segmentation_method
+
         # Validate registration method
-        if registration_method not in ["ants", "icon"]:
+        if registration_method not in REGISTRATION_METHODS:
             raise ValueError(
                 f"Invalid registration_method '{registration_method}'. "
-                "Must be 'ants' or 'icon'."
+                f"Must be one of: {', '.join(REGISTRATION_METHODS)}."
             )
         self.registration_method = registration_method
 
@@ -99,12 +122,19 @@ def __init__(
 
         # Initialize processing components
         self.converter = ConvertImage4DTo3D(log_level=log_level)
-        self.segmenter = SegmentChestTotalSegmentator(log_level=log_level)
-        self.segmenter.contrast_threshold = 500
+        self.segmenter: SegmentAnatomyBase
+        if self.segmentation_method == "ChestTotalSegmentator":
+            chest_segmenter = SegmentChestTotalSegmentator(log_level=log_level)
+            chest_segmenter.contrast_threshold = 500
+            self.segmenter = chest_segmenter
+        else:  # HeartSimpleware
+            heart_segmenter = SegmentHeartSimpleware(log_level=log_level)
+            heart_segmenter.set_trim_branches(True)
+            self.segmenter = heart_segmenter
 
         # Initialize registration method
         self.registrar: RegisterImagesBase
-        if self.registration_method == "ants":
+        if self.registration_method == "ANTS":
             self.log_info("Initializing ANTs registration...")
             ants_registrar = RegisterImagesANTs(log_level=log_level)
             ants_registrar.set_modality("ct")
@@ -121,7 +151,7 @@ def __init__(
                     ]
                 )
             self.registrar = ants_registrar
-        else:  # icon (default)
+        else:  # ICON (default)
             self.log_info("Initializing ICON registration...")
             icon_registrar = RegisterImagesICON(log_level=log_level)
             icon_registrar.set_modality("ct")
@@ -251,6 +281,26 @@ def _load_time_series(self) -> None:
 
         self.log_info("Loaded %d time points", self._num_time_points)
 
+    def _optional_mask(self, key: str) -> itk.Image:
+        """Return ``self._fixed_segmentation[key]`` or a zero mask if absent.
+
+        Segmenters expose only the anatomy groups they actually produce
+        (see ``SegmentAnatomyBase.create_anatomy_group_masks`` —
+        ``SegmentHeartSimpleware`` omits ``lung``/``bone``/``soft_tissue``/
+        ``contrast``, while ``SegmentChestTotalSegmentator`` provides them).
+        Treating missing groups as empty (uint8 zeros matching
+        ``self._fixed_image``) lets downstream mask arithmetic run
+        uniformly for any ``self.segmenter`` choice.
+        """
+        assert self._fixed_segmentation is not None, "Fixed segmentation must be set"
+        assert self._fixed_image is not None, "Fixed image must be set"
+        if key in self._fixed_segmentation:
+            return self._fixed_segmentation[key]
+        zeros = np.zeros(itk.array_from_image(self._fixed_image).shape, dtype=np.uint8)
+        empty = itk.GetImageFromArray(zeros)
+        empty.CopyInformation(self._fixed_image)
+        return empty
+
     def _segment_and_register_frames(self) -> None:
         """Segment each frame and register to reference image."""
         self.log_info("Segmenting and registering frames...")
@@ -262,15 +312,18 @@ def _segment_and_register_frames(self) -> None:
             self._fixed_image, contrast_enhanced_study=self.contrast_enhanced
         )
 
-        # Create combined masks for registration
+        # Create combined masks for registration. Optional groups
+        # (lung/bone/contrast) are absent from segmenters that do not produce
+        # them (e.g., SegmentHeartSimpleware) — fall back to empty masks so
+        # the static/dynamic-mask sums below remain well-defined.
         assert self._fixed_segmentation is not None, "Fixed segmentation must be set"
         labelmap_mask = self._fixed_segmentation["labelmap"]
-        lung_mask = self._fixed_segmentation["lung"]
         heart_mask = self._fixed_segmentation["heart"]
         major_vessels_mask = self._fixed_segmentation["major_vessels"]
-        bone_mask = self._fixed_segmentation["bone"]
         other_mask = self._fixed_segmentation["other"]
-        contrast_mask = self._fixed_segmentation["contrast"]
+        lung_mask = self._optional_mask("lung")
+        bone_mask = self._optional_mask("bone")
+        contrast_mask = self._optional_mask("contrast")
         self._write_image_if_enabled(
             labelmap_mask,
             "fixed_image_mask.mha",
@@ -294,7 +347,7 @@ def _segment_and_register_frames(self) -> None:
 
         # Set up registrar with fixed image
         self.registrar.set_fixed_image(self._fixed_image)
-        if self.registration_method == "icon" and isinstance(
+        if self.registration_method == "ICON" and isinstance(
             self.registrar, RegisterImagesICON
         ):
             if self.contrast_enhanced:
@@ -403,15 +456,19 @@ def _generate_reference_contours(self) -> None:
         """Generate contour meshes from reference segmentation."""
         self.log_info("Generating reference contours...")
 
+        # Optional groups (lung/bone/soft_tissue/contrast) are absent from
+        # segmenters that do not produce them (e.g., SegmentHeartSimpleware)
+        # — fall back to empty masks so the static/dynamic-anatomy sums below
+        # remain well-defined.
         assert self._fixed_segmentation is not None, "Fixed segmentation must be set"
         labelmap_image = self._fixed_segmentation["labelmap"]
-        lung_mask = self._fixed_segmentation["lung"]
         heart_mask = self._fixed_segmentation["heart"]
         major_vessels_mask = self._fixed_segmentation["major_vessels"]
-        bone_mask = self._fixed_segmentation["bone"]
-        soft_tissue_mask = self._fixed_segmentation["soft_tissue"]
         other_mask = self._fixed_segmentation["other"]
-        contrast_mask = self._fixed_segmentation["contrast"]
+        lung_mask = self._optional_mask("lung")
+        bone_mask = self._optional_mask("bone")
+        soft_tissue_mask = self._optional_mask("soft_tissue")
+        contrast_mask = self._optional_mask("contrast")
 
         # Generate all anatomy contours
         all_contours = self.contour_tools.extract_contours(labelmap_image)
diff --git a/src/physiomotion4d/workflow_convert_ct_to_vtk.py b/src/physiomotion4d/workflow_convert_image_to_vtk.py
similarity index 92%
rename from src/physiomotion4d/workflow_convert_ct_to_vtk.py
rename to src/physiomotion4d/workflow_convert_image_to_vtk.py
index 5283ff0..2991ddf 100644
--- a/src/physiomotion4d/workflow_convert_ct_to_vtk.py
+++ b/src/physiomotion4d/workflow_convert_image_to_vtk.py
@@ -9,19 +9,19 @@
 Typical usage::
 
     import itk
-    from physiomotion4d import WorkflowConvertCTToVTK
+    from physiomotion4d import WorkflowConvertImageToVTK
 
     ct = itk.imread('chest_ct.nii.gz')
-    workflow = WorkflowConvertCTToVTK(segmentation_method='total_segmentator')
+    workflow = WorkflowConvertImageToVTK(segmentation_method='ChestTotalSegmentator')
     result = workflow.run_workflow(ct, contrast_enhanced_study=True)
 
     # Combined single-file output (default)
-    WorkflowConvertCTToVTK.save_combined_surface(result['surfaces'], './out', prefix='patient')
-    WorkflowConvertCTToVTK.save_combined_mesh(result['meshes'], './out', prefix='patient')
+    WorkflowConvertImageToVTK.save_combined_surface(result['surfaces'], './out', prefix='patient')
+    WorkflowConvertImageToVTK.save_combined_mesh(result['meshes'], './out', prefix='patient')
 
     # Per-group split output
-    WorkflowConvertCTToVTK.save_surfaces(result['surfaces'], './out', prefix='patient')
-    WorkflowConvertCTToVTK.save_meshes(result['meshes'], './out', prefix='patient')
+    WorkflowConvertImageToVTK.save_surfaces(result['surfaces'], './out', prefix='patient')
+    WorkflowConvertImageToVTK.save_meshes(result['meshes'], './out', prefix='patient')
 """
 
 import logging
@@ -50,20 +50,20 @@
 
 #: Supported segmentation backend identifiers.
 SEGMENTATION_METHODS: tuple[str, ...] = (
-    "total_segmentator",
-    "simpleware_heart",
+    "ChestTotalSegmentator",
+    "HeartSimpleware",
 )
 
 
-class WorkflowConvertCTToVTK(PhysioMotion4DBase):
+class WorkflowConvertImageToVTK(PhysioMotion4DBase):
     """Segment a CT image and produce per-anatomy-group VTK surfaces and meshes.
 
     **Segmentation backends**
 
-    - ``'total_segmentator'`` — :class:`SegmentChestTotalSegmentator` (CPU-capable,
-      default).
-    - ``'simpleware_heart'`` — :class:`SegmentHeartSimpleware` (cardiac only; requires
-      a Simpleware Medical installation).
+    - ``'ChestTotalSegmentator'`` — :class:`SegmentChestTotalSegmentator`
+      (CPU-capable, default).
+    - ``'HeartSimpleware'`` — :class:`SegmentHeartSimpleware` (cardiac only;
+      requires a Simpleware Medical installation).
 
     **Output anatomy groups**
 
@@ -86,7 +86,7 @@ class WorkflowConvertCTToVTK(PhysioMotion4DBase):
 
     :meth:`run_workflow` performs *no* file I/O.  Use the static helpers
     :meth:`save_surfaces`, :meth:`save_meshes`, :meth:`save_combined_surface`, and
-    :meth:`save_combined_mesh` — or the CLI ``physiomotion4d-convert-ct-to-vtk`` — to
+    :meth:`save_combined_mesh` — or the CLI ``physiomotion4d-convert-image-to-vtk`` — to
     write results to disk.
     """
 
@@ -97,14 +97,14 @@ class WorkflowConvertCTToVTK(PhysioMotion4DBase):
 
     def __init__(
         self,
-        segmentation_method: str = "total_segmentator",
+        segmentation_method: str = "ChestTotalSegmentator",
         log_level: int | str = logging.INFO,
     ) -> None:
         """Initialize the workflow.
 
         Args:
             segmentation_method: Segmentation backend to use.  One of
-                ``'total_segmentator'`` (default) or ``'simpleware_heart'``.
+                ``'ChestTotalSegmentator'`` (default) or ``'HeartSimpleware'``.
             log_level: Logging level.  Default: ``logging.INFO``.
 
         Raises:
@@ -138,17 +138,17 @@ def __init__(
 
     def _create_segmenter(self) -> SegmentAnatomyBase:
         """Instantiate the chosen segmentation backend (lazy import)."""
-        if self.segmentation_method_name == "total_segmentator":
+        if self.segmentation_method_name == "ChestTotalSegmentator":
             from physiomotion4d.segment_chest_total_segmentator import (
                 SegmentChestTotalSegmentator,
             )
 
             return SegmentChestTotalSegmentator(log_level=self.log_level)
-        if self.segmentation_method_name == "simpleware_heart":
+        if self.segmentation_method_name == "HeartSimpleware":
             from physiomotion4d.segment_heart_simpleware import SegmentHeartSimpleware
 
             segmenter = SegmentHeartSimpleware(log_level=self.log_level)
-            segmenter.set_trim_mask_to_essentials(True)
+            segmenter.set_trim_branches(True)
             return segmenter
         raise ValueError(
             f"Unknown segmentation method: {self.segmentation_method_name}"
@@ -158,7 +158,7 @@ def _get_label_info_for_group(self, group: str) -> tuple[list[str], list[int]]:
         """Return ``(label_names, label_ids)`` for *group* from the active segmenter.
 
         Reads the segmenter's :class:`AnatomyTaxonomy`. Returns empty lists if
-        the group is not present (e.g. simpleware_heart does not register
+        the group is not present (e.g. HeartSimpleware does not register
         lung/bone).
         """
         assert self._segmenter is not None, (
@@ -268,7 +268,7 @@ def run_workflow(
         Raises:
             ValueError: If any name in *anatomy_groups* is invalid.
         """
-        self.log_section("STARTING CT TO VTK WORKFLOW")
+        self.log_section("STARTING IMAGE TO VTK WORKFLOW")
 
         # Validate requested groups
         if anatomy_groups is not None:
@@ -327,7 +327,7 @@ def run_workflow(
                 self._annotate(mesh, group, label_names, label_ids, color)
                 meshes[group] = mesh
 
-        self.log_section("CT TO VTK WORKFLOW COMPLETE")
+        self.log_section("IMAGE TO VTK WORKFLOW COMPLETE")
         self.log_info("Surfaces extracted: %d", len(surfaces))
         self.log_info("Meshes extracted:   %d", len(meshes))
 
diff --git a/src/physiomotion4d/workflow_fit_statistical_model_to_patient.py b/src/physiomotion4d/workflow_fit_statistical_model_to_patient.py
index 77f8c16..72945bc 100644
--- a/src/physiomotion4d/workflow_fit_statistical_model_to_patient.py
+++ b/src/physiomotion4d/workflow_fit_statistical_model_to_patient.py
@@ -37,7 +37,7 @@
 from physiomotion4d.register_models_icp import RegisterModelsICP
 from physiomotion4d.register_models_pca import RegisterModelsPCA
 from physiomotion4d.transform_tools import TransformTools
-from physiomotion4d.workflow_convert_ct_to_vtk import WorkflowConvertCTToVTK
+from physiomotion4d.workflow_convert_image_to_vtk import WorkflowConvertImageToVTK
 
 
 def _load_tubetk() -> Any:
@@ -137,7 +137,7 @@ def __init__(
         template_model: pv.DataSet,
         patient_models: list[pv.DataSet] | None = None,
         patient_image: Optional[itk.Image] = None,
-        segmentation_method: str = "simpleware_heart",
+        segmentation_method: str = "HeartSimpleware",
         log_level: int | str = logging.INFO,
     ):
         """Initialize the model-to-image-and-model registration pipeline.
@@ -149,6 +149,11 @@ def __init__(
             patient_image: Optional patient image providing the target coordinate frame.
                 If None, a reference image is created from the patient model surface
                 via create_reference_image (contour_tools).
+            segmentation_method: Segmentation backend used by
+                WorkflowConvertImageToVTK when patient_models is None and
+                patient_image is provided. One of ``'HeartSimpleware'`` (default)
+                or ``'ChestTotalSegmentator'``. Ignored when patient_models is
+                supplied.
             log_level: Logging level (logging.DEBUG, logging.INFO, logging.WARNING).
                 Default: logging.INFO
         """
@@ -167,11 +172,11 @@ def __init__(
         self.template_labelmap_background_ids: Optional[list[int]] = None
 
         if patient_models is None and patient_image is not None:
-            convert_ct_to_vtk = WorkflowConvertCTToVTK(
+            convert_image_to_vtk = WorkflowConvertImageToVTK(
                 segmentation_method=segmentation_method,
                 log_level=log_level,
             )
-            patient_models_data = convert_ct_to_vtk.run_workflow(
+            patient_models_data = convert_image_to_vtk.run_workflow(
                 input_image=patient_image,
                 contrast_enhanced_study=False,
                 anatomy_groups=["heart"],
diff --git a/tests/test_cli_smoke.py b/tests/test_cli_smoke.py
index b130298..dcb236a 100644
--- a/tests/test_cli_smoke.py
+++ b/tests/test_cli_smoke.py
@@ -9,7 +9,7 @@
 
 
 CLI_MODULES = [
-    "physiomotion4d.cli.convert_ct_to_vtk",
+    "physiomotion4d.cli.convert_image_to_vtk",
     "physiomotion4d.cli.convert_image_4d_to_3d",
     "physiomotion4d.cli.convert_image_to_usd",
     "physiomotion4d.cli.convert_vtk_to_usd",
diff --git a/tutorials/README.md b/tutorials/README.md
index bd24303..805988d 100644
--- a/tutorials/README.md
+++ b/tutorials/README.md
@@ -14,7 +14,7 @@ dataset licensing, and expected directory layout.
 | # | Script | Primary API | Dataset |
 |---|--------|-------------|---------|
 | 1 | [tutorial_01_heart_gated_ct_to_usd.py](tutorial_01_heart_gated_ct_to_usd.py) | `WorkflowConvertImageToUSD` | Slicer-Heart-CT (prepare first) |
-| 2 | [tutorial_02_ct_to_vtk.py](tutorial_02_ct_to_vtk.py) | `WorkflowConvertCTToVTK` | Slicer-Heart-CT (prepare first) |
+| 2 | [tutorial_02_ct_to_vtk.py](tutorial_02_ct_to_vtk.py) | `WorkflowConvertImageToVTK` | Slicer-Heart-CT (prepare first) |
 | 3 | [tutorial_03_create_statistical_model.py](tutorial_03_create_statistical_model.py) | `WorkflowCreateStatisticalModel` | KCL-Heart-Model (manual) |
 | 4 | [tutorial_04_fit_statistical_model_to_patient.py](tutorial_04_fit_statistical_model_to_patient.py) | `WorkflowFitStatisticalModelToPatient` | KCL-Heart-Model plus Tutorial 3 output |
 | 5 | [tutorial_05_vtk_to_usd.py](tutorial_05_vtk_to_usd.py) | `WorkflowConvertVTKToUSD` | Output of tutorial 2 |
diff --git a/tutorials/tutorial_01_heart_gated_ct_to_usd.py b/tutorials/tutorial_01_heart_gated_ct_to_usd.py
index b732789..19281cb 100644
--- a/tutorials/tutorial_01_heart_gated_ct_to_usd.py
+++ b/tutorials/tutorial_01_heart_gated_ct_to_usd.py
@@ -36,8 +36,8 @@
 
 Weaknesses / Limitations
 ------------------------
-- Requires a GPU for ICON registration (``registration_method='icon'``); use
-  ``registration_method='ants'`` for CPU-only environments (about 10x slower).
+- Requires a GPU for ICON registration (``registration_method='ICON'``); use
+  ``registration_method='ANTS'`` for CPU-only environments (about 10x slower).
 - Segmentation quality depends on TotalSegmentator's training distribution;
   unusual pathologies or pediatric anatomy may degrade results.
 - Large 4D datasets (>20 phases, high resolution) can require 32 GB+ RAM.
@@ -93,7 +93,7 @@
     FULL_DATA_DIR = DATA_DIR / "Slicer-Heart-CT"
     TEST_DATA_DIR = DATA_DIR / "test" / "slicer_heart_small"
     OUTPUT_DIR = TUTORIALS_DIR / "output" / "tutorial_01"
-    REGISTRATION_METHOD = "ants"
+    REGISTRATION_METHOD = "ANTS"
     LOG_LEVEL = logging.INFO
 
     # %%
diff --git a/tutorials/tutorial_02_ct_to_vtk.py b/tutorials/tutorial_02_ct_to_vtk.py
index 02c406a..a961a36 100644
--- a/tutorials/tutorial_02_ct_to_vtk.py
+++ b/tutorials/tutorial_02_ct_to_vtk.py
@@ -24,7 +24,7 @@
 import pyvista as pv
 
 from physiomotion4d.test_tools import TestTools
-from physiomotion4d.workflow_convert_ct_to_vtk import WorkflowConvertCTToVTK
+from physiomotion4d.workflow_convert_image_to_vtk import WorkflowConvertImageToVTK
 
 # nnUNetv2 (used by TotalSegmentator inside several workflows) spawns a
 # multiprocessing.Pool. On Windows the spawn start method re-imports this
@@ -67,8 +67,8 @@
 
     # %%
     # Workflow initialization
-    workflow = WorkflowConvertCTToVTK(
-        segmentation_method="total_segmentator",
+    workflow = WorkflowConvertImageToVTK(
+        segmentation_method="ChestTotalSegmentator",
         log_level=log_level,
     )
 
@@ -82,14 +82,14 @@
     # %%
     # Result saving
     surface_file = Path(
-        WorkflowConvertCTToVTK.save_combined_surface(
+        WorkflowConvertImageToVTK.save_combined_surface(
             result["surfaces"],
             str(output_dir),
             prefix="patient",
         )
     )
     mesh_file = Path(
-        WorkflowConvertCTToVTK.save_combined_mesh(
+        WorkflowConvertImageToVTK.save_combined_mesh(
             result["meshes"],
             str(output_dir),
             prefix="patient",
diff --git a/tutorials/tutorial_07_dirlab_pca_model.py b/tutorials/tutorial_07_dirlab_pca_model.py
index edfae3d..b0dc589 100644
--- a/tutorials/tutorial_07_dirlab_pca_model.py
+++ b/tutorials/tutorial_07_dirlab_pca_model.py
@@ -18,7 +18,7 @@
 import pyvista as pv
 
 from physiomotion4d.contour_tools import ContourTools
-from physiomotion4d.workflow_convert_ct_to_vtk import WorkflowConvertCTToVTK
+from physiomotion4d.workflow_convert_image_to_vtk import WorkflowConvertImageToVTK
 from physiomotion4d.workflow_create_statistical_model import (
     WorkflowCreateStatisticalModel,
 )
@@ -116,8 +116,8 @@ def create_meshes(
 
             print(f"Segmenting {case_prefix} from {phase_files[0].name}")
             image = itk.imread(str(phase_files[0]))
-            workflow = WorkflowConvertCTToVTK(
-                segmentation_method="total_segmentator",
+            workflow = WorkflowConvertImageToVTK(
+                segmentation_method="ChestTotalSegmentator",
                 log_level=log_level,
             )
             result = workflow.run_workflow(